From 8ae7d310e8c9a92cd2555f9022843084108228ae Mon Sep 17 00:00:00 2001 From: John Schember Date: Sun, 26 Jun 2011 10:32:17 -0400 Subject: [PATCH 01/22] Store: OpenSearch based store base class. OpenSearch module added. Make some OPDS store use the new OpenSearchStore class. --- src/calibre/gui2/store/archive_org_plugin.py | 81 +- src/calibre/gui2/store/opensearch_store.py | 72 + .../gui2/store/pragmatic_bookshelf_plugin.py | 80 +- src/calibre/gui2/store/search_result.py | 1 + src/calibre/utils/opensearch/__init__.py | 4 + src/calibre/utils/opensearch/client.py | 39 + src/calibre/utils/opensearch/description.py | 127 + src/calibre/utils/opensearch/osfeedparser.py | 2837 +++++++++++++++++ src/calibre/utils/opensearch/query.py | 66 + src/calibre/utils/opensearch/results.py | 131 + src/calibre/utils/opensearch/url.py | 8 + 11 files changed, 3311 insertions(+), 135 deletions(-) create mode 100644 src/calibre/gui2/store/opensearch_store.py create mode 100644 src/calibre/utils/opensearch/__init__.py create mode 100644 src/calibre/utils/opensearch/client.py create mode 100644 src/calibre/utils/opensearch/description.py create mode 100644 src/calibre/utils/opensearch/osfeedparser.py create mode 100644 src/calibre/utils/opensearch/query.py create mode 100644 src/calibre/utils/opensearch/results.py create mode 100644 src/calibre/utils/opensearch/url.py diff --git a/src/calibre/gui2/store/archive_org_plugin.py b/src/calibre/gui2/store/archive_org_plugin.py index e8e96b3839..944b7aeba1 100644 --- a/src/calibre/gui2/store/archive_org_plugin.py +++ b/src/calibre/gui2/store/archive_org_plugin.py @@ -6,84 +6,35 @@ __license__ = 'GPL 3' __copyright__ = '2011, John Schember ' __docformat__ = 'restructuredtext en' -import urllib from contextlib import closing from lxml import html -from PyQt4.Qt import QUrl - -from calibre import browser, url_slash_cleaner -from calibre.gui2 import open_url -from calibre.gui2.store import StorePlugin +from calibre import browser from calibre.gui2.store.basic_config import BasicStoreConfig +from calibre.gui2.store.opensearch_store import OpenSearchStore from calibre.gui2.store.search_result import SearchResult -from calibre.gui2.store.web_store_dialog import WebStoreDialog -class ArchiveOrgStore(BasicStoreConfig, StorePlugin): - - def open(self, parent=None, detail_item=None, external=False): - url = 'http://www.archive.org/details/texts' - - if detail_item: - detail_item = url_slash_cleaner('http://www.archive.org' + detail_item) - - if external or self.config.get('open_external', False): - open_url(QUrl(url_slash_cleaner(detail_item if detail_item else url))) - else: - d = WebStoreDialog(self.gui, url, parent, detail_item) - d.setWindowTitle(self.name) - d.set_tags(self.config.get('tags', '')) - d.exec_() +class ArchiveOrgStore(BasicStoreConfig, OpenSearchStore): + open_search_url = 'http://bookserver.archive.org/catalog/opensearch.xml' + web_url = 'http://www.archive.org/details/texts' + + # http://bookserver.archive.org/catalog/ + def search(self, query, max_results=10, timeout=60): - query = query + ' AND mediatype:texts' - url = 'http://www.archive.org/search.php?query=' + urllib.quote(query) - - br = browser() - - counter = max_results - with closing(br.open(url, timeout=timeout)) as f: - doc = html.fromstring(f.read()) - for data in doc.xpath('//td[@class="hitCell"]'): - if counter <= 0: - break - - id = ''.join(data.xpath('.//a[@class="titleLink"]/@href')) - if not id: - continue - - title = ''.join(data.xpath('.//a[@class="titleLink"]//text()')) - authors = data.xpath('.//text()') - if not authors: - continue - author = None - for a in authors: - if '-' in a: - author = a.replace('-', ' ').strip() - if author: - break - if not author: - continue - - counter -= 1 - - s = SearchResult() - s.title = title.strip() - s.author = author.strip() - s.price = '$0.00' - s.detail_item = id.strip() - s.drm = SearchResult.DRM_UNLOCKED - - yield s - + for s in OpenSearchStore.search(self, query, max_results, timeout): + s.detail_item = 'http://www.archive.org/details/' + s.detail_item.split(':')[-1] + s.price = '$0.00' + s.drm = SearchResult.DRM_UNLOCKED + yield s +''' def get_details(self, search_result, timeout): - url = url_slash_cleaner('http://www.archive.org' + search_result.detail_item) - br = browser() - with closing(br.open(url, timeout=timeout)) as nf: + with closing(br.open(search_result.detail_item, timeout=timeout)) as nf: idata = html.fromstring(nf.read()) formats = ', '.join(idata.xpath('//p[@id="dl" and @class="content"]//a/text()')) search_result.formats = formats.upper() return True +''' diff --git a/src/calibre/gui2/store/opensearch_store.py b/src/calibre/gui2/store/opensearch_store.py new file mode 100644 index 0000000000..f473608309 --- /dev/null +++ b/src/calibre/gui2/store/opensearch_store.py @@ -0,0 +1,72 @@ +# -*- coding: utf-8 -*- + +from __future__ import (unicode_literals, division, absolute_import, print_function) + +__license__ = 'GPL 3' +__copyright__ = '2011, John Schember ' +__docformat__ = 'restructuredtext en' + +import mimetypes +import urllib + +from PyQt4.Qt import QUrl + +from calibre.gui2 import open_url +from calibre.gui2.store import StorePlugin +from calibre.gui2.store.search_result import SearchResult +from calibre.gui2.store.web_store_dialog import WebStoreDialog +from calibre.utils.opensearch import Client + +class OpenSearchStore(StorePlugin): + + open_search_url = '' + web_url = '' + + def open(self, parent=None, detail_item=None, external=False): + if external or self.config.get('open_external', False): + open_url(QUrl(detail_item if detail_item else self.url)) + else: + d = WebStoreDialog(self.gui, self.url, parent, detail_item) + d.setWindowTitle(self.name) + d.set_tags(self.config.get('tags', '')) + d.exec_() + + def search(self, query, max_results=10, timeout=60): + if not hasattr(self, 'open_search_url'): + return + + client = Client(self.open_search_url) + results = client.search(urllib.quote_plus(query), max_results) + + counter = max_results + for r in results: + if counter <= 0: + break + counter -= 1 + + s = SearchResult() + + s.detail_item = r.get('id', '') + + links = r.get('links', None) + for l in links: + if l.get('rel', None): + if l['rel'] == u'http://opds-spec.org/image/thumbnail': + s.cover_url = l.get('href', '') + elif l['rel'] == u'http://opds-spec.org/acquisition/buy': + s.detail_item = l.get('href', s.detail_item) + elif l['rel'] == u'http://opds-spec.org/acquisition': + s.downloads.append((l.get('type', ''), l.get('href', ''))) + + formats = [] + for mime, url in s.downloads: + ext = mimetypes.guess_extension(mime) + if ext: + formats.append(ext[1:]) + s.formats = ', '.join(formats) + + s.title = r.get('title', '') + s.author = r.get('author', '') + s.price = r.get('price', '') + + yield s diff --git a/src/calibre/gui2/store/pragmatic_bookshelf_plugin.py b/src/calibre/gui2/store/pragmatic_bookshelf_plugin.py index f3803bbcea..671186ba87 100644 --- a/src/calibre/gui2/store/pragmatic_bookshelf_plugin.py +++ b/src/calibre/gui2/store/pragmatic_bookshelf_plugin.py @@ -6,79 +6,19 @@ __license__ = 'GPL 3' __copyright__ = '2011, John Schember ' __docformat__ = 'restructuredtext en' -import urllib -from contextlib import closing - -from lxml import html - -from PyQt4.Qt import QUrl - -from calibre import browser, url_slash_cleaner -from calibre.gui2 import open_url -from calibre.gui2.store import StorePlugin from calibre.gui2.store.basic_config import BasicStoreConfig +from calibre.gui2.store.opensearch_store import OpenSearchStore from calibre.gui2.store.search_result import SearchResult -from calibre.gui2.store.web_store_dialog import WebStoreDialog -class PragmaticBookshelfStore(BasicStoreConfig, StorePlugin): +class PragmaticBookshelfStore(BasicStoreConfig, OpenSearchStore): - def open(self, parent=None, detail_item=None, external=False): - url = 'http://pragprog.com/' - - if external or self.config.get('open_external', False): - open_url(QUrl(url_slash_cleaner(detail_item if detail_item else url))) - else: - d = WebStoreDialog(self.gui, url, parent, detail_item) - d.setWindowTitle(self.name) - d.set_tags(self.config.get('tags', '')) - d.exec_() + open_search_url = 'http://pragprog.com/catalog/search-description' + web_url = 'http://pragprog.com/' + + # http://pragprog.com/catalog.opds def search(self, query, max_results=10, timeout=60): - ''' - OPDS based search. - - We really should get the catelog from http://pragprog.com/catalog.opds - and look for the application/opensearchdescription+xml entry. - Then get the opensearch description to get the search url and - format. However, we are going to be lazy and hard code it. - ''' - url = 'http://pragprog.com/catalog/search?q=' + urllib.quote_plus(query) - - br = browser() - - counter = max_results - with closing(br.open(url, timeout=timeout)) as f: - # Use html instead of etree as html allows us - # to ignore the namespace easily. - doc = html.fromstring(f.read()) - for data in doc.xpath('//entry'): - if counter <= 0: - break - - id = ''.join(data.xpath('.//link[@rel="http://opds-spec.org/acquisition/buy"]/@href')) - if not id: - continue - - price = ''.join(data.xpath('.//price/@currencycode')).strip() - price += ' ' - price += ''.join(data.xpath('.//price/text()')).strip() - if not price.strip(): - continue - - cover_url = ''.join(data.xpath('.//link[@rel="http://opds-spec.org/cover"]/@href')) - - title = ''.join(data.xpath('.//title/text()')) - author = ''.join(data.xpath('.//author//text()')) - - counter -= 1 - - s = SearchResult() - s.cover_url = cover_url - s.title = title.strip() - s.author = author.strip() - s.price = price.strip() - s.detail_item = id.strip() - s.drm = SearchResult.DRM_UNLOCKED - s.formats = 'EPUB, PDF, MOBI' - - yield s + for s in OpenSearchStore.search(self, query, max_results, timeout): + s.drm = SearchResult.DRM_UNLOCKED + s.formats = 'EPUB, PDF, MOBI' + yield s diff --git a/src/calibre/gui2/store/search_result.py b/src/calibre/gui2/store/search_result.py index 7d6ac5acad..bbe5b83c38 100644 --- a/src/calibre/gui2/store/search_result.py +++ b/src/calibre/gui2/store/search_result.py @@ -22,6 +22,7 @@ class SearchResult(object): self.detail_item = '' self.drm = None self.formats = '' + self.downloads = [] self.affiliate = False self.plugin_author = '' diff --git a/src/calibre/utils/opensearch/__init__.py b/src/calibre/utils/opensearch/__init__.py new file mode 100644 index 0000000000..f2d51febc4 --- /dev/null +++ b/src/calibre/utils/opensearch/__init__.py @@ -0,0 +1,4 @@ +from description import Description +from query import Query +from client import Client +from results import Results diff --git a/src/calibre/utils/opensearch/client.py b/src/calibre/utils/opensearch/client.py new file mode 100644 index 0000000000..434e921568 --- /dev/null +++ b/src/calibre/utils/opensearch/client.py @@ -0,0 +1,39 @@ +from description import Description +from query import Query +from results import Results + +class Client: + + """This is the class you'll probably want to be using. You simply + pass the constructor the url for the service description file and + issue a search and get back results as an iterable Results object. + + The neat thing about a Results object is that it will seamlessly + handle fetching more results from the opensearch server when it can... + so you just need to iterate and can let the paging be taken care of + for you. + + from opensearch import Client + client = Client(description_url) + results = client.search("computer") + for result in results: + print result.title + """ + + def __init__(self, url, agent="python-opensearch "): + self.agent = agent + self.description = Description(url, self.agent) + + def search(self, search_terms, page_size=25): + """Perform a search and get back a results object + """ + url = self.description.get_best_template() + query = Query(url) + + # set up initial values + query.searchTerms = search_terms + query.count = page_size + + # run the results + return Results(query, agent=self.agent) + diff --git a/src/calibre/utils/opensearch/description.py b/src/calibre/utils/opensearch/description.py new file mode 100644 index 0000000000..d486e615df --- /dev/null +++ b/src/calibre/utils/opensearch/description.py @@ -0,0 +1,127 @@ +from urllib2 import urlopen, Request +from xml.dom.minidom import parse +from url import URL + +class Description: + """A class for representing OpenSearch Description files. + """ + + def __init__(self, url="", agent=""): + """The constructor which may pass an optional url to load from. + + d = Description("http://www.example.com/description") + """ + self.agent = agent + if url: + self.load(url) + + + def load(self, url): + """For loading up a description object from a url. Normally + you'll probably just want to pass a URL into the constructor. + """ + req = Request(url, headers={'User-Agent':self.agent}) + self.dom = parse(urlopen(req)) + + # version 1.1 has repeating Url elements + self.urls = self._get_urls() + + # this is version 1.0 specific + self.url = self._get_element_text('Url') + self.format = self._get_element_text('Format') + + self.shortname = self._get_element_text('ShortName') + self.longname = self._get_element_text('LongName') + self.description = self._get_element_text('Description') + self.image = self._get_element_text('Image') + self.samplesearch = self._get_element_text('SampleSearch') + self.developer = self._get_element_text('Developer') + self.contact = self._get_element_text('Contact') + self.attribution = self._get_element_text('Attribution') + self.syndicationright = self._get_element_text('SyndicationRight') + + tag_text = self._get_element_text('Tags') + if tag_text != None: + self.tags = tag_text.split(" ") + + if self._get_element_text('AdultContent') == 'true': + self.adultcontent = True + else: + self.adultcontent = False + + def get_url_by_type(self, type): + """Walks available urls and returns them by type. Only + appropriate in opensearch v1.1 where there can be multiple + query targets. Returns none if no such type is found. + + url = description.get_url_by_type('application/rss+xml') + """ + for url in self.urls: + if url.type == type: + return url + return None + + def get_best_template(self): + """OK, best is a value judgement, but so be it. You'll get + back either the atom, rss or first template available. This + method handles the main difference between opensearch v1.0 and v1.1 + """ + # version 1.0 + if self.url: + return self.url + + # atom + if self.get_url_by_type('application/atom+xml'): + return self.get_url_by_type('application/atom+xml').template + + # rss + if self.get_url_by_type('application/rss+xml'): + return self.get_url_by_type('application/rss+xml').template + + # other possible rss type + if self.get_url_by_type('text/xml'): + return self.get_url_by_Type('text/xml').template + + # otherwise just the first one + if len(self.urls) > 0: + return self.urls[0].template + + # out of luck + return Nil + + + # these are internal methods for querying xml + + def _get_element_text(self, tag): + elements = self._get_elements(tag) + if not elements: + return None + return self._get_text(elements[0].childNodes) + + def _get_attribute_text(self, tag, attribute): + elements = self._get_elements(tag) + if not elements: + return '' + return elements[0].getAttribute('template') + + def _get_elements(self, tag): + return self.dom.getElementsByTagName(tag) + + def _get_text(self, nodes): + text = '' + for node in nodes: + if node.nodeType == node.TEXT_NODE: + text += node.data + return text.strip() + + def _get_urls(self): + urls = [] + for element in self._get_elements('Url'): + template = element.getAttribute('template') + type = element.getAttribute('type') + if template and type: + url = URL() + url.template = template + url.type = type + urls.append(url) + return urls diff --git a/src/calibre/utils/opensearch/osfeedparser.py b/src/calibre/utils/opensearch/osfeedparser.py new file mode 100644 index 0000000000..364de2b26c --- /dev/null +++ b/src/calibre/utils/opensearch/osfeedparser.py @@ -0,0 +1,2837 @@ +#!/usr/bin/env python +"""Universal feed parser + +Handles RSS 0.9x, RSS 1.0, RSS 2.0, CDF, Atom 0.3, and Atom 1.0 feeds + +Visit http://feedparser.org/ for the latest version +Visit http://feedparser.org/docs/ for the latest documentation + +Required: Python 2.1 or later +Recommended: Python 2.3 or later +Recommended: CJKCodecs and iconv_codec +""" + +__version__ = "4.0.2"# + "$Revision: 1.88 $"[11:15] + "-cvs" +__license__ = """Copyright (c) 2002-2005, Mark Pilgrim, All rights reserved. + +Redistribution and use in source and binary forms, with or without modification, +are permitted provided that the following conditions are met: + +* Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. +* Redistributions in binary form must reproduce the above copyright notice, + this list of conditions and the following disclaimer in the documentation + and/or other materials provided with the distribution. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS' +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE.""" +__author__ = "Mark Pilgrim " +__contributors__ = ["Jason Diamond ", + "John Beimler ", + "Fazal Majid ", + "Aaron Swartz ", + "Kevin Marks "] +_debug = 0 + +# HTTP "User-Agent" header to send to servers when downloading feeds. +# If you are embedding feedparser in a larger application, you should +# change this to your application name and URL. +# Changed by John Schember +from calibre import random_user_agent +USER_AGENT = random_user_agent() + +# HTTP "Accept" header to send to servers when downloading feeds. If you don't +# want to send an Accept header, set this to None. +ACCEPT_HEADER = "application/atom+xml,application/rdf+xml,application/rss+xml,application/x-netcdf,application/xml;q=0.9,text/xml;q=0.2,*/*;q=0.1" + +# List of preferred XML parsers, by SAX driver name. These will be tried first, +# but if they're not installed, Python will keep searching through its own list +# of pre-installed parsers until it finds one that supports everything we need. +PREFERRED_XML_PARSERS = ["drv_libxml2"] + +# If you want feedparser to automatically run HTML markup through HTML Tidy, set +# this to 1. Requires mxTidy +# or utidylib . +TIDY_MARKUP = 0 + +# List of Python interfaces for HTML Tidy, in order of preference. Only useful +# if TIDY_MARKUP = 1 +PREFERRED_TIDY_INTERFACES = ["uTidy", "mxTidy"] + +# ---------- required modules (should come with any Python distribution) ---------- +import sgmllib, re, sys, copy, urlparse, time, rfc822, types, cgi +try: + from cStringIO import StringIO as _StringIO +except: + from StringIO import StringIO as _StringIO + +# ---------- optional modules (feedparser will work without these, but with reduced functionality) ---------- + +# gzip is included with most Python distributions, but may not be available if you compiled your own +try: + import gzip +except: + gzip = None +try: + import zlib +except: + zlib = None + +# timeoutsocket allows feedparser to time out rather than hang forever on ultra-slow servers. +# Python 2.3 now has this functionality available in the standard socket library, so under +# 2.3 or later you don't need to install anything. In fact, under Python 2.4, timeoutsocket +# write all sorts of crazy errors to stderr while running my unit tests, so it's probably +# outlived its usefulness. +import socket +if hasattr(socket, 'setdefaulttimeout'): + socket.setdefaulttimeout(20) +else: + try: + import timeoutsocket # http://www.timo-tasi.org/python/timeoutsocket.py + timeoutsocket.setDefaultSocketTimeout(20) + except ImportError: + pass +import urllib, urllib2 + +# If a real XML parser is available, feedparser will attempt to use it. feedparser has +# been tested with the built-in SAX parser, PyXML, and libxml2. On platforms where the +# Python distribution does not come with an XML parser (such as Mac OS X 10.2 and some +# versions of FreeBSD), feedparser will quietly fall back on regex-based parsing. +try: + import xml.sax + xml.sax.make_parser(PREFERRED_XML_PARSERS) # test for valid parsers + from xml.sax.saxutils import escape as _xmlescape + _XML_AVAILABLE = 1 +except: + _XML_AVAILABLE = 0 + def _xmlescape(data): + data = data.replace('&', '&') + data = data.replace('>', '>') + data = data.replace('<', '<') + return data + +# base64 support for Atom feeds that contain embedded binary data +try: + import base64, binascii +except: + base64 = binascii = None + +# cjkcodecs and iconv_codec provide support for more character encodings. +# Both are available from http://cjkpython.i18n.org/ +try: + import cjkcodecs.aliases +except: + pass +try: + import iconv_codec +except: + pass + +# ---------- don't touch these ---------- +class ThingsNobodyCaresAboutButMe(Exception): pass +class CharacterEncodingOverride(ThingsNobodyCaresAboutButMe): pass +class CharacterEncodingUnknown(ThingsNobodyCaresAboutButMe): pass +class NonXMLContentType(ThingsNobodyCaresAboutButMe): pass +class UndeclaredNamespace(Exception): pass + +sgmllib.tagfind = re.compile('[a-zA-Z][-_.:a-zA-Z0-9]*') +sgmllib.special = re.compile('' % (tag, ''.join([' %s="%s"' % t for t in attrs])), escape=0) + + # match namespaces + if tag.find(':') <> -1: + prefix, suffix = tag.split(':', 1) + else: + prefix, suffix = '', tag + prefix = self.namespacemap.get(prefix, prefix) + if prefix: + prefix = prefix + '_' + + # special hack for better tracking of empty textinput/image elements in illformed feeds + if (not prefix) and tag not in ('title', 'link', 'description', 'name'): + self.intextinput = 0 + if (not prefix) and tag not in ('title', 'link', 'description', 'url', 'href', 'width', 'height'): + self.inimage = 0 + + # call special handler (if defined) or default handler + methodname = '_start_' + prefix + suffix + try: + method = getattr(self, methodname) + return method(attrsD) + except AttributeError: + return self.push(prefix + suffix, 1) + + def unknown_endtag(self, tag): + if _debug: sys.stderr.write('end %s\n' % tag) + # match namespaces + if tag.find(':') <> -1: + prefix, suffix = tag.split(':', 1) + else: + prefix, suffix = '', tag + prefix = self.namespacemap.get(prefix, prefix) + if prefix: + prefix = prefix + '_' + + # call special handler (if defined) or default handler + methodname = '_end_' + prefix + suffix + try: + method = getattr(self, methodname) + method() + except AttributeError: + self.pop(prefix + suffix) + + # track inline content + if self.incontent and self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'): + # element declared itself as escaped markup, but it isn't really + self.contentparams['type'] = 'application/xhtml+xml' + if self.incontent and self.contentparams.get('type') == 'application/xhtml+xml': + tag = tag.split(':')[-1] + self.handle_data('' % tag, escape=0) + + # track xml:base and xml:lang going out of scope + if self.basestack: + self.basestack.pop() + if self.basestack and self.basestack[-1]: + self.baseuri = self.basestack[-1] + if self.langstack: + self.langstack.pop() + if self.langstack: # and (self.langstack[-1] is not None): + self.lang = self.langstack[-1] + + def handle_charref(self, ref): + # called for each character reference, e.g. for ' ', ref will be '160' + if not self.elementstack: return + ref = ref.lower() + if ref in ('34', '38', '39', '60', '62', 'x22', 'x26', 'x27', 'x3c', 'x3e'): + text = '&#%s;' % ref + else: + if ref[0] == 'x': + c = int(ref[1:], 16) + else: + c = int(ref) + text = unichr(c).encode('utf-8') + self.elementstack[-1][2].append(text) + + def handle_entityref(self, ref): + # called for each entity reference, e.g. for '©', ref will be 'copy' + if not self.elementstack: return + if _debug: sys.stderr.write('entering handle_entityref with %s\n' % ref) + if ref in ('lt', 'gt', 'quot', 'amp', 'apos'): + text = '&%s;' % ref + else: + # entity resolution graciously donated by Aaron Swartz + def name2cp(k): + import htmlentitydefs + if hasattr(htmlentitydefs, 'name2codepoint'): # requires Python 2.3 + return htmlentitydefs.name2codepoint[k] + k = htmlentitydefs.entitydefs[k] + if k.startswith('&#') and k.endswith(';'): + return int(k[2:-1]) # not in latin-1 + return ord(k) + try: name2cp(ref) + except KeyError: text = '&%s;' % ref + else: text = unichr(name2cp(ref)).encode('utf-8') + self.elementstack[-1][2].append(text) + + def handle_data(self, text, escape=1): + # called for each block of plain text, i.e. outside of any tag and + # not containing any character or entity references + if not self.elementstack: return + if escape and self.contentparams.get('type') == 'application/xhtml+xml': + text = _xmlescape(text) + self.elementstack[-1][2].append(text) + + def handle_comment(self, text): + # called for each comment, e.g. + pass + + def handle_pi(self, text): + # called for each processing instruction, e.g. + pass + + def handle_decl(self, text): + pass + + def parse_declaration(self, i): + # override internal declaration handler to handle CDATA blocks + if _debug: sys.stderr.write('entering parse_declaration\n') + if self.rawdata[i:i+9] == '', i) + if k == -1: k = len(self.rawdata) + self.handle_data(_xmlescape(self.rawdata[i+9:k]), 0) + return k+3 + else: + k = self.rawdata.find('>', i) + return k+1 + + def mapContentType(self, contentType): + contentType = contentType.lower() + if contentType == 'text': + contentType = 'text/plain' + elif contentType == 'html': + contentType = 'text/html' + elif contentType == 'xhtml': + contentType = 'application/xhtml+xml' + return contentType + + def trackNamespace(self, prefix, uri): + loweruri = uri.lower() + if (prefix, loweruri) == (None, 'http://my.netscape.com/rdf/simple/0.9/') and not self.version: + self.version = 'rss090' + if loweruri == 'http://purl.org/rss/1.0/' and not self.version: + self.version = 'rss10' + if loweruri == 'http://www.w3.org/2005/atom' and not self.version: + self.version = 'atom10' + if loweruri.find('backend.userland.com/rss') <> -1: + # match any backend.userland.com namespace + uri = 'http://backend.userland.com/rss' + loweruri = uri + if self._matchnamespaces.has_key(loweruri): + self.namespacemap[prefix] = self._matchnamespaces[loweruri] + self.namespacesInUse[self._matchnamespaces[loweruri]] = uri + else: + self.namespacesInUse[prefix or ''] = uri + + def resolveURI(self, uri): + return _urljoin(self.baseuri or '', uri) + + def decodeEntities(self, element, data): + return data + + def push(self, element, expectingText): + self.elementstack.append([element, expectingText, []]) + + def pop(self, element, stripWhitespace=1): + if not self.elementstack: return + if self.elementstack[-1][0] != element: return + + element, expectingText, pieces = self.elementstack.pop() + output = ''.join(pieces) + if stripWhitespace: + output = output.strip() + if not expectingText: return output + + # decode base64 content + if base64 and self.contentparams.get('base64', 0): + try: + output = base64.decodestring(output) + except binascii.Error: + pass + except binascii.Incomplete: + pass + + # resolve relative URIs + if (element in self.can_be_relative_uri) and output: + output = self.resolveURI(output) + + # decode entities within embedded markup + if not self.contentparams.get('base64', 0): + output = self.decodeEntities(element, output) + + # remove temporary cruft from contentparams + try: + del self.contentparams['mode'] + except KeyError: + pass + try: + del self.contentparams['base64'] + except KeyError: + pass + + # resolve relative URIs within embedded markup + if self.mapContentType(self.contentparams.get('type', 'text/html')) in self.html_types: + if element in self.can_contain_relative_uris: + output = _resolveRelativeURIs(output, self.baseuri, self.encoding) + + # sanitize embedded markup + if self.mapContentType(self.contentparams.get('type', 'text/html')) in self.html_types: + if element in self.can_contain_dangerous_markup: + output = _sanitizeHTML(output, self.encoding) + + if self.encoding and type(output) != type(u''): + try: + output = unicode(output, self.encoding) + except: + pass + + # categories/tags/keywords/whatever are handled in _end_category + if element == 'category': + return output + + # store output in appropriate place(s) + if self.inentry and not self.insource: + if element == 'content': + self.entries[-1].setdefault(element, []) + contentparams = copy.deepcopy(self.contentparams) + contentparams['value'] = output + self.entries[-1][element].append(contentparams) + elif element == 'link': + self.entries[-1][element] = output + if output: + self.entries[-1]['links'][-1]['href'] = output + else: + if element == 'description': + element = 'summary' + self.entries[-1][element] = output + if self.incontent: + contentparams = copy.deepcopy(self.contentparams) + contentparams['value'] = output + self.entries[-1][element + '_detail'] = contentparams + elif (self.infeed or self.insource) and (not self.intextinput) and (not self.inimage): + context = self._getContext() + if element == 'description': + element = 'subtitle' + context[element] = output + if element == 'link': + context['links'][-1]['href'] = output + elif self.incontent: + contentparams = copy.deepcopy(self.contentparams) + contentparams['value'] = output + context[element + '_detail'] = contentparams + return output + + def pushContent(self, tag, attrsD, defaultContentType, expectingText): + self.incontent += 1 + self.contentparams = FeedParserDict({ + 'type': self.mapContentType(attrsD.get('type', defaultContentType)), + 'language': self.lang, + 'base': self.baseuri}) + self.contentparams['base64'] = self._isBase64(attrsD, self.contentparams) + self.push(tag, expectingText) + + def popContent(self, tag): + value = self.pop(tag) + self.incontent -= 1 + self.contentparams.clear() + return value + + def _mapToStandardPrefix(self, name): + colonpos = name.find(':') + if colonpos <> -1: + prefix = name[:colonpos] + suffix = name[colonpos+1:] + prefix = self.namespacemap.get(prefix, prefix) + name = prefix + ':' + suffix + return name + + def _getAttribute(self, attrsD, name): + return attrsD.get(self._mapToStandardPrefix(name)) + + def _isBase64(self, attrsD, contentparams): + if attrsD.get('mode', '') == 'base64': + return 1 + if self.contentparams['type'].startswith('text/'): + return 0 + if self.contentparams['type'].endswith('+xml'): + return 0 + if self.contentparams['type'].endswith('/xml'): + return 0 + return 1 + + def _itsAnHrefDamnIt(self, attrsD): + href = attrsD.get('url', attrsD.get('uri', attrsD.get('href', None))) + if href: + try: + del attrsD['url'] + except KeyError: + pass + try: + del attrsD['uri'] + except KeyError: + pass + attrsD['href'] = href + return attrsD + + def _save(self, key, value): + context = self._getContext() + context.setdefault(key, value) + + def _start_rss(self, attrsD): + versionmap = {'0.91': 'rss091u', + '0.92': 'rss092', + '0.93': 'rss093', + '0.94': 'rss094'} + if not self.version: + attr_version = attrsD.get('version', '') + version = versionmap.get(attr_version) + if version: + self.version = version + elif attr_version.startswith('2.'): + self.version = 'rss20' + else: + self.version = 'rss' + + def _start_dlhottitles(self, attrsD): + self.version = 'hotrss' + + def _start_channel(self, attrsD): + self.infeed = 1 + self._cdf_common(attrsD) + _start_feedinfo = _start_channel + + def _cdf_common(self, attrsD): + if attrsD.has_key('lastmod'): + self._start_modified({}) + self.elementstack[-1][-1] = attrsD['lastmod'] + self._end_modified() + if attrsD.has_key('href'): + self._start_link({}) + self.elementstack[-1][-1] = attrsD['href'] + self._end_link() + + def _start_feed(self, attrsD): + self.infeed = 1 + versionmap = {'0.1': 'atom01', + '0.2': 'atom02', + '0.3': 'atom03'} + if not self.version: + attr_version = attrsD.get('version') + version = versionmap.get(attr_version) + if version: + self.version = version + else: + self.version = 'atom' + + def _end_channel(self): + self.infeed = 0 + _end_feed = _end_channel + + def _start_image(self, attrsD): + self.inimage = 1 + self.push('image', 0) + context = self._getContext() + context.setdefault('image', FeedParserDict()) + + def _end_image(self): + self.pop('image') + self.inimage = 0 + + def _start_textinput(self, attrsD): + self.intextinput = 1 + self.push('textinput', 0) + context = self._getContext() + context.setdefault('textinput', FeedParserDict()) + _start_textInput = _start_textinput + + def _end_textinput(self): + self.pop('textinput') + self.intextinput = 0 + _end_textInput = _end_textinput + + def _start_author(self, attrsD): + self.inauthor = 1 + self.push('author', 1) + _start_managingeditor = _start_author + _start_dc_author = _start_author + _start_dc_creator = _start_author + _start_itunes_author = _start_author + + def _end_author(self): + self.pop('author') + self.inauthor = 0 + self._sync_author_detail() + _end_managingeditor = _end_author + _end_dc_author = _end_author + _end_dc_creator = _end_author + _end_itunes_author = _end_author + + def _start_itunes_owner(self, attrsD): + self.inpublisher = 1 + self.push('publisher', 0) + + def _end_itunes_owner(self): + self.pop('publisher') + self.inpublisher = 0 + self._sync_author_detail('publisher') + + def _start_contributor(self, attrsD): + self.incontributor = 1 + context = self._getContext() + context.setdefault('contributors', []) + context['contributors'].append(FeedParserDict()) + self.push('contributor', 0) + + def _end_contributor(self): + self.pop('contributor') + self.incontributor = 0 + + def _start_dc_contributor(self, attrsD): + self.incontributor = 1 + context = self._getContext() + context.setdefault('contributors', []) + context['contributors'].append(FeedParserDict()) + self.push('name', 0) + + def _end_dc_contributor(self): + self._end_name() + self.incontributor = 0 + + def _start_name(self, attrsD): + self.push('name', 0) + _start_itunes_name = _start_name + + def _end_name(self): + value = self.pop('name') + if self.inpublisher: + self._save_author('name', value, 'publisher') + elif self.inauthor: + self._save_author('name', value) + elif self.incontributor: + self._save_contributor('name', value) + elif self.intextinput: + context = self._getContext() + context['textinput']['name'] = value + _end_itunes_name = _end_name + + def _start_width(self, attrsD): + self.push('width', 0) + + def _end_width(self): + value = self.pop('width') + try: + value = int(value) + except: + value = 0 + if self.inimage: + context = self._getContext() + context['image']['width'] = value + + def _start_height(self, attrsD): + self.push('height', 0) + + def _end_height(self): + value = self.pop('height') + try: + value = int(value) + except: + value = 0 + if self.inimage: + context = self._getContext() + context['image']['height'] = value + + def _start_url(self, attrsD): + self.push('href', 1) + _start_homepage = _start_url + _start_uri = _start_url + + def _end_url(self): + value = self.pop('href') + if self.inauthor: + self._save_author('href', value) + elif self.incontributor: + self._save_contributor('href', value) + elif self.inimage: + context = self._getContext() + context['image']['href'] = value + elif self.intextinput: + context = self._getContext() + context['textinput']['link'] = value + _end_homepage = _end_url + _end_uri = _end_url + + def _start_email(self, attrsD): + self.push('email', 0) + _start_itunes_email = _start_email + + def _end_email(self): + value = self.pop('email') + if self.inpublisher: + self._save_author('email', value, 'publisher') + elif self.inauthor: + self._save_author('email', value) + elif self.incontributor: + self._save_contributor('email', value) + _end_itunes_email = _end_email + + def _getContext(self): + if self.insource: + context = self.sourcedata + elif self.inentry: + context = self.entries[-1] + else: + context = self.feeddata + return context + + def _save_author(self, key, value, prefix='author'): + context = self._getContext() + context.setdefault(prefix + '_detail', FeedParserDict()) + context[prefix + '_detail'][key] = value + self._sync_author_detail() + + def _save_contributor(self, key, value): + context = self._getContext() + context.setdefault('contributors', [FeedParserDict()]) + context['contributors'][-1][key] = value + + def _sync_author_detail(self, key='author'): + context = self._getContext() + detail = context.get('%s_detail' % key) + if detail: + name = detail.get('name') + email = detail.get('email') + if name and email: + context[key] = '%s (%s)' % (name, email) + elif name: + context[key] = name + elif email: + context[key] = email + else: + author = context.get(key) + if not author: return + emailmatch = re.search(r'''(([a-zA-Z0-9\_\-\.\+]+)@((\[[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.)|(([a-zA-Z0-9\-]+\.)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\]?))''', author) + if not emailmatch: return + email = emailmatch.group(0) + # probably a better way to do the following, but it passes all the tests + author = author.replace(email, '') + author = author.replace('()', '') + author = author.strip() + if author and (author[0] == '('): + author = author[1:] + if author and (author[-1] == ')'): + author = author[:-1] + author = author.strip() + context.setdefault('%s_detail' % key, FeedParserDict()) + context['%s_detail' % key]['name'] = author + context['%s_detail' % key]['email'] = email + + def _start_subtitle(self, attrsD): + self.pushContent('subtitle', attrsD, 'text/plain', 1) + _start_tagline = _start_subtitle + _start_itunes_subtitle = _start_subtitle + + def _end_subtitle(self): + self.popContent('subtitle') + _end_tagline = _end_subtitle + _end_itunes_subtitle = _end_subtitle + + def _start_rights(self, attrsD): + self.pushContent('rights', attrsD, 'text/plain', 1) + _start_dc_rights = _start_rights + _start_copyright = _start_rights + + def _end_rights(self): + self.popContent('rights') + _end_dc_rights = _end_rights + _end_copyright = _end_rights + + def _start_item(self, attrsD): + self.entries.append(FeedParserDict()) + self.push('item', 0) + self.inentry = 1 + self.guidislink = 0 + id = self._getAttribute(attrsD, 'rdf:about') + if id: + context = self._getContext() + context['id'] = id + self._cdf_common(attrsD) + _start_entry = _start_item + _start_product = _start_item + + def _end_item(self): + self.pop('item') + self.inentry = 0 + _end_entry = _end_item + + def _start_dc_language(self, attrsD): + self.push('language', 1) + _start_language = _start_dc_language + + def _end_dc_language(self): + self.lang = self.pop('language') + _end_language = _end_dc_language + + def _start_dc_publisher(self, attrsD): + self.push('publisher', 1) + _start_webmaster = _start_dc_publisher + + def _end_dc_publisher(self): + self.pop('publisher') + self._sync_author_detail('publisher') + _end_webmaster = _end_dc_publisher + + def _start_published(self, attrsD): + self.push('published', 1) + _start_dcterms_issued = _start_published + _start_issued = _start_published + + def _end_published(self): + value = self.pop('published') + self._save('published_parsed', _parse_date(value)) + _end_dcterms_issued = _end_published + _end_issued = _end_published + + def _start_updated(self, attrsD): + self.push('updated', 1) + _start_modified = _start_updated + _start_dcterms_modified = _start_updated + _start_pubdate = _start_updated + _start_dc_date = _start_updated + + def _end_updated(self): + value = self.pop('updated') + parsed_value = _parse_date(value) + self._save('updated_parsed', parsed_value) + _end_modified = _end_updated + _end_dcterms_modified = _end_updated + _end_pubdate = _end_updated + _end_dc_date = _end_updated + + def _start_created(self, attrsD): + self.push('created', 1) + _start_dcterms_created = _start_created + + def _end_created(self): + value = self.pop('created') + self._save('created_parsed', _parse_date(value)) + _end_dcterms_created = _end_created + + def _start_expirationdate(self, attrsD): + self.push('expired', 1) + + def _end_expirationdate(self): + self._save('expired_parsed', _parse_date(self.pop('expired'))) + + def _start_cc_license(self, attrsD): + self.push('license', 1) + value = self._getAttribute(attrsD, 'rdf:resource') + if value: + self.elementstack[-1][2].append(value) + self.pop('license') + + def _start_creativecommons_license(self, attrsD): + self.push('license', 1) + + def _end_creativecommons_license(self): + self.pop('license') + + def _addTag(self, term, scheme, label): + context = self._getContext() + tags = context.setdefault('tags', []) + if (not term) and (not scheme) and (not label): return + value = FeedParserDict({'term': term, 'scheme': scheme, 'label': label}) + if value not in tags: + tags.append(FeedParserDict({'term': term, 'scheme': scheme, 'label': label})) + + def _start_category(self, attrsD): + if _debug: sys.stderr.write('entering _start_category with %s\n' % repr(attrsD)) + term = attrsD.get('term') + scheme = attrsD.get('scheme', attrsD.get('domain')) + label = attrsD.get('label') + self._addTag(term, scheme, label) + self.push('category', 1) + _start_dc_subject = _start_category + _start_keywords = _start_category + + def _end_itunes_keywords(self): + for term in self.pop('itunes_keywords').split(): + self._addTag(term, 'http://www.itunes.com/', None) + + def _start_itunes_category(self, attrsD): + self._addTag(attrsD.get('text'), 'http://www.itunes.com/', None) + self.push('category', 1) + + def _end_category(self): + value = self.pop('category') + if not value: return + context = self._getContext() + tags = context['tags'] + if value and len(tags) and not tags[-1]['term']: + tags[-1]['term'] = value + else: + self._addTag(value, None, None) + _end_dc_subject = _end_category + _end_keywords = _end_category + _end_itunes_category = _end_category + + def _start_cloud(self, attrsD): + self._getContext()['cloud'] = FeedParserDict(attrsD) + + def _start_link(self, attrsD): + attrsD.setdefault('rel', 'alternate') + attrsD.setdefault('type', 'text/html') + attrsD = self._itsAnHrefDamnIt(attrsD) + if attrsD.has_key('href'): + attrsD['href'] = self.resolveURI(attrsD['href']) + expectingText = self.infeed or self.inentry or self.insource + context = self._getContext() + context.setdefault('links', []) + context['links'].append(FeedParserDict(attrsD)) + if attrsD['rel'] == 'enclosure': + self._start_enclosure(attrsD) + if attrsD.has_key('href'): + expectingText = 0 + if (attrsD.get('rel') == 'alternate') and (self.mapContentType(attrsD.get('type')) in self.html_types): + context['link'] = attrsD['href'] + else: + self.push('link', expectingText) + _start_producturl = _start_link + + def _end_link(self): + value = self.pop('link') + context = self._getContext() + if self.intextinput: + context['textinput']['link'] = value + if self.inimage: + context['image']['link'] = value + _end_producturl = _end_link + + def _start_guid(self, attrsD): + self.guidislink = (attrsD.get('ispermalink', 'true') == 'true') + self.push('id', 1) + + def _end_guid(self): + value = self.pop('id') + self._save('guidislink', self.guidislink and not self._getContext().has_key('link')) + if self.guidislink: + # guid acts as link, but only if 'ispermalink' is not present or is 'true', + # and only if the item doesn't already have a link element + self._save('link', value) + + def _start_title(self, attrsD): + self.pushContent('title', attrsD, 'text/plain', self.infeed or self.inentry or self.insource) + _start_dc_title = _start_title + _start_media_title = _start_title + + def _end_title(self): + value = self.popContent('title') + context = self._getContext() + if self.intextinput: + context['textinput']['title'] = value + elif self.inimage: + context['image']['title'] = value + _end_dc_title = _end_title + _end_media_title = _end_title + + def _start_description(self, attrsD): + context = self._getContext() + if context.has_key('summary'): + self._summaryKey = 'content' + self._start_content(attrsD) + else: + self.pushContent('description', attrsD, 'text/html', self.infeed or self.inentry or self.insource) + + def _start_abstract(self, attrsD): + self.pushContent('description', attrsD, 'text/plain', self.infeed or self.inentry or self.insource) + + def _end_description(self): + if self._summaryKey == 'content': + self._end_content() + else: + value = self.popContent('description') + context = self._getContext() + if self.intextinput: + context['textinput']['description'] = value + elif self.inimage: + context['image']['description'] = value + self._summaryKey = None + _end_abstract = _end_description + + def _start_info(self, attrsD): + self.pushContent('info', attrsD, 'text/plain', 1) + _start_feedburner_browserfriendly = _start_info + + def _end_info(self): + self.popContent('info') + _end_feedburner_browserfriendly = _end_info + + def _start_generator(self, attrsD): + if attrsD: + attrsD = self._itsAnHrefDamnIt(attrsD) + if attrsD.has_key('href'): + attrsD['href'] = self.resolveURI(attrsD['href']) + self._getContext()['generator_detail'] = FeedParserDict(attrsD) + self.push('generator', 1) + + def _end_generator(self): + value = self.pop('generator') + context = self._getContext() + if context.has_key('generator_detail'): + context['generator_detail']['name'] = value + + def _start_admin_generatoragent(self, attrsD): + self.push('generator', 1) + value = self._getAttribute(attrsD, 'rdf:resource') + if value: + self.elementstack[-1][2].append(value) + self.pop('generator') + self._getContext()['generator_detail'] = FeedParserDict({'href': value}) + + def _start_admin_errorreportsto(self, attrsD): + self.push('errorreportsto', 1) + value = self._getAttribute(attrsD, 'rdf:resource') + if value: + self.elementstack[-1][2].append(value) + self.pop('errorreportsto') + + def _start_summary(self, attrsD): + context = self._getContext() + if context.has_key('summary'): + self._summaryKey = 'content' + self._start_content(attrsD) + else: + self._summaryKey = 'summary' + self.pushContent(self._summaryKey, attrsD, 'text/plain', 1) + _start_itunes_summary = _start_summary + + def _end_summary(self): + if self._summaryKey == 'content': + self._end_content() + else: + self.popContent(self._summaryKey or 'summary') + self._summaryKey = None + _end_itunes_summary = _end_summary + + def _start_enclosure(self, attrsD): + attrsD = self._itsAnHrefDamnIt(attrsD) + self._getContext().setdefault('enclosures', []).append(FeedParserDict(attrsD)) + href = attrsD.get('href') + if href: + context = self._getContext() + if not context.get('id'): + context['id'] = href + + def _start_source(self, attrsD): + self.insource = 1 + + def _end_source(self): + self.insource = 0 + self._getContext()['source'] = copy.deepcopy(self.sourcedata) + self.sourcedata.clear() + + def _start_content(self, attrsD): + self.pushContent('content', attrsD, 'text/plain', 1) + src = attrsD.get('src') + if src: + self.contentparams['src'] = src + self.push('content', 1) + + def _start_prodlink(self, attrsD): + self.pushContent('content', attrsD, 'text/html', 1) + + def _start_body(self, attrsD): + self.pushContent('content', attrsD, 'application/xhtml+xml', 1) + _start_xhtml_body = _start_body + + def _start_content_encoded(self, attrsD): + self.pushContent('content', attrsD, 'text/html', 1) + _start_fullitem = _start_content_encoded + + def _end_content(self): + copyToDescription = self.mapContentType(self.contentparams.get('type')) in (['text/plain'] + self.html_types) + value = self.popContent('content') + if copyToDescription: + self._save('description', value) + _end_body = _end_content + _end_xhtml_body = _end_content + _end_content_encoded = _end_content + _end_fullitem = _end_content + _end_prodlink = _end_content + + def _start_itunes_image(self, attrsD): + self.push('itunes_image', 0) + self._getContext()['image'] = FeedParserDict({'href': attrsD.get('href')}) + _start_itunes_link = _start_itunes_image + + def _end_itunes_block(self): + value = self.pop('itunes_block', 0) + self._getContext()['itunes_block'] = (value == 'yes') and 1 or 0 + + def _end_itunes_explicit(self): + value = self.pop('itunes_explicit', 0) + self._getContext()['itunes_explicit'] = (value == 'yes') and 1 or 0 + +if _XML_AVAILABLE: + class _StrictFeedParser(_FeedParserMixin, xml.sax.handler.ContentHandler): + def __init__(self, baseuri, baselang, encoding): + if _debug: sys.stderr.write('trying StrictFeedParser\n') + xml.sax.handler.ContentHandler.__init__(self) + _FeedParserMixin.__init__(self, baseuri, baselang, encoding) + self.bozo = 0 + self.exc = None + + def startPrefixMapping(self, prefix, uri): + self.trackNamespace(prefix, uri) + + def startElementNS(self, name, qname, attrs): + namespace, localname = name + lowernamespace = str(namespace or '').lower() + if lowernamespace.find('backend.userland.com/rss') <> -1: + # match any backend.userland.com namespace + namespace = 'http://backend.userland.com/rss' + lowernamespace = namespace + if qname and qname.find(':') > 0: + givenprefix = qname.split(':')[0] + else: + givenprefix = None + prefix = self._matchnamespaces.get(lowernamespace, givenprefix) + if givenprefix and (prefix == None or (prefix == '' and lowernamespace == '')) and not self.namespacesInUse.has_key(givenprefix): + raise UndeclaredNamespace, "'%s' is not associated with a namespace" % givenprefix + if prefix: + localname = prefix + ':' + localname + localname = str(localname).lower() + if _debug: sys.stderr.write('startElementNS: qname = %s, namespace = %s, givenprefix = %s, prefix = %s, attrs = %s, localname = %s\n' % (qname, namespace, givenprefix, prefix, attrs.items(), localname)) + + # qname implementation is horribly broken in Python 2.1 (it + # doesn't report any), and slightly broken in Python 2.2 (it + # doesn't report the xml: namespace). So we match up namespaces + # with a known list first, and then possibly override them with + # the qnames the SAX parser gives us (if indeed it gives us any + # at all). Thanks to MatejC for helping me test this and + # tirelessly telling me that it didn't work yet. + attrsD = {} + for (namespace, attrlocalname), attrvalue in attrs._attrs.items(): + lowernamespace = (namespace or '').lower() + prefix = self._matchnamespaces.get(lowernamespace, '') + if prefix: + attrlocalname = prefix + ':' + attrlocalname + attrsD[str(attrlocalname).lower()] = attrvalue + for qname in attrs.getQNames(): + attrsD[str(qname).lower()] = attrs.getValueByQName(qname) + self.unknown_starttag(localname, attrsD.items()) + + def characters(self, text): + self.handle_data(text) + + def endElementNS(self, name, qname): + namespace, localname = name + lowernamespace = str(namespace or '').lower() + if qname and qname.find(':') > 0: + givenprefix = qname.split(':')[0] + else: + givenprefix = '' + prefix = self._matchnamespaces.get(lowernamespace, givenprefix) + if prefix: + localname = prefix + ':' + localname + localname = str(localname).lower() + self.unknown_endtag(localname) + + def error(self, exc): + self.bozo = 1 + self.exc = exc + + def fatalError(self, exc): + self.error(exc) + raise exc + +class _BaseHTMLProcessor(sgmllib.SGMLParser): + elements_no_end_tag = ['area', 'base', 'basefont', 'br', 'col', 'frame', 'hr', + 'img', 'input', 'isindex', 'link', 'meta', 'param'] + + def __init__(self, encoding): + self.encoding = encoding + if _debug: sys.stderr.write('entering BaseHTMLProcessor, encoding=%s\n' % self.encoding) + sgmllib.SGMLParser.__init__(self) + + def reset(self): + self.pieces = [] + sgmllib.SGMLParser.reset(self) + + def _shorttag_replace(self, match): + tag = match.group(1) + if tag in self.elements_no_end_tag: + return '<' + tag + ' />' + else: + return '<' + tag + '>' + + def feed(self, data): + data = re.compile(r'', self._shorttag_replace, data) + data = data.replace(''', "'") + data = data.replace('"', '"') + if self.encoding and type(data) == type(u''): + data = data.encode(self.encoding) + sgmllib.SGMLParser.feed(self, data) + + def normalize_attrs(self, attrs): + # utility method to be called by descendants + attrs = [(k.lower(), v) for k, v in attrs] + attrs = [(k, k in ('rel', 'type') and v.lower() or v) for k, v in attrs] + return attrs + + def unknown_starttag(self, tag, attrs): + # called for each start tag + # attrs is a list of (attr, value) tuples + # e.g. for 
, tag='pre', attrs=[('class', 'screen')]
+        if _debug: sys.stderr.write('_BaseHTMLProcessor, unknown_starttag, tag=%s\n' % tag)
+        uattrs = []
+        # thanks to Kevin Marks for this breathtaking hack to deal with (valid) high-bit attribute values in UTF-8 feeds
+        for key, value in attrs:
+            if type(value) != type(u''):
+                value = unicode(value, self.encoding)
+            uattrs.append((unicode(key, self.encoding), value))
+        strattrs = u''.join([u' %s="%s"' % (key, value) for key, value in uattrs]).encode(self.encoding)
+        if tag in self.elements_no_end_tag:
+            self.pieces.append('<%(tag)s%(strattrs)s />' % locals())
+        else:
+            self.pieces.append('<%(tag)s%(strattrs)s>' % locals())
+
+    def unknown_endtag(self, tag):
+        # called for each end tag, e.g. for
, tag will be 'pre' + # Reconstruct the original end tag. + if tag not in self.elements_no_end_tag: + self.pieces.append("" % locals()) + + def handle_charref(self, ref): + # called for each character reference, e.g. for ' ', ref will be '160' + # Reconstruct the original character reference. + self.pieces.append('&#%(ref)s;' % locals()) + + def handle_entityref(self, ref): + # called for each entity reference, e.g. for '©', ref will be 'copy' + # Reconstruct the original entity reference. + self.pieces.append('&%(ref)s;' % locals()) + + def handle_data(self, text): + # called for each block of plain text, i.e. outside of any tag and + # not containing any character or entity references + # Store the original text verbatim. + if _debug: sys.stderr.write('_BaseHTMLProcessor, handle_text, text=%s\n' % text) + self.pieces.append(text) + + def handle_comment(self, text): + # called for each HTML comment, e.g. + # Reconstruct the original comment. + self.pieces.append('' % locals()) + + def handle_pi(self, text): + # called for each processing instruction, e.g. + # Reconstruct original processing instruction. + self.pieces.append('' % locals()) + + def handle_decl(self, text): + # called for the DOCTYPE, if present, e.g. + # + # Reconstruct original DOCTYPE + self.pieces.append('' % locals()) + + _new_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9:]*\s*').match + def _scan_name(self, i, declstartpos): + rawdata = self.rawdata + n = len(rawdata) + if i == n: + return None, -1 + m = self._new_declname_match(rawdata, i) + if m: + s = m.group() + name = s.strip() + if (i + len(s)) == n: + return None, -1 # end of buffer + return name.lower(), m.end() + else: + self.handle_data(rawdata) +# self.updatepos(declstartpos, i) + return None, -1 + + def output(self): + '''Return processed HTML as a single string''' + return ''.join([str(p) for p in self.pieces]) + +class _LooseFeedParser(_FeedParserMixin, _BaseHTMLProcessor): + def __init__(self, baseuri, baselang, encoding): + sgmllib.SGMLParser.__init__(self) + _FeedParserMixin.__init__(self, baseuri, baselang, encoding) + + def decodeEntities(self, element, data): + data = data.replace('<', '<') + data = data.replace('<', '<') + data = data.replace('>', '>') + data = data.replace('>', '>') + data = data.replace('&', '&') + data = data.replace('&', '&') + data = data.replace('"', '"') + data = data.replace('"', '"') + data = data.replace(''', ''') + data = data.replace(''', ''') + if self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'): + data = data.replace('<', '<') + data = data.replace('>', '>') + data = data.replace('&', '&') + data = data.replace('"', '"') + data = data.replace(''', "'") + return data + +class _RelativeURIResolver(_BaseHTMLProcessor): + relative_uris = [('a', 'href'), + ('applet', 'codebase'), + ('area', 'href'), + ('blockquote', 'cite'), + ('body', 'background'), + ('del', 'cite'), + ('form', 'action'), + ('frame', 'longdesc'), + ('frame', 'src'), + ('iframe', 'longdesc'), + ('iframe', 'src'), + ('head', 'profile'), + ('img', 'longdesc'), + ('img', 'src'), + ('img', 'usemap'), + ('input', 'src'), + ('input', 'usemap'), + ('ins', 'cite'), + ('link', 'href'), + ('object', 'classid'), + ('object', 'codebase'), + ('object', 'data'), + ('object', 'usemap'), + ('q', 'cite'), + ('script', 'src')] + + def __init__(self, baseuri, encoding): + _BaseHTMLProcessor.__init__(self, encoding) + self.baseuri = baseuri + + def resolveURI(self, uri): + return _urljoin(self.baseuri, uri) + + def unknown_starttag(self, tag, attrs): + attrs = self.normalize_attrs(attrs) + attrs = [(key, ((tag, key) in self.relative_uris) and self.resolveURI(value) or value) for key, value in attrs] + _BaseHTMLProcessor.unknown_starttag(self, tag, attrs) + +def _resolveRelativeURIs(htmlSource, baseURI, encoding): + if _debug: sys.stderr.write('entering _resolveRelativeURIs\n') + p = _RelativeURIResolver(baseURI, encoding) + p.feed(htmlSource) + return p.output() + +class _HTMLSanitizer(_BaseHTMLProcessor): + acceptable_elements = ['a', 'abbr', 'acronym', 'address', 'area', 'b', 'big', + 'blockquote', 'br', 'button', 'caption', 'center', 'cite', 'code', 'col', + 'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt', 'em', 'fieldset', + 'font', 'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input', + 'ins', 'kbd', 'label', 'legend', 'li', 'map', 'menu', 'ol', 'optgroup', + 'option', 'p', 'pre', 'q', 's', 'samp', 'select', 'small', 'span', 'strike', + 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'tfoot', 'th', + 'thead', 'tr', 'tt', 'u', 'ul', 'var'] + + acceptable_attributes = ['abbr', 'accept', 'accept-charset', 'accesskey', + 'action', 'align', 'alt', 'axis', 'border', 'cellpadding', 'cellspacing', + 'char', 'charoff', 'charset', 'checked', 'cite', 'class', 'clear', 'cols', + 'colspan', 'color', 'compact', 'coords', 'datetime', 'dir', 'disabled', + 'enctype', 'for', 'frame', 'headers', 'height', 'href', 'hreflang', 'hspace', + 'id', 'ismap', 'label', 'lang', 'longdesc', 'maxlength', 'media', 'method', + 'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'prompt', 'readonly', + 'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', 'selected', 'shape', 'size', + 'span', 'src', 'start', 'summary', 'tabindex', 'target', 'title', 'type', + 'usemap', 'valign', 'value', 'vspace', 'width'] + + unacceptable_elements_with_end_tag = ['script', 'applet'] + + def reset(self): + _BaseHTMLProcessor.reset(self) + self.unacceptablestack = 0 + + def unknown_starttag(self, tag, attrs): + if not tag in self.acceptable_elements: + if tag in self.unacceptable_elements_with_end_tag: + self.unacceptablestack += 1 + return + attrs = self.normalize_attrs(attrs) + attrs = [(key, value) for key, value in attrs if key in self.acceptable_attributes] + _BaseHTMLProcessor.unknown_starttag(self, tag, attrs) + + def unknown_endtag(self, tag): + if not tag in self.acceptable_elements: + if tag in self.unacceptable_elements_with_end_tag: + self.unacceptablestack -= 1 + return + _BaseHTMLProcessor.unknown_endtag(self, tag) + + def handle_pi(self, text): + pass + + def handle_decl(self, text): + pass + + def handle_data(self, text): + if not self.unacceptablestack: + _BaseHTMLProcessor.handle_data(self, text) + +def _sanitizeHTML(htmlSource, encoding): + p = _HTMLSanitizer(encoding) + p.feed(htmlSource) + data = p.output() + if TIDY_MARKUP: + # loop through list of preferred Tidy interfaces looking for one that's installed, + # then set up a common _tidy function to wrap the interface-specific API. + _tidy = None + for tidy_interface in PREFERRED_TIDY_INTERFACES: + try: + if tidy_interface == "uTidy": + from tidy import parseString as _utidy + def _tidy(data, **kwargs): + return str(_utidy(data, **kwargs)) + break + elif tidy_interface == "mxTidy": + from mx.Tidy import Tidy as _mxtidy + def _tidy(data, **kwargs): + nerrors, nwarnings, data, errordata = _mxtidy.tidy(data, **kwargs) + return data + break + except: + pass + if _tidy: + utf8 = type(data) == type(u'') + if utf8: + data = data.encode('utf-8') + data = _tidy(data, output_xhtml=1, numeric_entities=1, wrap=0, char_encoding="utf8") + if utf8: + data = unicode(data, 'utf-8') + if data.count(''): + data = data.split('>', 1)[1] + if data.count('= '2.3.3' + assert base64 != None + user, passw = base64.decodestring(req.headers['Authorization'].split(' ')[1]).split(':') + realm = re.findall('realm="([^"]*)"', headers['WWW-Authenticate'])[0] + self.add_password(realm, host, user, passw) + retry = self.http_error_auth_reqed('www-authenticate', host, req, headers) + self.reset_retry_count() + return retry + except: + return self.http_error_default(req, fp, code, msg, headers) + +def _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers): + """URL, filename, or string --> stream + + This function lets you define parsers that take any input source + (URL, pathname to local or network file, or actual data as a string) + and deal with it in a uniform manner. Returned object is guaranteed + to have all the basic stdio read methods (read, readline, readlines). + Just .close() the object when you're done with it. + + If the etag argument is supplied, it will be used as the value of an + If-None-Match request header. + + If the modified argument is supplied, it must be a tuple of 9 integers + as returned by gmtime() in the standard Python time module. This MUST + be in GMT (Greenwich Mean Time). The formatted date/time will be used + as the value of an If-Modified-Since request header. + + If the agent argument is supplied, it will be used as the value of a + User-Agent request header. + + If the referrer argument is supplied, it will be used as the value of a + Referer[sic] request header. + + If handlers is supplied, it is a list of handlers used to build a + urllib2 opener. + """ + + if hasattr(url_file_stream_or_string, 'read'): + return url_file_stream_or_string + + if url_file_stream_or_string == '-': + return sys.stdin + + if urlparse.urlparse(url_file_stream_or_string)[0] in ('http', 'https', 'ftp'): + if not agent: + agent = USER_AGENT + # test for inline user:password for basic auth + auth = None + if base64: + urltype, rest = urllib.splittype(url_file_stream_or_string) + realhost, rest = urllib.splithost(rest) + if realhost: + user_passwd, realhost = urllib.splituser(realhost) + if user_passwd: + url_file_stream_or_string = '%s://%s%s' % (urltype, realhost, rest) + auth = base64.encodestring(user_passwd).strip() + # try to open with urllib2 (to use optional headers) + request = urllib2.Request(url_file_stream_or_string) + request.add_header('User-Agent', agent) + if etag: + request.add_header('If-None-Match', etag) + if modified: + # format into an RFC 1123-compliant timestamp. We can't use + # time.strftime() since the %a and %b directives can be affected + # by the current locale, but RFC 2616 states that dates must be + # in English. + short_weekdays = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'] + months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'] + request.add_header('If-Modified-Since', '%s, %02d %s %04d %02d:%02d:%02d GMT' % (short_weekdays[modified[6]], modified[2], months[modified[1] - 1], modified[0], modified[3], modified[4], modified[5])) + if referrer: + request.add_header('Referer', referrer) + if gzip and zlib: + request.add_header('Accept-encoding', 'gzip, deflate') + elif gzip: + request.add_header('Accept-encoding', 'gzip') + elif zlib: + request.add_header('Accept-encoding', 'deflate') + else: + request.add_header('Accept-encoding', '') + if auth: + request.add_header('Authorization', 'Basic %s' % auth) + if ACCEPT_HEADER: + request.add_header('Accept', ACCEPT_HEADER) + request.add_header('A-IM', 'feed') # RFC 3229 support + opener = apply(urllib2.build_opener, tuple([_FeedURLHandler()] + handlers)) + opener.addheaders = [] # RMK - must clear so we only send our custom User-Agent + try: + return opener.open(request) + finally: + opener.close() # JohnD + + # try to open with native open function (if url_file_stream_or_string is a filename) + try: + return open(url_file_stream_or_string) + except: + pass + + # treat url_file_stream_or_string as string + return _StringIO(str(url_file_stream_or_string)) + +_date_handlers = [] +def registerDateHandler(func): + '''Register a date handler function (takes string, returns 9-tuple date in GMT)''' + _date_handlers.insert(0, func) + +# ISO-8601 date parsing routines written by Fazal Majid. +# The ISO 8601 standard is very convoluted and irregular - a full ISO 8601 +# parser is beyond the scope of feedparser and would be a worthwhile addition +# to the Python library. +# A single regular expression cannot parse ISO 8601 date formats into groups +# as the standard is highly irregular (for instance is 030104 2003-01-04 or +# 0301-04-01), so we use templates instead. +# Please note the order in templates is significant because we need a +# greedy match. +_iso8601_tmpl = ['YYYY-?MM-?DD', 'YYYY-MM', 'YYYY-?OOO', + 'YY-?MM-?DD', 'YY-?OOO', 'YYYY', + '-YY-?MM', '-OOO', '-YY', + '--MM-?DD', '--MM', + '---DD', + 'CC', ''] +_iso8601_re = [ + tmpl.replace( + 'YYYY', r'(?P\d{4})').replace( + 'YY', r'(?P\d\d)').replace( + 'MM', r'(?P[01]\d)').replace( + 'DD', r'(?P[0123]\d)').replace( + 'OOO', r'(?P[0123]\d\d)').replace( + 'CC', r'(?P\d\d$)') + + r'(T?(?P\d{2}):(?P\d{2})' + + r'(:(?P\d{2}))?' + + r'(?P[+-](?P\d{2})(:(?P\d{2}))?|Z)?)?' + for tmpl in _iso8601_tmpl] +del tmpl +_iso8601_matches = [re.compile(regex).match for regex in _iso8601_re] +del regex +def _parse_date_iso8601(dateString): + '''Parse a variety of ISO-8601-compatible formats like 20040105''' + m = None + for _iso8601_match in _iso8601_matches: + m = _iso8601_match(dateString) + if m: break + if not m: return + if m.span() == (0, 0): return + params = m.groupdict() + ordinal = params.get('ordinal', 0) + if ordinal: + ordinal = int(ordinal) + else: + ordinal = 0 + year = params.get('year', '--') + if not year or year == '--': + year = time.gmtime()[0] + elif len(year) == 2: + # ISO 8601 assumes current century, i.e. 93 -> 2093, NOT 1993 + year = 100 * int(time.gmtime()[0] / 100) + int(year) + else: + year = int(year) + month = params.get('month', '-') + if not month or month == '-': + # ordinals are NOT normalized by mktime, we simulate them + # by setting month=1, day=ordinal + if ordinal: + month = 1 + else: + month = time.gmtime()[1] + month = int(month) + day = params.get('day', 0) + if not day: + # see above + if ordinal: + day = ordinal + elif params.get('century', 0) or \ + params.get('year', 0) or params.get('month', 0): + day = 1 + else: + day = time.gmtime()[2] + else: + day = int(day) + # special case of the century - is the first year of the 21st century + # 2000 or 2001 ? The debate goes on... + if 'century' in params.keys(): + year = (int(params['century']) - 1) * 100 + 1 + # in ISO 8601 most fields are optional + for field in ['hour', 'minute', 'second', 'tzhour', 'tzmin']: + if not params.get(field, None): + params[field] = 0 + hour = int(params.get('hour', 0)) + minute = int(params.get('minute', 0)) + second = int(params.get('second', 0)) + # weekday is normalized by mktime(), we can ignore it + weekday = 0 + # daylight savings is complex, but not needed for feedparser's purposes + # as time zones, if specified, include mention of whether it is active + # (e.g. PST vs. PDT, CET). Using -1 is implementation-dependent and + # and most implementations have DST bugs + daylight_savings_flag = 0 + tm = [year, month, day, hour, minute, second, weekday, + ordinal, daylight_savings_flag] + # ISO 8601 time zone adjustments + tz = params.get('tz') + if tz and tz != 'Z': + if tz[0] == '-': + tm[3] += int(params.get('tzhour', 0)) + tm[4] += int(params.get('tzmin', 0)) + elif tz[0] == '+': + tm[3] -= int(params.get('tzhour', 0)) + tm[4] -= int(params.get('tzmin', 0)) + else: + return None + # Python's time.mktime() is a wrapper around the ANSI C mktime(3c) + # which is guaranteed to normalize d/m/y/h/m/s. + # Many implementations have bugs, but we'll pretend they don't. + return time.localtime(time.mktime(tm)) +registerDateHandler(_parse_date_iso8601) + +# 8-bit date handling routines written by ytrewq1. +_korean_year = u'\ub144' # b3e2 in euc-kr +_korean_month = u'\uc6d4' # bff9 in euc-kr +_korean_day = u'\uc77c' # c0cf in euc-kr +_korean_am = u'\uc624\uc804' # bfc0 c0fc in euc-kr +_korean_pm = u'\uc624\ud6c4' # bfc0 c8c4 in euc-kr + +_korean_onblog_date_re = \ + re.compile('(\d{4})%s\s+(\d{2})%s\s+(\d{2})%s\s+(\d{2}):(\d{2}):(\d{2})' % \ + (_korean_year, _korean_month, _korean_day)) +_korean_nate_date_re = \ + re.compile(u'(\d{4})-(\d{2})-(\d{2})\s+(%s|%s)\s+(\d{,2}):(\d{,2}):(\d{,2})' % \ + (_korean_am, _korean_pm)) +def _parse_date_onblog(dateString): + '''Parse a string according to the OnBlog 8-bit date format''' + m = _korean_onblog_date_re.match(dateString) + if not m: return + w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \ + {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\ + 'hour': m.group(4), 'minute': m.group(5), 'second': m.group(6),\ + 'zonediff': '+09:00'} + if _debug: sys.stderr.write('OnBlog date parsed as: %s\n' % w3dtfdate) + return _parse_date_w3dtf(w3dtfdate) +registerDateHandler(_parse_date_onblog) + +def _parse_date_nate(dateString): + '''Parse a string according to the Nate 8-bit date format''' + m = _korean_nate_date_re.match(dateString) + if not m: return + hour = int(m.group(5)) + ampm = m.group(4) + if (ampm == _korean_pm): + hour += 12 + hour = str(hour) + if len(hour) == 1: + hour = '0' + hour + w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \ + {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\ + 'hour': hour, 'minute': m.group(6), 'second': m.group(7),\ + 'zonediff': '+09:00'} + if _debug: sys.stderr.write('Nate date parsed as: %s\n' % w3dtfdate) + return _parse_date_w3dtf(w3dtfdate) +registerDateHandler(_parse_date_nate) + +_mssql_date_re = \ + re.compile('(\d{4})-(\d{2})-(\d{2})\s+(\d{2}):(\d{2}):(\d{2})(\.\d+)?') +def _parse_date_mssql(dateString): + '''Parse a string according to the MS SQL date format''' + m = _mssql_date_re.match(dateString) + if not m: return + w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \ + {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\ + 'hour': m.group(4), 'minute': m.group(5), 'second': m.group(6),\ + 'zonediff': '+09:00'} + if _debug: sys.stderr.write('MS SQL date parsed as: %s\n' % w3dtfdate) + return _parse_date_w3dtf(w3dtfdate) +registerDateHandler(_parse_date_mssql) + +# Unicode strings for Greek date strings +_greek_months = \ + { \ + u'\u0399\u03b1\u03bd': u'Jan', # c9e1ed in iso-8859-7 + u'\u03a6\u03b5\u03b2': u'Feb', # d6e5e2 in iso-8859-7 + u'\u039c\u03ac\u03ce': u'Mar', # ccdcfe in iso-8859-7 + u'\u039c\u03b1\u03ce': u'Mar', # cce1fe in iso-8859-7 + u'\u0391\u03c0\u03c1': u'Apr', # c1f0f1 in iso-8859-7 + u'\u039c\u03ac\u03b9': u'May', # ccdce9 in iso-8859-7 + u'\u039c\u03b1\u03ca': u'May', # cce1fa in iso-8859-7 + u'\u039c\u03b1\u03b9': u'May', # cce1e9 in iso-8859-7 + u'\u0399\u03bf\u03cd\u03bd': u'Jun', # c9effded in iso-8859-7 + u'\u0399\u03bf\u03bd': u'Jun', # c9efed in iso-8859-7 + u'\u0399\u03bf\u03cd\u03bb': u'Jul', # c9effdeb in iso-8859-7 + u'\u0399\u03bf\u03bb': u'Jul', # c9f9eb in iso-8859-7 + u'\u0391\u03cd\u03b3': u'Aug', # c1fde3 in iso-8859-7 + u'\u0391\u03c5\u03b3': u'Aug', # c1f5e3 in iso-8859-7 + u'\u03a3\u03b5\u03c0': u'Sep', # d3e5f0 in iso-8859-7 + u'\u039f\u03ba\u03c4': u'Oct', # cfeaf4 in iso-8859-7 + u'\u039d\u03bf\u03ad': u'Nov', # cdefdd in iso-8859-7 + u'\u039d\u03bf\u03b5': u'Nov', # cdefe5 in iso-8859-7 + u'\u0394\u03b5\u03ba': u'Dec', # c4e5ea in iso-8859-7 + } + +_greek_wdays = \ + { \ + u'\u039a\u03c5\u03c1': u'Sun', # caf5f1 in iso-8859-7 + u'\u0394\u03b5\u03c5': u'Mon', # c4e5f5 in iso-8859-7 + u'\u03a4\u03c1\u03b9': u'Tue', # d4f1e9 in iso-8859-7 + u'\u03a4\u03b5\u03c4': u'Wed', # d4e5f4 in iso-8859-7 + u'\u03a0\u03b5\u03bc': u'Thu', # d0e5ec in iso-8859-7 + u'\u03a0\u03b1\u03c1': u'Fri', # d0e1f1 in iso-8859-7 + u'\u03a3\u03b1\u03b2': u'Sat', # d3e1e2 in iso-8859-7 + } + +_greek_date_format_re = \ + re.compile(u'([^,]+),\s+(\d{2})\s+([^\s]+)\s+(\d{4})\s+(\d{2}):(\d{2}):(\d{2})\s+([^\s]+)') + +def _parse_date_greek(dateString): + '''Parse a string according to a Greek 8-bit date format.''' + m = _greek_date_format_re.match(dateString) + if not m: return + try: + wday = _greek_wdays[m.group(1)] + month = _greek_months[m.group(3)] + except: + return + rfc822date = '%(wday)s, %(day)s %(month)s %(year)s %(hour)s:%(minute)s:%(second)s %(zonediff)s' % \ + {'wday': wday, 'day': m.group(2), 'month': month, 'year': m.group(4),\ + 'hour': m.group(5), 'minute': m.group(6), 'second': m.group(7),\ + 'zonediff': m.group(8)} + if _debug: sys.stderr.write('Greek date parsed as: %s\n' % rfc822date) + return _parse_date_rfc822(rfc822date) +registerDateHandler(_parse_date_greek) + +# Unicode strings for Hungarian date strings +_hungarian_months = \ + { \ + u'janu\u00e1r': u'01', # e1 in iso-8859-2 + u'febru\u00e1ri': u'02', # e1 in iso-8859-2 + u'm\u00e1rcius': u'03', # e1 in iso-8859-2 + u'\u00e1prilis': u'04', # e1 in iso-8859-2 + u'm\u00e1ujus': u'05', # e1 in iso-8859-2 + u'j\u00fanius': u'06', # fa in iso-8859-2 + u'j\u00falius': u'07', # fa in iso-8859-2 + u'augusztus': u'08', + u'szeptember': u'09', + u'okt\u00f3ber': u'10', # f3 in iso-8859-2 + u'november': u'11', + u'december': u'12', + } + +_hungarian_date_format_re = \ + re.compile(u'(\d{4})-([^-]+)-(\d{,2})T(\d{,2}):(\d{2})((\+|-)(\d{,2}:\d{2}))') + +def _parse_date_hungarian(dateString): + '''Parse a string according to a Hungarian 8-bit date format.''' + m = _hungarian_date_format_re.match(dateString) + if not m: return + try: + month = _hungarian_months[m.group(2)] + day = m.group(3) + if len(day) == 1: + day = '0' + day + hour = m.group(4) + if len(hour) == 1: + hour = '0' + hour + except: + return + w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s%(zonediff)s' % \ + {'year': m.group(1), 'month': month, 'day': day,\ + 'hour': hour, 'minute': m.group(5),\ + 'zonediff': m.group(6)} + if _debug: sys.stderr.write('Hungarian date parsed as: %s\n' % w3dtfdate) + return _parse_date_w3dtf(w3dtfdate) +registerDateHandler(_parse_date_hungarian) + +# W3DTF-style date parsing adapted from PyXML xml.utils.iso8601, written by +# Drake and licensed under the Python license. Removed all range checking +# for month, day, hour, minute, and second, since mktime will normalize +# these later +def _parse_date_w3dtf(dateString): + def __extract_date(m): + year = int(m.group('year')) + if year < 100: + year = 100 * int(time.gmtime()[0] / 100) + int(year) + if year < 1000: + return 0, 0, 0 + julian = m.group('julian') + if julian: + julian = int(julian) + month = julian / 30 + 1 + day = julian % 30 + 1 + jday = None + while jday != julian: + t = time.mktime((year, month, day, 0, 0, 0, 0, 0, 0)) + jday = time.gmtime(t)[-2] + diff = abs(jday - julian) + if jday > julian: + if diff < day: + day = day - diff + else: + month = month - 1 + day = 31 + elif jday < julian: + if day + diff < 28: + day = day + diff + else: + month = month + 1 + return year, month, day + month = m.group('month') + day = 1 + if month is None: + month = 1 + else: + month = int(month) + day = m.group('day') + if day: + day = int(day) + else: + day = 1 + return year, month, day + + def __extract_time(m): + if not m: + return 0, 0, 0 + hours = m.group('hours') + if not hours: + return 0, 0, 0 + hours = int(hours) + minutes = int(m.group('minutes')) + seconds = m.group('seconds') + if seconds: + seconds = int(seconds) + else: + seconds = 0 + return hours, minutes, seconds + + def __extract_tzd(m): + '''Return the Time Zone Designator as an offset in seconds from UTC.''' + if not m: + return 0 + tzd = m.group('tzd') + if not tzd: + return 0 + if tzd == 'Z': + return 0 + hours = int(m.group('tzdhours')) + minutes = m.group('tzdminutes') + if minutes: + minutes = int(minutes) + else: + minutes = 0 + offset = (hours*60 + minutes) * 60 + if tzd[0] == '+': + return -offset + return offset + + __date_re = ('(?P\d\d\d\d)' + '(?:(?P-|)' + '(?:(?P\d\d\d)' + '|(?P\d\d)(?:(?P=dsep)(?P\d\d))?))?') + __tzd_re = '(?P[-+](?P\d\d)(?::?(?P\d\d))|Z)' + __tzd_rx = re.compile(__tzd_re) + __time_re = ('(?P\d\d)(?P:|)(?P\d\d)' + '(?:(?P=tsep)(?P\d\d(?:[.,]\d+)?))?' + + __tzd_re) + __datetime_re = '%s(?:T%s)?' % (__date_re, __time_re) + __datetime_rx = re.compile(__datetime_re) + m = __datetime_rx.match(dateString) + if (m is None) or (m.group() != dateString): return + gmt = __extract_date(m) + __extract_time(m) + (0, 0, 0) + if gmt[0] == 0: return + return time.gmtime(time.mktime(gmt) + __extract_tzd(m) - time.timezone) +registerDateHandler(_parse_date_w3dtf) + +def _parse_date_rfc822(dateString): + '''Parse an RFC822, RFC1123, RFC2822, or asctime-style date''' + data = dateString.split() + if data[0][-1] in (',', '.') or data[0].lower() in rfc822._daynames: + del data[0] + if len(data) == 4: + s = data[3] + i = s.find('+') + if i > 0: + data[3:] = [s[:i], s[i+1:]] + else: + data.append('') + dateString = " ".join(data) + if len(data) < 5: + dateString += ' 00:00:00 GMT' + tm = rfc822.parsedate_tz(dateString) + if tm: + return time.gmtime(rfc822.mktime_tz(tm)) +# rfc822.py defines several time zones, but we define some extra ones. +# 'ET' is equivalent to 'EST', etc. +_additional_timezones = {'AT': -400, 'ET': -500, 'CT': -600, 'MT': -700, 'PT': -800} +rfc822._timezones.update(_additional_timezones) +registerDateHandler(_parse_date_rfc822) + +def _parse_date(dateString): + '''Parses a variety of date formats into a 9-tuple in GMT''' + for handler in _date_handlers: + try: + date9tuple = handler(dateString) + if not date9tuple: continue + if len(date9tuple) != 9: + if _debug: sys.stderr.write('date handler function must return 9-tuple\n') + raise ValueError + map(int, date9tuple) + return date9tuple + except Exception, e: + if _debug: sys.stderr.write('%s raised %s\n' % (handler.__name__, repr(e))) + pass + return None + +def _getCharacterEncoding(http_headers, xml_data): + '''Get the character encoding of the XML document + + http_headers is a dictionary + xml_data is a raw string (not Unicode) + + This is so much trickier than it sounds, it's not even funny. + According to RFC 3023 ('XML Media Types'), if the HTTP Content-Type + is application/xml, application/*+xml, + application/xml-external-parsed-entity, or application/xml-dtd, + the encoding given in the charset parameter of the HTTP Content-Type + takes precedence over the encoding given in the XML prefix within the + document, and defaults to 'utf-8' if neither are specified. But, if + the HTTP Content-Type is text/xml, text/*+xml, or + text/xml-external-parsed-entity, the encoding given in the XML prefix + within the document is ALWAYS IGNORED and only the encoding given in + the charset parameter of the HTTP Content-Type header should be + respected, and it defaults to 'us-ascii' if not specified. + + Furthermore, discussion on the atom-syntax mailing list with the + author of RFC 3023 leads me to the conclusion that any document + served with a Content-Type of text/* and no charset parameter + must be treated as us-ascii. (We now do this.) And also that it + must always be flagged as non-well-formed. (We now do this too.) + + If Content-Type is unspecified (input was local file or non-HTTP source) + or unrecognized (server just got it totally wrong), then go by the + encoding given in the XML prefix of the document and default to + 'iso-8859-1' as per the HTTP specification (RFC 2616). + + Then, assuming we didn't find a character encoding in the HTTP headers + (and the HTTP Content-type allowed us to look in the body), we need + to sniff the first few bytes of the XML data and try to determine + whether the encoding is ASCII-compatible. Section F of the XML + specification shows the way here: + http://www.w3.org/TR/REC-xml/#sec-guessing-no-ext-info + + If the sniffed encoding is not ASCII-compatible, we need to make it + ASCII compatible so that we can sniff further into the XML declaration + to find the encoding attribute, which will tell us the true encoding. + + Of course, none of this guarantees that we will be able to parse the + feed in the declared character encoding (assuming it was declared + correctly, which many are not). CJKCodecs and iconv_codec help a lot; + you should definitely install them if you can. + http://cjkpython.i18n.org/ + ''' + + def _parseHTTPContentType(content_type): + '''takes HTTP Content-Type header and returns (content type, charset) + + If no charset is specified, returns (content type, '') + If no content type is specified, returns ('', '') + Both return parameters are guaranteed to be lowercase strings + ''' + content_type = content_type or '' + content_type, params = cgi.parse_header(content_type) + return content_type, params.get('charset', '').replace("'", '') + + sniffed_xml_encoding = '' + xml_encoding = '' + true_encoding = '' + http_content_type, http_encoding = _parseHTTPContentType(http_headers.get('content-type')) + # Must sniff for non-ASCII-compatible character encodings before + # searching for XML declaration. This heuristic is defined in + # section F of the XML specification: + # http://www.w3.org/TR/REC-xml/#sec-guessing-no-ext-info + try: + if xml_data[:4] == '\x4c\x6f\xa7\x94': + # EBCDIC + xml_data = _ebcdic_to_ascii(xml_data) + elif xml_data[:4] == '\x00\x3c\x00\x3f': + # UTF-16BE + sniffed_xml_encoding = 'utf-16be' + xml_data = unicode(xml_data, 'utf-16be').encode('utf-8') + elif (len(xml_data) >= 4) and (xml_data[:2] == '\xfe\xff') and (xml_data[2:4] != '\x00\x00'): + # UTF-16BE with BOM + sniffed_xml_encoding = 'utf-16be' + xml_data = unicode(xml_data[2:], 'utf-16be').encode('utf-8') + elif xml_data[:4] == '\x3c\x00\x3f\x00': + # UTF-16LE + sniffed_xml_encoding = 'utf-16le' + xml_data = unicode(xml_data, 'utf-16le').encode('utf-8') + elif (len(xml_data) >= 4) and (xml_data[:2] == '\xff\xfe') and (xml_data[2:4] != '\x00\x00'): + # UTF-16LE with BOM + sniffed_xml_encoding = 'utf-16le' + xml_data = unicode(xml_data[2:], 'utf-16le').encode('utf-8') + elif xml_data[:4] == '\x00\x00\x00\x3c': + # UTF-32BE + sniffed_xml_encoding = 'utf-32be' + xml_data = unicode(xml_data, 'utf-32be').encode('utf-8') + elif xml_data[:4] == '\x3c\x00\x00\x00': + # UTF-32LE + sniffed_xml_encoding = 'utf-32le' + xml_data = unicode(xml_data, 'utf-32le').encode('utf-8') + elif xml_data[:4] == '\x00\x00\xfe\xff': + # UTF-32BE with BOM + sniffed_xml_encoding = 'utf-32be' + xml_data = unicode(xml_data[4:], 'utf-32be').encode('utf-8') + elif xml_data[:4] == '\xff\xfe\x00\x00': + # UTF-32LE with BOM + sniffed_xml_encoding = 'utf-32le' + xml_data = unicode(xml_data[4:], 'utf-32le').encode('utf-8') + elif xml_data[:3] == '\xef\xbb\xbf': + # UTF-8 with BOM + sniffed_xml_encoding = 'utf-8' + xml_data = unicode(xml_data[3:], 'utf-8').encode('utf-8') + else: + # ASCII-compatible + pass + xml_encoding_match = re.compile('^<\?.*encoding=[\'"](.*?)[\'"].*\?>').match(xml_data) + except: + xml_encoding_match = None + if xml_encoding_match: + xml_encoding = xml_encoding_match.groups()[0].lower() + if sniffed_xml_encoding and (xml_encoding in ('iso-10646-ucs-2', 'ucs-2', 'csunicode', 'iso-10646-ucs-4', 'ucs-4', 'csucs4', 'utf-16', 'utf-32', 'utf_16', 'utf_32', 'utf16', 'u16')): + xml_encoding = sniffed_xml_encoding + acceptable_content_type = 0 + application_content_types = ('application/xml', 'application/xml-dtd', 'application/xml-external-parsed-entity') + text_content_types = ('text/xml', 'text/xml-external-parsed-entity') + if (http_content_type in application_content_types) or \ + (http_content_type.startswith('application/') and http_content_type.endswith('+xml')): + acceptable_content_type = 1 + true_encoding = http_encoding or xml_encoding or 'utf-8' + elif (http_content_type in text_content_types) or \ + (http_content_type.startswith('text/')) and http_content_type.endswith('+xml'): + acceptable_content_type = 1 + true_encoding = http_encoding or 'us-ascii' + elif http_content_type.startswith('text/'): + true_encoding = http_encoding or 'us-ascii' + elif http_headers and (not http_headers.has_key('content-type')): + true_encoding = xml_encoding or 'iso-8859-1' + else: + true_encoding = xml_encoding or 'utf-8' + return true_encoding, http_encoding, xml_encoding, sniffed_xml_encoding, acceptable_content_type + +def _toUTF8(data, encoding): + '''Changes an XML data stream on the fly to specify a new encoding + + data is a raw sequence of bytes (not Unicode) that is presumed to be in %encoding already + encoding is a string recognized by encodings.aliases + ''' + if _debug: sys.stderr.write('entering _toUTF8, trying encoding %s\n' % encoding) + # strip Byte Order Mark (if present) + if (len(data) >= 4) and (data[:2] == '\xfe\xff') and (data[2:4] != '\x00\x00'): + if _debug: + sys.stderr.write('stripping BOM\n') + if encoding != 'utf-16be': + sys.stderr.write('trying utf-16be instead\n') + encoding = 'utf-16be' + data = data[2:] + elif (len(data) >= 4) and (data[:2] == '\xff\xfe') and (data[2:4] != '\x00\x00'): + if _debug: + sys.stderr.write('stripping BOM\n') + if encoding != 'utf-16le': + sys.stderr.write('trying utf-16le instead\n') + encoding = 'utf-16le' + data = data[2:] + elif data[:3] == '\xef\xbb\xbf': + if _debug: + sys.stderr.write('stripping BOM\n') + if encoding != 'utf-8': + sys.stderr.write('trying utf-8 instead\n') + encoding = 'utf-8' + data = data[3:] + elif data[:4] == '\x00\x00\xfe\xff': + if _debug: + sys.stderr.write('stripping BOM\n') + if encoding != 'utf-32be': + sys.stderr.write('trying utf-32be instead\n') + encoding = 'utf-32be' + data = data[4:] + elif data[:4] == '\xff\xfe\x00\x00': + if _debug: + sys.stderr.write('stripping BOM\n') + if encoding != 'utf-32le': + sys.stderr.write('trying utf-32le instead\n') + encoding = 'utf-32le' + data = data[4:] + newdata = unicode(data, encoding) + if _debug: sys.stderr.write('successfully converted %s data to unicode\n' % encoding) + declmatch = re.compile('^<\?xml[^>]*?>') + newdecl = '''''' + if declmatch.search(newdata): + newdata = declmatch.sub(newdecl, newdata) + else: + newdata = newdecl + u'\n' + newdata + return newdata.encode('utf-8') + +def _stripDoctype(data): + '''Strips DOCTYPE from XML document, returns (rss_version, stripped_data) + + rss_version may be 'rss091n' or None + stripped_data is the same XML document, minus the DOCTYPE + ''' + entity_pattern = re.compile(r']*?)>', re.MULTILINE) + data = entity_pattern.sub('', data) + doctype_pattern = re.compile(r']*?)>', re.MULTILINE) + doctype_results = doctype_pattern.findall(data) + doctype = doctype_results and doctype_results[0] or '' + if doctype.lower().count('netscape'): + version = 'rss091n' + else: + version = None + data = doctype_pattern.sub('', data) + return version, data + +def opensearch_parse(url_file_stream_or_string, etag=None, modified=None, agent=None, referrer=None, handlers=[]): + '''Parse a feed from a URL, file, stream, or string''' + result = FeedParserDict() + result['feed'] = FeedParserDict() + result['entries'] = [] + if _XML_AVAILABLE: + result['bozo'] = 0 + if type(handlers) == types.InstanceType: + handlers = [handlers] + try: + f = _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers) + data = f.read() + except Exception, e: + result['bozo'] = 1 + result['bozo_exception'] = e + data = '' + f = None + + # if feed is gzip-compressed, decompress it + if f and data and hasattr(f, 'headers'): + if gzip and f.headers.get('content-encoding', '') == 'gzip': + try: + data = gzip.GzipFile(fileobj=_StringIO(data)).read() + except Exception, e: + # Some feeds claim to be gzipped but they're not, so + # we get garbage. Ideally, we should re-request the + # feed without the 'Accept-encoding: gzip' header, + # but we don't. + result['bozo'] = 1 + result['bozo_exception'] = e + data = '' + elif zlib and f.headers.get('content-encoding', '') == 'deflate': + try: + data = zlib.decompress(data, -zlib.MAX_WBITS) + except Exception, e: + result['bozo'] = 1 + result['bozo_exception'] = e + data = '' + + # save HTTP headers + if hasattr(f, 'info'): + info = f.info() + result['etag'] = info.getheader('ETag') + last_modified = info.getheader('Last-Modified') + if last_modified: + result['modified'] = _parse_date(last_modified) + if hasattr(f, 'url'): + result['href'] = f.url + result['status'] = 200 + if hasattr(f, 'status'): + result['status'] = f.status + if hasattr(f, 'headers'): + result['headers'] = f.headers.dict + if hasattr(f, 'close'): + f.close() + + # there are four encodings to keep track of: + # - http_encoding is the encoding declared in the Content-Type HTTP header + # - xml_encoding is the encoding declared in the ; changed +# project name +#2.5 - 7/25/2003 - MAP - changed to Python license (all contributors agree); +# removed unnecessary urllib code -- urllib2 should always be available anyway; +# return actual url, status, and full HTTP headers (as result['url'], +# result['status'], and result['headers']) if parsing a remote feed over HTTP -- +# this should pass all the HTTP tests at ; +# added the latest namespace-of-the-week for RSS 2.0 +#2.5.1 - 7/26/2003 - RMK - clear opener.addheaders so we only send our custom +# User-Agent (otherwise urllib2 sends two, which confuses some servers) +#2.5.2 - 7/28/2003 - MAP - entity-decode inline xml properly; added support for +# inline and as used in some RSS 2.0 feeds +#2.5.3 - 8/6/2003 - TvdV - patch to track whether we're inside an image or +# textInput, and also to return the character encoding (if specified) +#2.6 - 1/1/2004 - MAP - dc:author support (MarekK); fixed bug tracking +# nested divs within content (JohnD); fixed missing sys import (JohanS); +# fixed regular expression to capture XML character encoding (Andrei); +# added support for Atom 0.3-style links; fixed bug with textInput tracking; +# added support for cloud (MartijnP); added support for multiple +# category/dc:subject (MartijnP); normalize content model: 'description' gets +# description (which can come from description, summary, or full content if no +# description), 'content' gets dict of base/language/type/value (which can come +# from content:encoded, xhtml:body, content, or fullitem); +# fixed bug matching arbitrary Userland namespaces; added xml:base and xml:lang +# tracking; fixed bug tracking unknown tags; fixed bug tracking content when +# element is not in default namespace (like Pocketsoap feed); +# resolve relative URLs in link, guid, docs, url, comments, wfw:comment, +# wfw:commentRSS; resolve relative URLs within embedded HTML markup in +# description, xhtml:body, content, content:encoded, title, subtitle, +# summary, info, tagline, and copyright; added support for pingback and +# trackback namespaces +#2.7 - 1/5/2004 - MAP - really added support for trackback and pingback +# namespaces, as opposed to 2.6 when I said I did but didn't really; +# sanitize HTML markup within some elements; added mxTidy support (if +# installed) to tidy HTML markup within some elements; fixed indentation +# bug in _parse_date (FazalM); use socket.setdefaulttimeout if available +# (FazalM); universal date parsing and normalization (FazalM): 'created', modified', +# 'issued' are parsed into 9-tuple date format and stored in 'created_parsed', +# 'modified_parsed', and 'issued_parsed'; 'date' is duplicated in 'modified' +# and vice-versa; 'date_parsed' is duplicated in 'modified_parsed' and vice-versa +#2.7.1 - 1/9/2004 - MAP - fixed bug handling " and '. fixed memory +# leak not closing url opener (JohnD); added dc:publisher support (MarekK); +# added admin:errorReportsTo support (MarekK); Python 2.1 dict support (MarekK) +#2.7.4 - 1/14/2004 - MAP - added workaround for improperly formed
tags in +# encoded HTML (skadz); fixed unicode handling in normalize_attrs (ChrisL); +# fixed relative URI processing for guid (skadz); added ICBM support; added +# base64 support +#2.7.5 - 1/15/2004 - MAP - added workaround for malformed DOCTYPE (seen on many +# blogspot.com sites); added _debug variable +#2.7.6 - 1/16/2004 - MAP - fixed bug with StringIO importing +#3.0b3 - 1/23/2004 - MAP - parse entire feed with real XML parser (if available); +# added several new supported namespaces; fixed bug tracking naked markup in +# description; added support for enclosure; added support for source; re-added +# support for cloud which got dropped somehow; added support for expirationDate +#3.0b4 - 1/26/2004 - MAP - fixed xml:lang inheritance; fixed multiple bugs tracking +# xml:base URI, one for documents that don't define one explicitly and one for +# documents that define an outer and an inner xml:base that goes out of scope +# before the end of the document +#3.0b5 - 1/26/2004 - MAP - fixed bug parsing multiple links at feed level +#3.0b6 - 1/27/2004 - MAP - added feed type and version detection, result['version'] +# will be one of SUPPORTED_VERSIONS.keys() or empty string if unrecognized; +# added support for creativeCommons:license and cc:license; added support for +# full Atom content model in title, tagline, info, copyright, summary; fixed bug +# with gzip encoding (not always telling server we support it when we do) +#3.0b7 - 1/28/2004 - MAP - support Atom-style author element in author_detail +# (dictionary of 'name', 'url', 'email'); map author to author_detail if author +# contains name + email address +#3.0b8 - 1/28/2004 - MAP - added support for contributor +#3.0b9 - 1/29/2004 - MAP - fixed check for presence of dict function; added +# support for summary +#3.0b10 - 1/31/2004 - MAP - incorporated ISO-8601 date parsing routines from +# xml.util.iso8601 +#3.0b11 - 2/2/2004 - MAP - added 'rights' to list of elements that can contain +# dangerous markup; fiddled with decodeEntities (not right); liberalized +# date parsing even further +#3.0b12 - 2/6/2004 - MAP - fiddled with decodeEntities (still not right); +# added support to Atom 0.2 subtitle; added support for Atom content model +# in copyright; better sanitizing of dangerous HTML elements with end tags +# (script, frameset) +#3.0b13 - 2/8/2004 - MAP - better handling of empty HTML tags (br, hr, img, +# etc.) in embedded markup, in either HTML or XHTML form (
,
,
) +#3.0b14 - 2/8/2004 - MAP - fixed CDATA handling in non-wellformed feeds under +# Python 2.1 +#3.0b15 - 2/11/2004 - MAP - fixed bug resolving relative links in wfw:commentRSS; +# fixed bug capturing author and contributor URL; fixed bug resolving relative +# links in author and contributor URL; fixed bug resolvin relative links in +# generator URL; added support for recognizing RSS 1.0; passed Simon Fell's +# namespace tests, and included them permanently in the test suite with his +# permission; fixed namespace handling under Python 2.1 +#3.0b16 - 2/12/2004 - MAP - fixed support for RSS 0.90 (broken in b15) +#3.0b17 - 2/13/2004 - MAP - determine character encoding as per RFC 3023 +#3.0b18 - 2/17/2004 - MAP - always map description to summary_detail (Andrei); +# use libxml2 (if available) +#3.0b19 - 3/15/2004 - MAP - fixed bug exploding author information when author +# name was in parentheses; removed ultra-problematic mxTidy support; patch to +# workaround crash in PyXML/expat when encountering invalid entities +# (MarkMoraes); support for textinput/textInput +#3.0b20 - 4/7/2004 - MAP - added CDF support +#3.0b21 - 4/14/2004 - MAP - added Hot RSS support +#3.0b22 - 4/19/2004 - MAP - changed 'channel' to 'feed', 'item' to 'entries' in +# results dict; changed results dict to allow getting values with results.key +# as well as results[key]; work around embedded illformed HTML with half +# a DOCTYPE; work around malformed Content-Type header; if character encoding +# is wrong, try several common ones before falling back to regexes (if this +# works, bozo_exception is set to CharacterEncodingOverride); fixed character +# encoding issues in BaseHTMLProcessor by tracking encoding and converting +# from Unicode to raw strings before feeding data to sgmllib.SGMLParser; +# convert each value in results to Unicode (if possible), even if using +# regex-based parsing +#3.0b23 - 4/21/2004 - MAP - fixed UnicodeDecodeError for feeds that contain +# high-bit characters in attributes in embedded HTML in description (thanks +# Thijs van de Vossen); moved guid, date, and date_parsed to mapped keys in +# FeedParserDict; tweaked FeedParserDict.has_key to return True if asking +# about a mapped key +#3.0fc1 - 4/23/2004 - MAP - made results.entries[0].links[0] and +# results.entries[0].enclosures[0] into FeedParserDict; fixed typo that could +# cause the same encoding to be tried twice (even if it failed the first time); +# fixed DOCTYPE stripping when DOCTYPE contained entity declarations; +# better textinput and image tracking in illformed RSS 1.0 feeds +#3.0fc2 - 5/10/2004 - MAP - added and passed Sam's amp tests; added and passed +# my blink tag tests +#3.0fc3 - 6/18/2004 - MAP - fixed bug in _changeEncodingDeclaration that +# failed to parse utf-16 encoded feeds; made source into a FeedParserDict; +# duplicate admin:generatorAgent/@rdf:resource in generator_detail.url; +# added support for image; refactored parse() fallback logic to try other +# encodings if SAX parsing fails (previously it would only try other encodings +# if re-encoding failed); remove unichr madness in normalize_attrs now that +# we're properly tracking encoding in and out of BaseHTMLProcessor; set +# feed.language from root-level xml:lang; set entry.id from rdf:about; +# send Accept header +#3.0 - 6/21/2004 - MAP - don't try iso-8859-1 (can't distinguish between +# iso-8859-1 and windows-1252 anyway, and most incorrectly marked feeds are +# windows-1252); fixed regression that could cause the same encoding to be +# tried twice (even if it failed the first time) +#3.0.1 - 6/22/2004 - MAP - default to us-ascii for all text/* content types; +# recover from malformed content-type header parameter with no equals sign +# ('text/xml; charset:iso-8859-1') +#3.1 - 6/28/2004 - MAP - added and passed tests for converting HTML entities +# to Unicode equivalents in illformed feeds (aaronsw); added and +# passed tests for converting character entities to Unicode equivalents +# in illformed feeds (aaronsw); test for valid parsers when setting +# XML_AVAILABLE; make version and encoding available when server returns +# a 304; add handlers parameter to pass arbitrary urllib2 handlers (like +# digest auth or proxy support); add code to parse username/password +# out of url and send as basic authentication; expose downloading-related +# exceptions in bozo_exception (aaronsw); added __contains__ method to +# FeedParserDict (aaronsw); added publisher_detail (aaronsw) +#3.2 - 7/3/2004 - MAP - use cjkcodecs and iconv_codec if available; always +# convert feed to UTF-8 before passing to XML parser; completely revamped +# logic for determining character encoding and attempting XML parsing +# (much faster); increased default timeout to 20 seconds; test for presence +# of Location header on redirects; added tests for many alternate character +# encodings; support various EBCDIC encodings; support UTF-16BE and +# UTF16-LE with or without a BOM; support UTF-8 with a BOM; support +# UTF-32BE and UTF-32LE with or without a BOM; fixed crashing bug if no +# XML parsers are available; added support for 'Content-encoding: deflate'; +# send blank 'Accept-encoding: ' header if neither gzip nor zlib modules +# are available +#3.3 - 7/15/2004 - MAP - optimize EBCDIC to ASCII conversion; fix obscure +# problem tracking xml:base and xml:lang if element declares it, child +# doesn't, first grandchild redeclares it, and second grandchild doesn't; +# refactored date parsing; defined public registerDateHandler so callers +# can add support for additional date formats at runtime; added support +# for OnBlog, Nate, MSSQL, Greek, and Hungarian dates (ytrewq1); added +# zopeCompatibilityHack() which turns FeedParserDict into a regular +# dictionary, required for Zope compatibility, and also makes command- +# line debugging easier because pprint module formats real dictionaries +# better than dictionary-like objects; added NonXMLContentType exception, +# which is stored in bozo_exception when a feed is served with a non-XML +# media type such as 'text/plain'; respect Content-Language as default +# language if not xml:lang is present; cloud dict is now FeedParserDict; +# generator dict is now FeedParserDict; better tracking of xml:lang, +# including support for xml:lang='' to unset the current language; +# recognize RSS 1.0 feeds even when RSS 1.0 namespace is not the default +# namespace; don't overwrite final status on redirects (scenarios: +# redirecting to a URL that returns 304, redirecting to a URL that +# redirects to another URL with a different type of redirect); add +# support for HTTP 303 redirects +#4.0 - MAP - support for relative URIs in xml:base attribute; fixed +# encoding issue with mxTidy (phopkins); preliminary support for RFC 3229; +# support for Atom 1.0; support for iTunes extensions; new 'tags' for +# categories/keywords/etc. as array of dict +# {'term': term, 'scheme': scheme, 'label': label} to match Atom 1.0 +# terminology; parse RFC 822-style dates with no time; lots of other +# bug fixes diff --git a/src/calibre/utils/opensearch/query.py b/src/calibre/utils/opensearch/query.py new file mode 100644 index 0000000000..31c37ca923 --- /dev/null +++ b/src/calibre/utils/opensearch/query.py @@ -0,0 +1,66 @@ +from urlparse import urlparse, urlunparse +from urllib import urlencode +from cgi import parse_qs + +class Query: + """Represents an opensearch query. Used internally by the Client to + construct an opensearch url to request. Really this class is just a + helper for substituting values into the macros in a format. + + format = 'http://beta.indeed.com/opensearch?q={searchTerms}&start={startIndex}&limit={count}' + q = Query(format) + q.searchTerms('zx81') + q.startIndex = 1 + q.count = 25 + print q.to_url() + """ + + standard_macros = ['searchTerms','count','startIndex','startPage', + 'language', 'outputEncoding', 'inputEncoding'] + + def __init__(self, format): + """Create a query object by passing it the url format obtained + from the opensearch Description. + """ + self.format = format + + # unpack the url to a tuple + self.url_parts = urlparse(format) + + # unpack the query string to a dictionary + self.query_string = parse_qs(self.url_parts[4]) + + # look for standard macros and create a mapping of the + # opensearch names to the service specific ones + # so q={searchTerms} will result in a mapping between searchTerms and q + self.macro_map = {} + for key,values in self.query_string.items(): + # TODO eventually optional/required params should be + # distinguished somehow (the ones with/without trailing ? + macro = values[0].replace('{','').replace('}','').replace('?','') + if macro in Query.standard_macros: + self.macro_map[macro] = key + + def url(self): + # copy the original query string + query_string = dict(self.query_string) + + # iterate through macros and set the position in the querystring + for macro, name in self.macro_map.items(): + if hasattr(self, macro): + # set the name/value pair + query_string[name] = [getattr(self, macro)] + else: + # remove the name/value pair + del(query_string[name]) + + # copy the url parts and substitute in our new query string + url_parts = list(self.url_parts) + url_parts[4] = urlencode(query_string, 1) + + # recompose and return url + return urlunparse(tuple(url_parts)) + + def has_macro(self, macro): + return self.macro_map.has_key(macro) + diff --git a/src/calibre/utils/opensearch/results.py b/src/calibre/utils/opensearch/results.py new file mode 100644 index 0000000000..1922848e22 --- /dev/null +++ b/src/calibre/utils/opensearch/results.py @@ -0,0 +1,131 @@ +import osfeedparser + +class Results(object): + + def __init__(self, query, agent=None): + self.agent = agent + self._fetch(query) + self._iter = 0 + + def __iter__(self): + self._iter = 0 + return self + + def __len__(self): + return self.totalResults + + def next(self): + + # just keep going like the energizer bunny + while True: + + # return any item we haven't returned + if self._iter < len(self.items): + self._iter += 1 + return self.items[self._iter-1] + + # if there appears to be more to fetch + if \ + self.totalResults != 0 \ + and self.totalResults > self.startIndex + self.itemsPerPage - 1: + + # get the next query + next_query = self._get_next_query() + + # if we got one executed it and go back to the beginning + if next_query: + self._fetch(next_query) + # very important to reset this counter + # or else the return will fail + self._iter = 0 + + else: + raise StopIteration + + + def _fetch(self, query): + feed = osfeedparser.opensearch_parse(query.url(), agent=self.agent) + self.feed = feed + + # general channel stuff + channel = feed['feed'] + self.title = _pick(channel,'title') + self.link = _pick(channel,'link') + self.description = _pick(channel,'description') + self.language = _pick(channel,'language') + self.copyright = _pick(channel,'copyright') + + # get back opensearch specific values + self.totalResults = _pick(channel,'opensearch_totalresults',0) + self.startIndex = _pick(channel,'opensearch_startindex',1) + self.itemsPerPage = _pick(channel,'opensearch_itemsperpage',0) + + # alias items from the feed to our results object + self.items = feed['items'] + + # set default values if necessary + if self.startIndex == 0: + self.startIndex = 1 + if self.itemsPerPage == 0 and len(self.items) > 0: + self.itemsPerPage = len(self.items) + + # store away query for calculating next results + # if necessary + self.last_query = query + + + def _get_next_query(self): + # update our query to get the next set of records + query = self.last_query + + # use start page if the query supports it + if query.has_macro('startPage'): + # if the query already defined the startPage + # we just need to increment it + if hasattr(query, 'startPage'): + query.startPage += 1 + # to issue the first query startPage might not have + # been specified, so set it to 2 + else: + query.startPage = 2 + return query + + # otherwise the query should support startIndex + elif query.has_macro('startIndex'): + # if startIndex was used before we just add the + # items per page to it to get the next set + if hasattr(query, 'startIndex'): + query.startIndex += self.itemsPerPage + # to issue the first query the startIndex may have + # been left blank in that case we assume it to be + # the item just after the last one on this page + else: + query.startIndex = self.itemsPerPage + 1 + return query + + # doesn't look like there is another stage to this query + return None + + +# helper for pulling values out of a dictionary if they're there +# and returning a default value if they're not +def _pick(d,key,default=None): + + # get the value out + value = d.get(key) + + # if it wasn't there return the default + if value == None: + return default + + # if they want an int try to convert to an int + # and return default if it fails + if type(default) == int: + try: + return int(d[key]) + except: + return default + + # otherwise we're good to return the value + return value + diff --git a/src/calibre/utils/opensearch/url.py b/src/calibre/utils/opensearch/url.py new file mode 100644 index 0000000000..665c024ef3 --- /dev/null +++ b/src/calibre/utils/opensearch/url.py @@ -0,0 +1,8 @@ +class URL: + """Class for representing a URL in an opensearch v1.1 query""" + + def __init__(self, type='', template='', method='GET'): + self.type = type + self.template = template + self.method = 'GET' + self.params = [] From 5570a17ee0544b2b4284eba3ed0b37cefe801f9b Mon Sep 17 00:00:00 2001 From: John Schember Date: Sun, 26 Jun 2011 10:33:22 -0400 Subject: [PATCH 02/22] Store: OpenSearchStore fix opening store directly. --- src/calibre/gui2/store/opensearch_store.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/src/calibre/gui2/store/opensearch_store.py b/src/calibre/gui2/store/opensearch_store.py index f473608309..773bc6d4a7 100644 --- a/src/calibre/gui2/store/opensearch_store.py +++ b/src/calibre/gui2/store/opensearch_store.py @@ -23,10 +23,13 @@ class OpenSearchStore(StorePlugin): web_url = '' def open(self, parent=None, detail_item=None, external=False): + if not hasattr(self, 'web_url'): + return + if external or self.config.get('open_external', False): - open_url(QUrl(detail_item if detail_item else self.url)) + open_url(QUrl(detail_item if detail_item else self.web_url)) else: - d = WebStoreDialog(self.gui, self.url, parent, detail_item) + d = WebStoreDialog(self.gui, self.web_url, parent, detail_item) d.setWindowTitle(self.name) d.set_tags(self.config.get('tags', '')) d.exec_() From 85a4cca82249dc24fc633791b7de94ed1f8e23dc Mon Sep 17 00:00:00 2001 From: John Schember Date: Sun, 26 Jun 2011 10:41:43 -0400 Subject: [PATCH 03/22] Store: Convert EpubBud to use new OpenSearchStore class. --- src/calibre/gui2/store/epubbud_plugin.py | 75 ++++------------------ src/calibre/gui2/store/opensearch_store.py | 2 +- 2 files changed, 12 insertions(+), 65 deletions(-) diff --git a/src/calibre/gui2/store/epubbud_plugin.py b/src/calibre/gui2/store/epubbud_plugin.py index d6193f6ae0..7c581b9578 100644 --- a/src/calibre/gui2/store/epubbud_plugin.py +++ b/src/calibre/gui2/store/epubbud_plugin.py @@ -6,73 +6,20 @@ __license__ = 'GPL 3' __copyright__ = '2011, John Schember ' __docformat__ = 'restructuredtext en' -import urllib -from contextlib import closing - -from lxml import html - -from PyQt4.Qt import QUrl - -from calibre import browser, url_slash_cleaner -from calibre.gui2 import open_url -from calibre.gui2.store import StorePlugin from calibre.gui2.store.basic_config import BasicStoreConfig +from calibre.gui2.store.opensearch_store import OpenSearchStore from calibre.gui2.store.search_result import SearchResult -from calibre.gui2.store.web_store_dialog import WebStoreDialog -class EpubBudStore(BasicStoreConfig, StorePlugin): +class EpubBudStore(BasicStoreConfig, OpenSearchStore): - def open(self, parent=None, detail_item=None, external=False): - url = 'http://epubbud.com/' - - if external or self.config.get('open_external', False): - open_url(QUrl(url_slash_cleaner(detail_item if detail_item else url))) - else: - d = WebStoreDialog(self.gui, url, parent, detail_item) - d.setWindowTitle(self.name) - d.set_tags(self.config.get('tags', '')) - d.exec_() + open_search_url = 'http://www.epubbud.com/feeds/opensearch.xml' + web_url = 'http://www.epubbud.com/' + + # http://www.epubbud.com/feeds/catalog.atom def search(self, query, max_results=10, timeout=60): - ''' - OPDS based search. - - We really should get the catelog from http://pragprog.com/catalog.opds - and look for the application/opensearchdescription+xml entry. - Then get the opensearch description to get the search url and - format. However, we are going to be lazy and hard code it. - ''' - url = 'http://www.epubbud.com/search.php?format=atom&q=' + urllib.quote_plus(query) - - br = browser() - - counter = max_results - with closing(br.open(url, timeout=timeout)) as f: - # Use html instead of etree as html allows us - # to ignore the namespace easily. - doc = html.fromstring(f.read()) - for data in doc.xpath('//entry'): - if counter <= 0: - break - - id = ''.join(data.xpath('.//id/text()')) - if not id: - continue - - cover_url = ''.join(data.xpath('.//link[@rel="http://opds-spec.org/thumbnail"]/@href')) - - title = u''.join(data.xpath('.//title/text()')) - author = u''.join(data.xpath('.//author/name/text()')) - - counter -= 1 - - s = SearchResult() - s.cover_url = cover_url - s.title = title.strip() - s.author = author.strip() - s.price = '$0.00' - s.detail_item = id.strip() - s.drm = SearchResult.DRM_UNLOCKED - s.formats = 'EPUB' - - yield s + for s in OpenSearchStore.search(self, query, max_results, timeout): + s.price = '$0.00' + s.drm = SearchResult.DRM_UNLOCKED + s.formats = 'EPUB' + yield s diff --git a/src/calibre/gui2/store/opensearch_store.py b/src/calibre/gui2/store/opensearch_store.py index 773bc6d4a7..a3dc0e7941 100644 --- a/src/calibre/gui2/store/opensearch_store.py +++ b/src/calibre/gui2/store/opensearch_store.py @@ -54,7 +54,7 @@ class OpenSearchStore(StorePlugin): links = r.get('links', None) for l in links: if l.get('rel', None): - if l['rel'] == u'http://opds-spec.org/image/thumbnail': + if l['rel'] in ('http://opds-spec.org/thumbnail', 'http://opds-spec.org/image/thumbnail'): s.cover_url = l.get('href', '') elif l['rel'] == u'http://opds-spec.org/acquisition/buy': s.detail_item = l.get('href', s.detail_item) From 08e263e29717da2df0e4c23c66eea1682e5b4340 Mon Sep 17 00:00:00 2001 From: John Schember Date: Sun, 26 Jun 2011 10:58:49 -0400 Subject: [PATCH 04/22] OpenSearch: Fix a few bugs. Store: Use Feedbooks OpenSearch. --- src/calibre/gui2/store/feedbooks_plugin.py | 104 +++---------------- src/calibre/utils/opensearch/description.py | 2 +- src/calibre/utils/opensearch/osfeedparser.py | 4 +- 3 files changed, 16 insertions(+), 94 deletions(-) diff --git a/src/calibre/gui2/store/feedbooks_plugin.py b/src/calibre/gui2/store/feedbooks_plugin.py index 9b1f7f6574..96d0a10dc7 100644 --- a/src/calibre/gui2/store/feedbooks_plugin.py +++ b/src/calibre/gui2/store/feedbooks_plugin.py @@ -6,101 +6,23 @@ __license__ = 'GPL 3' __copyright__ = '2011, John Schember ' __docformat__ = 'restructuredtext en' -import urllib2 -from contextlib import closing - -from lxml import html - -from PyQt4.Qt import QUrl - -from calibre import browser, url_slash_cleaner -from calibre.gui2 import open_url -from calibre.gui2.store import StorePlugin from calibre.gui2.store.basic_config import BasicStoreConfig +from calibre.gui2.store.opensearch_store import OpenSearchStore from calibre.gui2.store.search_result import SearchResult -from calibre.gui2.store.web_store_dialog import WebStoreDialog -class FeedbooksStore(BasicStoreConfig, StorePlugin): +class FeedbooksStore(BasicStoreConfig, OpenSearchStore): - def open(self, parent=None, detail_item=None, external=False): - url = 'http://m.feedbooks.com/' - ext_url = 'http://feedbooks.com/' - - if external or self.config.get('open_external', False): - if detail_item: - ext_url = ext_url + detail_item - open_url(QUrl(url_slash_cleaner(ext_url))) - else: - detail_url = None - if detail_item: - detail_url = url + detail_item - d = WebStoreDialog(self.gui, url, parent, detail_url) - d.setWindowTitle(self.name) - d.set_tags(self.config.get('tags', '')) - d.exec_() + open_search_url = 'http://assets0.feedbooks.net/opensearch.xml?t=1253087147' + web_url = 'http://feedbooks.com/' + + # http://www.feedbooks.com/catalog def search(self, query, max_results=10, timeout=60): - url = 'http://m.feedbooks.com/search?query=' + urllib2.quote(query) - - br = browser() - - counter = max_results - with closing(br.open(url, timeout=timeout)) as f: - doc = html.fromstring(f.read()) - for data in doc.xpath('//ul[@class="m-list"]//li'): - if counter <= 0: - break - data = html.fromstring(html.tostring(data)) - - id = '' - id_a = data.xpath('//a[@class="buy"]') - if id_a: - id = id_a[0].get('href', None) - id = id.split('/')[-2] - id = '/item/' + id - else: - id_a = data.xpath('//a[@class="download"]') - if id_a: - id = id_a[0].get('href', None) - id = id.split('/')[-1] - id = id.split('.')[0] - id = '/book/' + id - if not id: - continue - - title = ''.join(data.xpath('//h5//a/text()')) - author = ''.join(data.xpath('//h6//a/text()')) - price = ''.join(data.xpath('//a[@class="buy"]/text()')) - formats = 'EPUB' - if not price: - price = '$0.00' - formats = 'EPUB, MOBI, PDF' - cover_url = '' - cover_url_img = data.xpath('//img') - if cover_url_img: - cover_url = cover_url_img[0].get('src') - cover_url.split('?')[0] - - counter -= 1 - - s = SearchResult() - s.cover_url = cover_url - s.title = title.strip() - s.author = author.strip() - s.price = price.replace(' ', '').strip() - s.detail_item = id.strip() - s.formats = formats - - yield s - - def get_details(self, search_result, timeout): - url = 'http://m.feedbooks.com/' - - br = browser() - with closing(br.open(url_slash_cleaner(url + search_result.detail_item), timeout=timeout)) as nf: - idata = html.fromstring(nf.read()) - if idata.xpath('boolean(//div[contains(@class, "m-description-long")]//p[contains(., "DRM") or contains(b, "Protection")])'): - search_result.drm = SearchResult.DRM_LOCKED + for s in OpenSearchStore.search(self, query, max_results, timeout): + if s.downloads: + s.drm = SearchResult.DRM_UNLOCKED + s.price = '$0.00' else: - search_result.drm = SearchResult.DRM_UNLOCKED - return True + s.drm = SearchResult.DRM_LOCKED + s.formats = 'EPUB' + yield s diff --git a/src/calibre/utils/opensearch/description.py b/src/calibre/utils/opensearch/description.py index d486e615df..2909dbceb3 100644 --- a/src/calibre/utils/opensearch/description.py +++ b/src/calibre/utils/opensearch/description.py @@ -87,7 +87,7 @@ class Description: return self.urls[0].template # out of luck - return Nil + return None # these are internal methods for querying xml diff --git a/src/calibre/utils/opensearch/osfeedparser.py b/src/calibre/utils/opensearch/osfeedparser.py index 364de2b26c..ed894cb572 100644 --- a/src/calibre/utils/opensearch/osfeedparser.py +++ b/src/calibre/utils/opensearch/osfeedparser.py @@ -46,8 +46,8 @@ _debug = 0 # If you are embedding feedparser in a larger application, you should # change this to your application name and URL. # Changed by John Schember -from calibre import random_user_agent -USER_AGENT = random_user_agent() +from calibre import USER_AGENT +USER_AGENT = USER_AGENT # HTTP "Accept" header to send to servers when downloading feeds. If you don't # want to send an Accept header, set this to None. From 12e9b6194e7585039abf1167da9c7d634d9eeca2 Mon Sep 17 00:00:00 2001 From: John Schember Date: Sun, 26 Jun 2011 11:15:19 -0400 Subject: [PATCH 05/22] Store: Organize store plugins into their own module. --- src/calibre/customize/builtins.py | 74 +++++++++---------- src/calibre/gui2/store/stores/__init__.py | 3 + .../store/{ => stores}/amazon_de_plugin.py | 0 .../gui2/store/{ => stores}/amazon_plugin.py | 0 .../store/{ => stores}/amazon_uk_plugin.py | 0 .../store/{ => stores}/archive_org_plugin.py | 0 .../{ => stores}/baen_webscription_plugin.py | 0 .../{ => stores}/beam_ebooks_de_plugin.py | 0 .../gui2/store/{ => stores}/bewrite_plugin.py | 0 .../gui2/store/{ => stores}/bn_plugin.py | 0 .../{ => stores}/diesel_ebooks_plugin.py | 0 .../store/{ => stores}/ebooks_com_plugin.py | 0 .../{ => stores}/ebookshoppe_uk_plugin.py | 0 .../store/{ => stores}/eharlequin_plugin.py | 0 .../gui2/store/{ => stores}/epubbud_plugin.py | 0 .../store/{ => stores}/epubbuy_de_plugin.py | 0 .../store/{ => stores}/feedbooks_plugin.py | 0 .../store/{ => stores}/foyles_uk_plugin.py | 0 .../gui2/store/{ => stores}/gandalf_plugin.py | 0 .../store/{ => stores}/google_books_plugin.py | 0 .../store/{ => stores}/gutenberg_plugin.py | 0 .../gui2/store/{ => stores}/kobo_plugin.py | 0 .../gui2/store/{ => stores}/legimi_plugin.py | 0 .../store/{ => stores}/libri_de_plugin.py | 0 .../store/{ => stores}/manybooks_plugin.py | 0 .../store/{ => stores}/mobileread/__init__.py | 0 .../mobileread/adv_search_builder.py | 2 +- .../mobileread/adv_search_builder.ui | 0 .../mobileread/cache_progress_dialog.py | 2 +- .../mobileread/cache_progress_dialog.ui | 0 .../mobileread/cache_update_thread.py | 0 .../mobileread/mobileread_plugin.py | 8 +- .../store/{ => stores}/mobileread/models.py | 0 .../{ => stores}/mobileread/store_dialog.py | 6 +- .../{ => stores}/mobileread/store_dialog.ui | 0 .../gui2/store/{ => stores}/nexto_plugin.py | 0 .../store/{ => stores}/open_books_plugin.py | 0 .../store/{ => stores}/open_library_plugin.py | 0 .../gui2/store/{ => stores}/oreilly_plugin.py | 0 .../pragmatic_bookshelf_plugin.py | 0 .../store/{ => stores}/smashwords_plugin.py | 0 .../store/{ => stores}/virtualo_plugin.py | 0 .../{ => stores}/waterstones_uk_plugin.py | 0 .../{ => stores}/weightless_books_plugin.py | 0 .../store/{ => stores}/whsmith_uk_plugin.py | 0 .../wizards_tower_books_plugin.py | 0 .../gui2/store/{ => stores}/woblink_plugin.py | 0 .../gui2/store/{ => stores}/zixo_plugin.py | 0 48 files changed, 49 insertions(+), 46 deletions(-) create mode 100644 src/calibre/gui2/store/stores/__init__.py rename src/calibre/gui2/store/{ => stores}/amazon_de_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/amazon_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/amazon_uk_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/archive_org_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/baen_webscription_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/beam_ebooks_de_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/bewrite_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/bn_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/diesel_ebooks_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/ebooks_com_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/ebookshoppe_uk_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/eharlequin_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/epubbud_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/epubbuy_de_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/feedbooks_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/foyles_uk_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/gandalf_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/google_books_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/gutenberg_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/kobo_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/legimi_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/libri_de_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/manybooks_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/mobileread/__init__.py (100%) rename src/calibre/gui2/store/{ => stores}/mobileread/adv_search_builder.py (97%) rename src/calibre/gui2/store/{ => stores}/mobileread/adv_search_builder.ui (100%) rename src/calibre/gui2/store/{ => stores}/mobileread/cache_progress_dialog.py (94%) rename src/calibre/gui2/store/{ => stores}/mobileread/cache_progress_dialog.ui (100%) rename src/calibre/gui2/store/{ => stores}/mobileread/cache_update_thread.py (100%) rename src/calibre/gui2/store/{ => stores}/mobileread/mobileread_plugin.py (91%) rename src/calibre/gui2/store/{ => stores}/mobileread/models.py (100%) rename src/calibre/gui2/store/{ => stores}/mobileread/store_dialog.py (93%) rename src/calibre/gui2/store/{ => stores}/mobileread/store_dialog.ui (100%) rename src/calibre/gui2/store/{ => stores}/nexto_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/open_books_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/open_library_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/oreilly_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/pragmatic_bookshelf_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/smashwords_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/virtualo_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/waterstones_uk_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/weightless_books_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/whsmith_uk_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/wizards_tower_books_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/woblink_plugin.py (100%) rename src/calibre/gui2/store/{ => stores}/zixo_plugin.py (100%) diff --git a/src/calibre/customize/builtins.py b/src/calibre/customize/builtins.py index 8305e32303..333a5baaa4 100644 --- a/src/calibre/customize/builtins.py +++ b/src/calibre/customize/builtins.py @@ -1148,7 +1148,7 @@ plugins += [LookAndFeel, Behavior, Columns, Toolbar, Search, InputOptions, class StoreAmazonKindleStore(StoreBase): name = 'Amazon Kindle' description = u'Kindle books from Amazon.' - actual_plugin = 'calibre.gui2.store.amazon_plugin:AmazonKindleStore' + actual_plugin = 'calibre.gui2.store.stores.amazon_plugin:AmazonKindleStore' headquarters = 'US' formats = ['KINDLE'] @@ -1158,7 +1158,7 @@ class StoreAmazonDEKindleStore(StoreBase): name = 'Amazon DE Kindle' author = 'Charles Haley' description = u'Kindle Bücher von Amazon.' - actual_plugin = 'calibre.gui2.store.amazon_de_plugin:AmazonDEKindleStore' + actual_plugin = 'calibre.gui2.store.stores.amazon_de_plugin:AmazonDEKindleStore' headquarters = 'DE' formats = ['KINDLE'] @@ -1168,7 +1168,7 @@ class StoreAmazonUKKindleStore(StoreBase): name = 'Amazon UK Kindle' author = 'Charles Haley' description = u'Kindle books from Amazon\'s UK web site. Also, includes French language ebooks.' - actual_plugin = 'calibre.gui2.store.amazon_uk_plugin:AmazonUKKindleStore' + actual_plugin = 'calibre.gui2.store.stores.amazon_uk_plugin:AmazonUKKindleStore' headquarters = 'UK' formats = ['KINDLE'] @@ -1177,7 +1177,7 @@ class StoreAmazonUKKindleStore(StoreBase): class StoreArchiveOrgStore(StoreBase): name = 'Archive.org' description = u'An Internet library offering permanent access for researchers, historians, scholars, people with disabilities, and the general public to historical collections that exist in digital format.' - actual_plugin = 'calibre.gui2.store.archive_org_plugin:ArchiveOrgStore' + actual_plugin = 'calibre.gui2.store.stores.archive_org_plugin:ArchiveOrgStore' drm_free_only = True headquarters = 'US' @@ -1186,7 +1186,7 @@ class StoreArchiveOrgStore(StoreBase): class StoreBaenWebScriptionStore(StoreBase): name = 'Baen WebScription' description = u'Sci-Fi & Fantasy brought to you by Jim Baen.' - actual_plugin = 'calibre.gui2.store.baen_webscription_plugin:BaenWebScriptionStore' + actual_plugin = 'calibre.gui2.store.stores.baen_webscription_plugin:BaenWebScriptionStore' drm_free_only = True headquarters = 'US' @@ -1195,7 +1195,7 @@ class StoreBaenWebScriptionStore(StoreBase): class StoreBNStore(StoreBase): name = 'Barnes and Noble' description = u'The world\'s largest book seller. As the ultimate destination for book lovers, Barnes & Noble.com offers an incredible array of content.' - actual_plugin = 'calibre.gui2.store.bn_plugin:BNStore' + actual_plugin = 'calibre.gui2.store.stores.bn_plugin:BNStore' headquarters = 'US' formats = ['NOOK'] @@ -1205,7 +1205,7 @@ class StoreBeamEBooksDEStore(StoreBase): name = 'Beam EBooks DE' author = 'Charles Haley' description = u'Bei uns finden Sie: Tausende deutschsprachige eBooks; Alle eBooks ohne hartes DRM; PDF, ePub und Mobipocket Format; Sofortige Verfügbarkeit - 24 Stunden am Tag; Günstige Preise; eBooks für viele Lesegeräte, PC,Mac und Smartphones; Viele Gratis eBooks' - actual_plugin = 'calibre.gui2.store.beam_ebooks_de_plugin:BeamEBooksDEStore' + actual_plugin = 'calibre.gui2.store.stores.beam_ebooks_de_plugin:BeamEBooksDEStore' drm_free_only = True headquarters = 'DE' @@ -1215,7 +1215,7 @@ class StoreBeamEBooksDEStore(StoreBase): class StoreBeWriteStore(StoreBase): name = 'BeWrite Books' description = u'Publishers of fine books. Highly selective and editorially driven. Does not offer: books for children or exclusively YA, erotica, swords-and-sorcery fantasy and space-opera-style science fiction. All other genres are represented.' - actual_plugin = 'calibre.gui2.store.bewrite_plugin:BeWriteStore' + actual_plugin = 'calibre.gui2.store.stores.bewrite_plugin:BeWriteStore' drm_free_only = True headquarters = 'US' @@ -1224,7 +1224,7 @@ class StoreBeWriteStore(StoreBase): class StoreDieselEbooksStore(StoreBase): name = 'Diesel eBooks' description = u'Instant access to over 2.4 million titles from hundreds of publishers including Harlequin, HarperCollins, John Wiley & Sons, McGraw-Hill, Simon & Schuster and Random House.' - actual_plugin = 'calibre.gui2.store.diesel_ebooks_plugin:DieselEbooksStore' + actual_plugin = 'calibre.gui2.store.stores.diesel_ebooks_plugin:DieselEbooksStore' headquarters = 'US' formats = ['EPUB', 'PDF'] @@ -1233,7 +1233,7 @@ class StoreDieselEbooksStore(StoreBase): class StoreEbookscomStore(StoreBase): name = 'eBooks.com' description = u'Sells books in multiple electronic formats in all categories. Technical infrastructure is cutting edge, robust and scalable, with servers in the US and Europe.' - actual_plugin = 'calibre.gui2.store.ebooks_com_plugin:EbookscomStore' + actual_plugin = 'calibre.gui2.store.stores.ebooks_com_plugin:EbookscomStore' headquarters = 'US' formats = ['EPUB', 'LIT', 'MOBI', 'PDF'] @@ -1243,7 +1243,7 @@ class StoreEPubBuyDEStore(StoreBase): name = 'EPUBBuy DE' author = 'Charles Haley' description = u'Bei EPUBBuy.com finden Sie ausschliesslich eBooks im weitverbreiteten EPUB-Format und ohne DRM. So haben Sie die freie Wahl, wo Sie Ihr eBook lesen: Tablet, eBook-Reader, Smartphone oder einfach auf Ihrem PC. So macht eBook-Lesen Spaß!' - actual_plugin = 'calibre.gui2.store.epubbuy_de_plugin:EPubBuyDEStore' + actual_plugin = 'calibre.gui2.store.stores.epubbuy_de_plugin:EPubBuyDEStore' drm_free_only = True headquarters = 'DE' @@ -1254,7 +1254,7 @@ class StoreEBookShoppeUKStore(StoreBase): name = 'ebookShoppe UK' author = u'Charles Haley' description = u'We made this website in an attempt to offer the widest range of UK eBooks possible across and as many formats as we could manage.' - actual_plugin = 'calibre.gui2.store.ebookshoppe_uk_plugin:EBookShoppeUKStore' + actual_plugin = 'calibre.gui2.store.stores.ebookshoppe_uk_plugin:EBookShoppeUKStore' headquarters = 'UK' formats = ['EPUB', 'PDF'] @@ -1263,7 +1263,7 @@ class StoreEBookShoppeUKStore(StoreBase): class StoreEHarlequinStore(StoreBase): name = 'eHarlequin' description = u'A global leader in series romance and one of the world\'s leading publishers of books for women. Offers women a broad range of reading from romance to bestseller fiction, from young adult novels to erotic literature, from nonfiction to fantasy, from African-American novels to inspirational romance, and more.' - actual_plugin = 'calibre.gui2.store.eharlequin_plugin:EHarlequinStore' + actual_plugin = 'calibre.gui2.store.stores.eharlequin_plugin:EHarlequinStore' headquarters = 'CA' formats = ['EPUB', 'PDF'] @@ -1272,7 +1272,7 @@ class StoreEHarlequinStore(StoreBase): class StoreEpubBudStore(StoreBase): name = 'ePub Bud' description = 'Well, it\'s pretty much just "YouTube for Children\'s eBooks. A not-for-profit organization devoted to brining self published childrens books to the world.' - actual_plugin = 'calibre.gui2.store.epubbud_plugin:EpubBudStore' + actual_plugin = 'calibre.gui2.store.stores.epubbud_plugin:EpubBudStore' drm_free_only = True headquarters = 'US' @@ -1281,7 +1281,7 @@ class StoreEpubBudStore(StoreBase): class StoreFeedbooksStore(StoreBase): name = 'Feedbooks' description = u'Feedbooks is a cloud publishing and distribution service, connected to a large ecosystem of reading systems and social networks. Provides a variety of genres from independent and classic books.' - actual_plugin = 'calibre.gui2.store.feedbooks_plugin:FeedbooksStore' + actual_plugin = 'calibre.gui2.store.stores.feedbooks_plugin:FeedbooksStore' headquarters = 'FR' formats = ['EPUB', 'MOBI', 'PDF'] @@ -1290,7 +1290,7 @@ class StoreFoylesUKStore(StoreBase): name = 'Foyles UK' author = 'Charles Haley' description = u'Foyles of London\'s ebook store. Provides extensive range covering all subjects.' - actual_plugin = 'calibre.gui2.store.foyles_uk_plugin:FoylesUKStore' + actual_plugin = 'calibre.gui2.store.stores.foyles_uk_plugin:FoylesUKStore' headquarters = 'UK' formats = ['EPUB', 'PDF'] @@ -1300,7 +1300,7 @@ class StoreGandalfStore(StoreBase): name = 'Gandalf' author = u'Tomasz Długosz' description = u'Księgarnia internetowa Gandalf.' - actual_plugin = 'calibre.gui2.store.gandalf_plugin:GandalfStore' + actual_plugin = 'calibre.gui2.store.stores.gandalf_plugin:GandalfStore' headquarters = 'PL' formats = ['EPUB', 'PDF'] @@ -1308,7 +1308,7 @@ class StoreGandalfStore(StoreBase): class StoreGoogleBooksStore(StoreBase): name = 'Google Books' description = u'Google Books' - actual_plugin = 'calibre.gui2.store.google_books_plugin:GoogleBooksStore' + actual_plugin = 'calibre.gui2.store.stores.google_books_plugin:GoogleBooksStore' headquarters = 'US' formats = ['EPUB', 'PDF', 'TXT'] @@ -1316,7 +1316,7 @@ class StoreGoogleBooksStore(StoreBase): class StoreGutenbergStore(StoreBase): name = 'Project Gutenberg' description = u'The first producer of free ebooks. Free in the United States because their copyright has expired. They may not be free of copyright in other countries. Readers outside of the United States must check the copyright laws of their countries before downloading or redistributing our ebooks.' - actual_plugin = 'calibre.gui2.store.gutenberg_plugin:GutenbergStore' + actual_plugin = 'calibre.gui2.store.stores.gutenberg_plugin:GutenbergStore' drm_free_only = True headquarters = 'US' @@ -1325,7 +1325,7 @@ class StoreGutenbergStore(StoreBase): class StoreKoboStore(StoreBase): name = 'Kobo' description = u'With over 2.3 million eBooks to browse we have engaged readers in over 200 countries in Kobo eReading. Our eBook listings include New York Times Bestsellers, award winners, classics and more!' - actual_plugin = 'calibre.gui2.store.kobo_plugin:KoboStore' + actual_plugin = 'calibre.gui2.store.stores.kobo_plugin:KoboStore' headquarters = 'CA' formats = ['EPUB'] @@ -1335,7 +1335,7 @@ class StoreLegimiStore(StoreBase): name = 'Legimi' author = u'Tomasz Długosz' description = u'Tanie oraz darmowe ebooki, egazety i blogi w formacie EPUB, wprost na Twój e-czytnik, iPhone, iPad, Android i komputer' - actual_plugin = 'calibre.gui2.store.legimi_plugin:LegimiStore' + actual_plugin = 'calibre.gui2.store.stores.legimi_plugin:LegimiStore' headquarters = 'PL' formats = ['EPUB'] @@ -1344,7 +1344,7 @@ class StoreLibreDEStore(StoreBase): name = 'Libri DE' author = 'Charles Haley' description = u'Sicher Bücher, Hörbücher und Downloads online bestellen.' - actual_plugin = 'calibre.gui2.store.libri_de_plugin:LibreDEStore' + actual_plugin = 'calibre.gui2.store.stores.libri_de_plugin:LibreDEStore' headquarters = 'DE' formats = ['EPUB', 'PDF'] @@ -1353,7 +1353,7 @@ class StoreLibreDEStore(StoreBase): class StoreManyBooksStore(StoreBase): name = 'ManyBooks' description = u'Public domain and creative commons works from many sources.' - actual_plugin = 'calibre.gui2.store.manybooks_plugin:ManyBooksStore' + actual_plugin = 'calibre.gui2.store.stores.manybooks_plugin:ManyBooksStore' drm_free_only = True headquarters = 'US' @@ -1362,7 +1362,7 @@ class StoreManyBooksStore(StoreBase): class StoreMobileReadStore(StoreBase): name = 'MobileRead' description = u'Ebooks handcrafted with the utmost care.' - actual_plugin = 'calibre.gui2.store.mobileread.mobileread_plugin:MobileReadStore' + actual_plugin = 'calibre.gui2.store.stores.mobileread.mobileread_plugin:MobileReadStore' drm_free_only = True headquarters = 'CH' @@ -1372,7 +1372,7 @@ class StoreNextoStore(StoreBase): name = 'Nexto' author = u'Tomasz Długosz' description = u'Największy w Polsce sklep internetowy z audiobookami mp3, ebookami pdf oraz prasą do pobrania on-line.' - actual_plugin = 'calibre.gui2.store.nexto_plugin:NextoStore' + actual_plugin = 'calibre.gui2.store.stores.nexto_plugin:NextoStore' headquarters = 'PL' formats = ['EPUB', 'PDF'] @@ -1381,7 +1381,7 @@ class StoreNextoStore(StoreBase): class StoreOpenBooksStore(StoreBase): name = 'Open Books' description = u'Comprehensive listing of DRM free ebooks from a variety of sources provided by users of calibre.' - actual_plugin = 'calibre.gui2.store.open_books_plugin:OpenBooksStore' + actual_plugin = 'calibre.gui2.store.stores.open_books_plugin:OpenBooksStore' drm_free_only = True headquarters = 'US' @@ -1389,7 +1389,7 @@ class StoreOpenBooksStore(StoreBase): class StoreOpenLibraryStore(StoreBase): name = 'Open Library' description = u'One web page for every book ever published. The goal is to be a true online library. Over 20 million records from a variety of large catalogs as well as single contributions, with more on the way.' - actual_plugin = 'calibre.gui2.store.open_library_plugin:OpenLibraryStore' + actual_plugin = 'calibre.gui2.store.stores.open_library_plugin:OpenLibraryStore' drm_free_only = True headquarters = 'US' @@ -1398,7 +1398,7 @@ class StoreOpenLibraryStore(StoreBase): class StoreOReillyStore(StoreBase): name = 'OReilly' description = u'Programming and tech ebooks from OReilly.' - actual_plugin = 'calibre.gui2.store.oreilly_plugin:OReillyStore' + actual_plugin = 'calibre.gui2.store.stores.oreilly_plugin:OReillyStore' drm_free_only = True headquarters = 'US' @@ -1407,7 +1407,7 @@ class StoreOReillyStore(StoreBase): class StorePragmaticBookshelfStore(StoreBase): name = 'Pragmatic Bookshelf' description = u'The Pragmatic Bookshelf\'s collection of programming and tech books avaliable as ebooks.' - actual_plugin = 'calibre.gui2.store.pragmatic_bookshelf_plugin:PragmaticBookshelfStore' + actual_plugin = 'calibre.gui2.store.stores.pragmatic_bookshelf_plugin:PragmaticBookshelfStore' drm_free_only = True headquarters = 'US' @@ -1416,7 +1416,7 @@ class StorePragmaticBookshelfStore(StoreBase): class StoreSmashwordsStore(StoreBase): name = 'Smashwords' description = u'An ebook publishing and distribution platform for ebook authors, publishers and readers. Covers many genres and formats.' - actual_plugin = 'calibre.gui2.store.smashwords_plugin:SmashwordsStore' + actual_plugin = 'calibre.gui2.store.stores.smashwords_plugin:SmashwordsStore' drm_free_only = True headquarters = 'US' @@ -1427,7 +1427,7 @@ class StoreVirtualoStore(StoreBase): name = 'Virtualo' author = u'Tomasz Długosz' description = u'Księgarnia internetowa, która oferuje bezpieczny i szeroki dostęp do książek w formie cyfrowej.' - actual_plugin = 'calibre.gui2.store.virtualo_plugin:VirtualoStore' + actual_plugin = 'calibre.gui2.store.stores.virtualo_plugin:VirtualoStore' headquarters = 'PL' formats = ['EPUB', 'PDF'] @@ -1436,7 +1436,7 @@ class StoreWaterstonesUKStore(StoreBase): name = 'Waterstones UK' author = 'Charles Haley' description = u'Waterstone\'s mission is to be the leading Bookseller on the High Street and online providing customers the widest choice, great value and expert advice from a team passionate about Bookselling.' - actual_plugin = 'calibre.gui2.store.waterstones_uk_plugin:WaterstonesUKStore' + actual_plugin = 'calibre.gui2.store.stores.waterstones_uk_plugin:WaterstonesUKStore' headquarters = 'UK' formats = ['EPUB', 'PDF'] @@ -1444,7 +1444,7 @@ class StoreWaterstonesUKStore(StoreBase): class StoreWeightlessBooksStore(StoreBase): name = 'Weightless Books' description = u'An independent DRM-free ebooksite devoted to ebooks of all sorts.' - actual_plugin = 'calibre.gui2.store.weightless_books_plugin:WeightlessBooksStore' + actual_plugin = 'calibre.gui2.store.stores.weightless_books_plugin:WeightlessBooksStore' drm_free_only = True headquarters = 'US' @@ -1454,7 +1454,7 @@ class StoreWHSmithUKStore(StoreBase): name = 'WH Smith UK' author = 'Charles Haley' description = u"Shop for savings on Books, discounted Magazine subscriptions and great prices on Stationery, Toys & Games" - actual_plugin = 'calibre.gui2.store.whsmith_uk_plugin:WHSmithUKStore' + actual_plugin = 'calibre.gui2.store.stores.whsmith_uk_plugin:WHSmithUKStore' headquarters = 'UK' formats = ['EPUB', 'PDF'] @@ -1462,7 +1462,7 @@ class StoreWHSmithUKStore(StoreBase): class StoreWizardsTowerBooksStore(StoreBase): name = 'Wizards Tower Books' description = u'A science fiction and fantasy publisher. Concentrates mainly on making out-of-print works available once more as e-books, and helping other small presses exploit the e-book market. Also publishes a small number of limited-print-run anthologies with a view to encouraging diversity in the science fiction and fantasy field.' - actual_plugin = 'calibre.gui2.store.wizards_tower_books_plugin:WizardsTowerBooksStore' + actual_plugin = 'calibre.gui2.store.stores.wizards_tower_books_plugin:WizardsTowerBooksStore' drm_free_only = True headquarters = 'UK' @@ -1472,7 +1472,7 @@ class StoreWoblinkStore(StoreBase): name = 'Woblink' author = u'Tomasz Długosz' description = u'Czytanie zdarza się wszędzie!' - actual_plugin = 'calibre.gui2.store.woblink_plugin:WoblinkStore' + actual_plugin = 'calibre.gui2.store.stores.woblink_plugin:WoblinkStore' headquarters = 'PL' formats = ['EPUB'] @@ -1481,7 +1481,7 @@ class StoreZixoStore(StoreBase): name = 'Zixo' author = u'Tomasz Długosz' description = u'Księgarnia z ebookami oraz książkami audio. Aby otwierać książki w formacie Zixo należy zainstalować program dostępny na stronie księgarni. Umożliwia on m.in. dodawanie zakładek i dostosowywanie rozmiaru czcionki.' - actual_plugin = 'calibre.gui2.store.zixo_plugin:ZixoStore' + actual_plugin = 'calibre.gui2.store.stores.zixo_plugin:ZixoStore' headquarters = 'PL' formats = ['PDF, ZIXO'] diff --git a/src/calibre/gui2/store/stores/__init__.py b/src/calibre/gui2/store/stores/__init__.py new file mode 100644 index 0000000000..db25b54b67 --- /dev/null +++ b/src/calibre/gui2/store/stores/__init__.py @@ -0,0 +1,3 @@ +''' +All store plugins are placed here. +''' \ No newline at end of file diff --git a/src/calibre/gui2/store/amazon_de_plugin.py b/src/calibre/gui2/store/stores/amazon_de_plugin.py similarity index 100% rename from src/calibre/gui2/store/amazon_de_plugin.py rename to src/calibre/gui2/store/stores/amazon_de_plugin.py diff --git a/src/calibre/gui2/store/amazon_plugin.py b/src/calibre/gui2/store/stores/amazon_plugin.py similarity index 100% rename from src/calibre/gui2/store/amazon_plugin.py rename to src/calibre/gui2/store/stores/amazon_plugin.py diff --git a/src/calibre/gui2/store/amazon_uk_plugin.py b/src/calibre/gui2/store/stores/amazon_uk_plugin.py similarity index 100% rename from src/calibre/gui2/store/amazon_uk_plugin.py rename to src/calibre/gui2/store/stores/amazon_uk_plugin.py diff --git a/src/calibre/gui2/store/archive_org_plugin.py b/src/calibre/gui2/store/stores/archive_org_plugin.py similarity index 100% rename from src/calibre/gui2/store/archive_org_plugin.py rename to src/calibre/gui2/store/stores/archive_org_plugin.py diff --git a/src/calibre/gui2/store/baen_webscription_plugin.py b/src/calibre/gui2/store/stores/baen_webscription_plugin.py similarity index 100% rename from src/calibre/gui2/store/baen_webscription_plugin.py rename to src/calibre/gui2/store/stores/baen_webscription_plugin.py diff --git a/src/calibre/gui2/store/beam_ebooks_de_plugin.py b/src/calibre/gui2/store/stores/beam_ebooks_de_plugin.py similarity index 100% rename from src/calibre/gui2/store/beam_ebooks_de_plugin.py rename to src/calibre/gui2/store/stores/beam_ebooks_de_plugin.py diff --git a/src/calibre/gui2/store/bewrite_plugin.py b/src/calibre/gui2/store/stores/bewrite_plugin.py similarity index 100% rename from src/calibre/gui2/store/bewrite_plugin.py rename to src/calibre/gui2/store/stores/bewrite_plugin.py diff --git a/src/calibre/gui2/store/bn_plugin.py b/src/calibre/gui2/store/stores/bn_plugin.py similarity index 100% rename from src/calibre/gui2/store/bn_plugin.py rename to src/calibre/gui2/store/stores/bn_plugin.py diff --git a/src/calibre/gui2/store/diesel_ebooks_plugin.py b/src/calibre/gui2/store/stores/diesel_ebooks_plugin.py similarity index 100% rename from src/calibre/gui2/store/diesel_ebooks_plugin.py rename to src/calibre/gui2/store/stores/diesel_ebooks_plugin.py diff --git a/src/calibre/gui2/store/ebooks_com_plugin.py b/src/calibre/gui2/store/stores/ebooks_com_plugin.py similarity index 100% rename from src/calibre/gui2/store/ebooks_com_plugin.py rename to src/calibre/gui2/store/stores/ebooks_com_plugin.py diff --git a/src/calibre/gui2/store/ebookshoppe_uk_plugin.py b/src/calibre/gui2/store/stores/ebookshoppe_uk_plugin.py similarity index 100% rename from src/calibre/gui2/store/ebookshoppe_uk_plugin.py rename to src/calibre/gui2/store/stores/ebookshoppe_uk_plugin.py diff --git a/src/calibre/gui2/store/eharlequin_plugin.py b/src/calibre/gui2/store/stores/eharlequin_plugin.py similarity index 100% rename from src/calibre/gui2/store/eharlequin_plugin.py rename to src/calibre/gui2/store/stores/eharlequin_plugin.py diff --git a/src/calibre/gui2/store/epubbud_plugin.py b/src/calibre/gui2/store/stores/epubbud_plugin.py similarity index 100% rename from src/calibre/gui2/store/epubbud_plugin.py rename to src/calibre/gui2/store/stores/epubbud_plugin.py diff --git a/src/calibre/gui2/store/epubbuy_de_plugin.py b/src/calibre/gui2/store/stores/epubbuy_de_plugin.py similarity index 100% rename from src/calibre/gui2/store/epubbuy_de_plugin.py rename to src/calibre/gui2/store/stores/epubbuy_de_plugin.py diff --git a/src/calibre/gui2/store/feedbooks_plugin.py b/src/calibre/gui2/store/stores/feedbooks_plugin.py similarity index 100% rename from src/calibre/gui2/store/feedbooks_plugin.py rename to src/calibre/gui2/store/stores/feedbooks_plugin.py diff --git a/src/calibre/gui2/store/foyles_uk_plugin.py b/src/calibre/gui2/store/stores/foyles_uk_plugin.py similarity index 100% rename from src/calibre/gui2/store/foyles_uk_plugin.py rename to src/calibre/gui2/store/stores/foyles_uk_plugin.py diff --git a/src/calibre/gui2/store/gandalf_plugin.py b/src/calibre/gui2/store/stores/gandalf_plugin.py similarity index 100% rename from src/calibre/gui2/store/gandalf_plugin.py rename to src/calibre/gui2/store/stores/gandalf_plugin.py diff --git a/src/calibre/gui2/store/google_books_plugin.py b/src/calibre/gui2/store/stores/google_books_plugin.py similarity index 100% rename from src/calibre/gui2/store/google_books_plugin.py rename to src/calibre/gui2/store/stores/google_books_plugin.py diff --git a/src/calibre/gui2/store/gutenberg_plugin.py b/src/calibre/gui2/store/stores/gutenberg_plugin.py similarity index 100% rename from src/calibre/gui2/store/gutenberg_plugin.py rename to src/calibre/gui2/store/stores/gutenberg_plugin.py diff --git a/src/calibre/gui2/store/kobo_plugin.py b/src/calibre/gui2/store/stores/kobo_plugin.py similarity index 100% rename from src/calibre/gui2/store/kobo_plugin.py rename to src/calibre/gui2/store/stores/kobo_plugin.py diff --git a/src/calibre/gui2/store/legimi_plugin.py b/src/calibre/gui2/store/stores/legimi_plugin.py similarity index 100% rename from src/calibre/gui2/store/legimi_plugin.py rename to src/calibre/gui2/store/stores/legimi_plugin.py diff --git a/src/calibre/gui2/store/libri_de_plugin.py b/src/calibre/gui2/store/stores/libri_de_plugin.py similarity index 100% rename from src/calibre/gui2/store/libri_de_plugin.py rename to src/calibre/gui2/store/stores/libri_de_plugin.py diff --git a/src/calibre/gui2/store/manybooks_plugin.py b/src/calibre/gui2/store/stores/manybooks_plugin.py similarity index 100% rename from src/calibre/gui2/store/manybooks_plugin.py rename to src/calibre/gui2/store/stores/manybooks_plugin.py diff --git a/src/calibre/gui2/store/mobileread/__init__.py b/src/calibre/gui2/store/stores/mobileread/__init__.py similarity index 100% rename from src/calibre/gui2/store/mobileread/__init__.py rename to src/calibre/gui2/store/stores/mobileread/__init__.py diff --git a/src/calibre/gui2/store/mobileread/adv_search_builder.py b/src/calibre/gui2/store/stores/mobileread/adv_search_builder.py similarity index 97% rename from src/calibre/gui2/store/mobileread/adv_search_builder.py rename to src/calibre/gui2/store/stores/mobileread/adv_search_builder.py index 8c41f1924b..8bc7850b0f 100644 --- a/src/calibre/gui2/store/mobileread/adv_search_builder.py +++ b/src/calibre/gui2/store/stores/mobileread/adv_search_builder.py @@ -10,7 +10,7 @@ import re from PyQt4.Qt import (QDialog, QDialogButtonBox) -from calibre.gui2.store.mobileread.adv_search_builder_ui import Ui_Dialog +from calibre.gui2.store.stores.mobileread.adv_search_builder_ui import Ui_Dialog from calibre.library.caches import CONTAINS_MATCH, EQUALS_MATCH class AdvSearchBuilderDialog(QDialog, Ui_Dialog): diff --git a/src/calibre/gui2/store/mobileread/adv_search_builder.ui b/src/calibre/gui2/store/stores/mobileread/adv_search_builder.ui similarity index 100% rename from src/calibre/gui2/store/mobileread/adv_search_builder.ui rename to src/calibre/gui2/store/stores/mobileread/adv_search_builder.ui diff --git a/src/calibre/gui2/store/mobileread/cache_progress_dialog.py b/src/calibre/gui2/store/stores/mobileread/cache_progress_dialog.py similarity index 94% rename from src/calibre/gui2/store/mobileread/cache_progress_dialog.py rename to src/calibre/gui2/store/stores/mobileread/cache_progress_dialog.py index 71416d8680..de2cf50f84 100644 --- a/src/calibre/gui2/store/mobileread/cache_progress_dialog.py +++ b/src/calibre/gui2/store/stores/mobileread/cache_progress_dialog.py @@ -8,7 +8,7 @@ __docformat__ = 'restructuredtext en' from PyQt4.Qt import QDialog -from calibre.gui2.store.mobileread.cache_progress_dialog_ui import Ui_Dialog +from calibre.gui2.store.stores.mobileread.cache_progress_dialog_ui import Ui_Dialog class CacheProgressDialog(QDialog, Ui_Dialog): diff --git a/src/calibre/gui2/store/mobileread/cache_progress_dialog.ui b/src/calibre/gui2/store/stores/mobileread/cache_progress_dialog.ui similarity index 100% rename from src/calibre/gui2/store/mobileread/cache_progress_dialog.ui rename to src/calibre/gui2/store/stores/mobileread/cache_progress_dialog.ui diff --git a/src/calibre/gui2/store/mobileread/cache_update_thread.py b/src/calibre/gui2/store/stores/mobileread/cache_update_thread.py similarity index 100% rename from src/calibre/gui2/store/mobileread/cache_update_thread.py rename to src/calibre/gui2/store/stores/mobileread/cache_update_thread.py diff --git a/src/calibre/gui2/store/mobileread/mobileread_plugin.py b/src/calibre/gui2/store/stores/mobileread/mobileread_plugin.py similarity index 91% rename from src/calibre/gui2/store/mobileread/mobileread_plugin.py rename to src/calibre/gui2/store/stores/mobileread/mobileread_plugin.py index 4e11d62bbd..3ffb5c36a1 100644 --- a/src/calibre/gui2/store/mobileread/mobileread_plugin.py +++ b/src/calibre/gui2/store/stores/mobileread/mobileread_plugin.py @@ -15,10 +15,10 @@ from calibre.gui2.store import StorePlugin from calibre.gui2.store.basic_config import BasicStoreConfig from calibre.gui2.store.search_result import SearchResult from calibre.gui2.store.web_store_dialog import WebStoreDialog -from calibre.gui2.store.mobileread.models import SearchFilter -from calibre.gui2.store.mobileread.cache_progress_dialog import CacheProgressDialog -from calibre.gui2.store.mobileread.cache_update_thread import CacheUpdateThread -from calibre.gui2.store.mobileread.store_dialog import MobileReadStoreDialog +from calibre.gui2.store.stores.mobileread.models import SearchFilter +from calibre.gui2.store.stores.mobileread.cache_progress_dialog import CacheProgressDialog +from calibre.gui2.store.stores.mobileread.cache_update_thread import CacheUpdateThread +from calibre.gui2.store.stores.mobileread.store_dialog import MobileReadStoreDialog class MobileReadStore(BasicStoreConfig, StorePlugin): diff --git a/src/calibre/gui2/store/mobileread/models.py b/src/calibre/gui2/store/stores/mobileread/models.py similarity index 100% rename from src/calibre/gui2/store/mobileread/models.py rename to src/calibre/gui2/store/stores/mobileread/models.py diff --git a/src/calibre/gui2/store/mobileread/store_dialog.py b/src/calibre/gui2/store/stores/mobileread/store_dialog.py similarity index 93% rename from src/calibre/gui2/store/mobileread/store_dialog.py rename to src/calibre/gui2/store/stores/mobileread/store_dialog.py index 749f96a614..ff7fea090f 100644 --- a/src/calibre/gui2/store/mobileread/store_dialog.py +++ b/src/calibre/gui2/store/stores/mobileread/store_dialog.py @@ -9,9 +9,9 @@ __docformat__ = 'restructuredtext en' from PyQt4.Qt import (Qt, QDialog, QIcon, QComboBox) -from calibre.gui2.store.mobileread.adv_search_builder import AdvSearchBuilderDialog -from calibre.gui2.store.mobileread.models import BooksModel -from calibre.gui2.store.mobileread.store_dialog_ui import Ui_Dialog +from calibre.gui2.store.stores.mobileread.adv_search_builder import AdvSearchBuilderDialog +from calibre.gui2.store.stores.mobileread.models import BooksModel +from calibre.gui2.store.stores.mobileread.store_dialog_ui import Ui_Dialog class MobileReadStoreDialog(QDialog, Ui_Dialog): diff --git a/src/calibre/gui2/store/mobileread/store_dialog.ui b/src/calibre/gui2/store/stores/mobileread/store_dialog.ui similarity index 100% rename from src/calibre/gui2/store/mobileread/store_dialog.ui rename to src/calibre/gui2/store/stores/mobileread/store_dialog.ui diff --git a/src/calibre/gui2/store/nexto_plugin.py b/src/calibre/gui2/store/stores/nexto_plugin.py similarity index 100% rename from src/calibre/gui2/store/nexto_plugin.py rename to src/calibre/gui2/store/stores/nexto_plugin.py diff --git a/src/calibre/gui2/store/open_books_plugin.py b/src/calibre/gui2/store/stores/open_books_plugin.py similarity index 100% rename from src/calibre/gui2/store/open_books_plugin.py rename to src/calibre/gui2/store/stores/open_books_plugin.py diff --git a/src/calibre/gui2/store/open_library_plugin.py b/src/calibre/gui2/store/stores/open_library_plugin.py similarity index 100% rename from src/calibre/gui2/store/open_library_plugin.py rename to src/calibre/gui2/store/stores/open_library_plugin.py diff --git a/src/calibre/gui2/store/oreilly_plugin.py b/src/calibre/gui2/store/stores/oreilly_plugin.py similarity index 100% rename from src/calibre/gui2/store/oreilly_plugin.py rename to src/calibre/gui2/store/stores/oreilly_plugin.py diff --git a/src/calibre/gui2/store/pragmatic_bookshelf_plugin.py b/src/calibre/gui2/store/stores/pragmatic_bookshelf_plugin.py similarity index 100% rename from src/calibre/gui2/store/pragmatic_bookshelf_plugin.py rename to src/calibre/gui2/store/stores/pragmatic_bookshelf_plugin.py diff --git a/src/calibre/gui2/store/smashwords_plugin.py b/src/calibre/gui2/store/stores/smashwords_plugin.py similarity index 100% rename from src/calibre/gui2/store/smashwords_plugin.py rename to src/calibre/gui2/store/stores/smashwords_plugin.py diff --git a/src/calibre/gui2/store/virtualo_plugin.py b/src/calibre/gui2/store/stores/virtualo_plugin.py similarity index 100% rename from src/calibre/gui2/store/virtualo_plugin.py rename to src/calibre/gui2/store/stores/virtualo_plugin.py diff --git a/src/calibre/gui2/store/waterstones_uk_plugin.py b/src/calibre/gui2/store/stores/waterstones_uk_plugin.py similarity index 100% rename from src/calibre/gui2/store/waterstones_uk_plugin.py rename to src/calibre/gui2/store/stores/waterstones_uk_plugin.py diff --git a/src/calibre/gui2/store/weightless_books_plugin.py b/src/calibre/gui2/store/stores/weightless_books_plugin.py similarity index 100% rename from src/calibre/gui2/store/weightless_books_plugin.py rename to src/calibre/gui2/store/stores/weightless_books_plugin.py diff --git a/src/calibre/gui2/store/whsmith_uk_plugin.py b/src/calibre/gui2/store/stores/whsmith_uk_plugin.py similarity index 100% rename from src/calibre/gui2/store/whsmith_uk_plugin.py rename to src/calibre/gui2/store/stores/whsmith_uk_plugin.py diff --git a/src/calibre/gui2/store/wizards_tower_books_plugin.py b/src/calibre/gui2/store/stores/wizards_tower_books_plugin.py similarity index 100% rename from src/calibre/gui2/store/wizards_tower_books_plugin.py rename to src/calibre/gui2/store/stores/wizards_tower_books_plugin.py diff --git a/src/calibre/gui2/store/woblink_plugin.py b/src/calibre/gui2/store/stores/woblink_plugin.py similarity index 100% rename from src/calibre/gui2/store/woblink_plugin.py rename to src/calibre/gui2/store/stores/woblink_plugin.py diff --git a/src/calibre/gui2/store/zixo_plugin.py b/src/calibre/gui2/store/stores/zixo_plugin.py similarity index 100% rename from src/calibre/gui2/store/zixo_plugin.py rename to src/calibre/gui2/store/stores/zixo_plugin.py From 9540ad9528e0dc9e1a18d2ed99eb53af65ac7a1a Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 26 Jun 2011 09:40:00 -0600 Subject: [PATCH 06/22] Try to get Qt to use the calibre config dir as well --- src/calibre/gui2/__init__.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/src/calibre/gui2/__init__.py b/src/calibre/gui2/__init__.py index 0b21502327..8dbc72ab98 100644 --- a/src/calibre/gui2/__init__.py +++ b/src/calibre/gui2/__init__.py @@ -7,12 +7,13 @@ from urllib import unquote from PyQt4.Qt import (QVariant, QFileInfo, QObject, SIGNAL, QBuffer, Qt, QByteArray, QTranslator, QCoreApplication, QThread, QEvent, QTimer, pyqtSignal, QDate, QDesktopServices, - QFileDialog, QFileIconProvider, + QFileDialog, QFileIconProvider, QSettings, QIcon, QApplication, QDialog, QUrl, QFont) ORG_NAME = 'KovidsBrain' APP_UID = 'libprs500' -from calibre.constants import islinux, iswindows, isbsd, isfrozen, isosx +from calibre.constants import (islinux, iswindows, isbsd, isfrozen, isosx, + config_dir) from calibre.utils.config import Config, ConfigProxy, dynamic, JSONConfig from calibre.utils.localization import set_qt_translator from calibre.ebooks.metadata import MetaInformation @@ -192,6 +193,11 @@ def _config(): # {{{ config = _config() # }}} +QSettings.setPath(QSettings.IniFormat, QSettings.UserScope, config_dir) +QSettings.setPath(QSettings.IniFormat, QSettings.SystemScope, + config_dir) +QSettings.setDefaultFormat(QSettings.IniFormat) + # Turn off DeprecationWarnings in windows GUI if iswindows: import warnings From 3c83b7873a108764bf78a8d04d5d9bbe8755d2a1 Mon Sep 17 00:00:00 2001 From: John Schember Date: Sun, 26 Jun 2011 12:29:58 -0400 Subject: [PATCH 07/22] Store: Allow for direct downloading of ebooks in the Get Books search dialog. Allow the user to right click and choose between downloading or opening in the store. --- src/calibre/gui2/store/opensearch_store.py | 14 ++++---- .../gui2/store/search/adv_search_builder.py | 4 +++ .../gui2/store/search/adv_search_builder.ui | 34 ++++++++++++++++--- src/calibre/gui2/store/search/models.py | 25 +++++++++++--- src/calibre/gui2/store/search/results_view.py | 22 +++++++++++- src/calibre/gui2/store/search/search.py | 28 ++++++++++++--- src/calibre/gui2/store/search_result.py | 4 ++- .../gui2/store/stores/epubbud_plugin.py | 2 ++ 8 files changed, 112 insertions(+), 21 deletions(-) diff --git a/src/calibre/gui2/store/opensearch_store.py b/src/calibre/gui2/store/opensearch_store.py index a3dc0e7941..8a25a80132 100644 --- a/src/calibre/gui2/store/opensearch_store.py +++ b/src/calibre/gui2/store/opensearch_store.py @@ -59,14 +59,14 @@ class OpenSearchStore(StorePlugin): elif l['rel'] == u'http://opds-spec.org/acquisition/buy': s.detail_item = l.get('href', s.detail_item) elif l['rel'] == u'http://opds-spec.org/acquisition': - s.downloads.append((l.get('type', ''), l.get('href', ''))) + mime = l.get('type', '') + if mime: + ext = mimetypes.guess_extension(mime) + if ext: + ext = ext[1:].upper() + s.downloads[ext] = l.get('href', '') - formats = [] - for mime, url in s.downloads: - ext = mimetypes.guess_extension(mime) - if ext: - formats.append(ext[1:]) - s.formats = ', '.join(formats) + s.formats = ', '.join(s.downloads.keys()) s.title = r.get('title', '') s.author = r.get('author', '') diff --git a/src/calibre/gui2/store/search/adv_search_builder.py b/src/calibre/gui2/store/search/adv_search_builder.py index cc89ca4eb7..127ac27acb 100644 --- a/src/calibre/gui2/store/search/adv_search_builder.py +++ b/src/calibre/gui2/store/search/adv_search_builder.py @@ -45,6 +45,7 @@ class AdvSearchBuilderDialog(QDialog, Ui_Dialog): self.author_box.setText('') self.price_box.setText('') self.format_box.setText('') + self.download_combo.setCurrentIndex(0) self.affiliate_combo.setCurrentIndex(0) def tokens(self, raw): @@ -119,6 +120,9 @@ class AdvSearchBuilderDialog(QDialog, Ui_Dialog): format = unicode(self.format_box.text()).strip() if format: ans.append('format:"' + self.mc + format + '"') + download = unicode(self.download_combo.currentText()).strip() + if download: + ans.append('download:' + download) affiliate = unicode(self.affiliate_combo.currentText()).strip() if affiliate: ans.append('affiliate:' + affiliate) diff --git a/src/calibre/gui2/store/search/adv_search_builder.ui b/src/calibre/gui2/store/search/adv_search_builder.ui index ab12dbbc00..02eb8f6aa1 100644 --- a/src/calibre/gui2/store/search/adv_search_builder.ui +++ b/src/calibre/gui2/store/search/adv_search_builder.ui @@ -226,7 +226,7 @@ - + @@ -244,7 +244,7 @@ - + Qt::Vertical @@ -283,14 +283,14 @@ - + Affiliate: - + @@ -309,6 +309,32 @@ + + + + Download: + + + + + + + + + + + + + true + + + + + false + + + + diff --git a/src/calibre/gui2/store/search/models.py b/src/calibre/gui2/store/search/models.py index e2c1a03e90..1fb0e5327b 100644 --- a/src/calibre/gui2/store/search/models.py +++ b/src/calibre/gui2/store/search/models.py @@ -33,7 +33,7 @@ class Matches(QAbstractItemModel): total_changed = pyqtSignal(int) - HEADERS = [_('Cover'), _('Title'), _('Price'), _('DRM'), _('Store'), ''] + HEADERS = [_('Cover'), _('Title'), _('Price'), _('DRM'), _('Store'), _('Download'), _('Affiliate')] HTML_COLS = (1, 4) def __init__(self, cover_thread_count=2, detail_thread_count=4): @@ -47,6 +47,8 @@ class Matches(QAbstractItemModel): Qt.SmoothTransformation) self.DONATE_ICON = QPixmap(I('donate.png')).scaledToHeight(16, Qt.SmoothTransformation) + self.DOWNLOAD_ICON = QPixmap(I('arrow-down.png')).scaledToHeight(16, + Qt.SmoothTransformation) # All matches. Used to determine the order to display # self.matches because the SearchFilter returns @@ -181,9 +183,11 @@ class Matches(QAbstractItemModel): elif result.drm == SearchResult.DRM_UNKNOWN: return QVariant(self.DRM_UNKNOWN_ICON) if col == 5: + if result.downloads: + return QVariant(self.DOWNLOAD_ICON) + if col == 6: if result.affiliate: return QVariant(self.DONATE_ICON) - return NONE elif role == Qt.ToolTipRole: if col == 1: return QVariant('

%s

' % result.title) @@ -199,6 +203,9 @@ class Matches(QAbstractItemModel): elif col == 4: return QVariant('

%s

' % result.formats) elif col == 5: + if result.downloads: + return QVariant('

' + _('The following formats can be downloaded directly: %s.') % ', '.join(result.downloads.keys()) + '

') + elif col == 6: if result.affiliate: return QVariant('

' + _('Buying from this store supports the calibre developer: %s.') % result.plugin_author + '

') elif role == Qt.SizeHintRole: @@ -221,6 +228,11 @@ class Matches(QAbstractItemModel): elif col == 4: text = result.store_name elif col == 5: + if result.downloads: + text = 'a' + else: + text = 'b' + elif col == 6: if result.affiliate: text = 'a' else: @@ -257,6 +269,8 @@ class SearchFilter(SearchQueryParser): 'author', 'authors', 'cover', + 'download', + 'downloads', 'drm', 'format', 'formats', @@ -282,6 +296,8 @@ class SearchFilter(SearchQueryParser): location = location.lower().strip() if location == 'authors': location = 'author' + elif location == 'downloads': + location = 'download' elif location == 'formats': location = 'format' @@ -308,12 +324,13 @@ class SearchFilter(SearchQueryParser): 'author': lambda x: x.author.lower(), 'cover': attrgetter('cover_url'), 'drm': attrgetter('drm'), + 'download': attrgetter('downloads'), 'format': attrgetter('formats'), 'price': lambda x: comparable_price(x.price), 'store': lambda x: x.store_name.lower(), 'title': lambda x: x.title.lower(), } - for x in ('author', 'format'): + for x in ('author', 'download', 'format'): q[x+'s'] = q[x] for sr in self.srs: for locvalue in locations: @@ -347,7 +364,7 @@ class SearchFilter(SearchQueryParser): matches.add(sr) continue # this is bool or treated as bool, so can't match below. - if locvalue in ('affiliate', 'drm'): + if locvalue in ('affiliate', 'drm', 'download', 'downloads'): continue try: ### Can't separate authors because comma is used for name sep and author sep diff --git a/src/calibre/gui2/store/search/results_view.py b/src/calibre/gui2/store/search/results_view.py index 91c067006e..3957e18ef6 100644 --- a/src/calibre/gui2/store/search/results_view.py +++ b/src/calibre/gui2/store/search/results_view.py @@ -6,13 +6,18 @@ __license__ = 'GPL 3' __copyright__ = '2011, John Schember ' __docformat__ = 'restructuredtext en' -from PyQt4.Qt import (QTreeView) +from functools import partial + +from PyQt4.Qt import (pyqtSignal, QMenu, QTreeView) from calibre.gui2.metadata.single_download import RichTextDelegate from calibre.gui2.store.search.models import Matches class ResultsView(QTreeView): + download_requested = pyqtSignal(object) + open_requested = pyqtSignal(object) + def __init__(self, *args): QTreeView.__init__(self,*args) @@ -24,3 +29,18 @@ class ResultsView(QTreeView): for i in self._model.HTML_COLS: self.setItemDelegateForColumn(i, self.rt_delegate) + def contextMenuEvent(self, event): + index = self.indexAt(event.pos()) + + if not index.isValid(): + return + + result = self.model().get_result(index) + + menu = QMenu() + da = menu.addAction(_('Download...'), partial(self.download_requested.emit, result)) + if not result.downloads: + da.setEnabled(False) + menu.addSeparator() + menu.addAction(_('Goto in store...'), partial(self.open_requested.emit, result)) + menu.exec_(event.globalPos()) diff --git a/src/calibre/gui2/store/search/search.py b/src/calibre/gui2/store/search/search.py index 7db4d1bbaf..fd20669f09 100644 --- a/src/calibre/gui2/store/search/search.py +++ b/src/calibre/gui2/store/search/search.py @@ -14,6 +14,7 @@ from PyQt4.Qt import (Qt, QDialog, QDialogButtonBox, QTimer, QCheckBox, QLabel, QComboBox) from calibre.gui2 import JSONConfig, info_dialog +from calibre.gui2.dialogs.choose_format import ChooseFormatDialog from calibre.gui2.progress_indicator import ProgressIndicator from calibre.gui2.store.config.chooser.chooser_widget import StoreChooserWidget from calibre.gui2.store.config.search.search_widget import StoreConfigWidget @@ -72,7 +73,9 @@ class SearchDialog(QDialog, Ui_Dialog): self.search.clicked.connect(self.do_search) self.checker.timeout.connect(self.get_results) self.progress_checker.timeout.connect(self.check_progress) - self.results_view.activated.connect(self.open_store) + self.results_view.activated.connect(self.result_item_activated) + self.results_view.download_requested.connect(self.download_book) + self.results_view.open_requested.connect(self.open_store) self.results_view.model().total_changed.connect(self.update_book_total) self.select_all_stores.clicked.connect(self.stores_select_all) self.select_invert_stores.clicked.connect(self.stores_select_invert) @@ -129,11 +132,15 @@ class SearchDialog(QDialog, Ui_Dialog): # Title / Author self.results_view.setColumnWidth(1,int(total*.40)) # Price - self.results_view.setColumnWidth(2,int(total*.20)) + self.results_view.setColumnWidth(2,int(total*.12)) # DRM self.results_view.setColumnWidth(3, int(total*.15)) # Store / Formats self.results_view.setColumnWidth(4, int(total*.25)) + # Download + self.results_view.setColumnWidth(5, 20) + # Affiliate + self.results_view.setColumnWidth(6, 20) def do_search(self): # Stop all running threads. @@ -183,7 +190,7 @@ class SearchDialog(QDialog, Ui_Dialog): query = re.sub(r'%s:"(?P[^\s"]+)"' % loc, '\g', query) query = query.replace('%s:' % loc, '') # Remove the prefix and search text. - for loc in ('cover', 'drm', 'format', 'formats', 'price', 'store'): + for loc in ('cover', 'download', 'downloads', 'drm', 'format', 'formats', 'price', 'store'): query = re.sub(r'%s:"[^"]"' % loc, '', query) query = re.sub(r'%s:[^\s]*' % loc, '', query) # Remove logic. @@ -330,8 +337,21 @@ class SearchDialog(QDialog, Ui_Dialog): def update_book_total(self, total): self.total.setText('%s' % total) - def open_store(self, index): + def result_item_activated(self, index): result = self.results_view.model().get_result(index) + + if result.downloads: + self.download_book(result) + else: + self.open_store(result) + + def download_book(self, result): + d = ChooseFormatDialog(self, _('Choose format to download to your library.'), result.downloads.keys()) + if d.exec_() == d.Accepted: + ext = d.format() + self.gui.download_ebook(result.downloads[ext]) + + def open_store(self, result): self.gui.istores[result.store_name].open(self, result.detail_item, self.open_external.isChecked()) def check_progress(self): diff --git a/src/calibre/gui2/store/search_result.py b/src/calibre/gui2/store/search_result.py index bbe5b83c38..5cf71f011e 100644 --- a/src/calibre/gui2/store/search_result.py +++ b/src/calibre/gui2/store/search_result.py @@ -22,7 +22,9 @@ class SearchResult(object): self.detail_item = '' self.drm = None self.formats = '' - self.downloads = [] + # key = format in upper case. + # value = url to download the file. + self.downloads = {} self.affiliate = False self.plugin_author = '' diff --git a/src/calibre/gui2/store/stores/epubbud_plugin.py b/src/calibre/gui2/store/stores/epubbud_plugin.py index 7c581b9578..b4d642f62b 100644 --- a/src/calibre/gui2/store/stores/epubbud_plugin.py +++ b/src/calibre/gui2/store/stores/epubbud_plugin.py @@ -22,4 +22,6 @@ class EpubBudStore(BasicStoreConfig, OpenSearchStore): s.price = '$0.00' s.drm = SearchResult.DRM_UNLOCKED s.formats = 'EPUB' + # Download links are broken for this store. + s.downloads = {} yield s From 53b0b57959c1e2680a1a414f0e7a98696d85aed5 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 26 Jun 2011 13:31:47 -0600 Subject: [PATCH 08/22] Fix #802232 (Updated recipe for Financial times rss) --- recipes/financial_times.recipe | 100 +++++++++++++++++++++--------- recipes/icons/financial_times.png | Bin 0 -> 1470 bytes 2 files changed, 71 insertions(+), 29 deletions(-) create mode 100644 recipes/icons/financial_times.png diff --git a/recipes/financial_times.recipe b/recipes/financial_times.recipe index e750b6f113..91d989a778 100644 --- a/recipes/financial_times.recipe +++ b/recipes/financial_times.recipe @@ -1,32 +1,42 @@ -#!/usr/bin/env python - __license__ = 'GPL v3' -__copyright__ = '2008, Darko Miletic ' +__copyright__ = '2010-2011, Darko Miletic ' ''' -ft.com +www.ft.com ''' +import datetime +from calibre import strftime from calibre.web.feeds.news import BasicNewsRecipe -class FinancialTimes(BasicNewsRecipe): - title = u'Financial Times' - __author__ = 'Darko Miletic and Sujata Raman' - description = ('Financial world news. Available after 5AM ' - 'GMT, daily.') +class FinancialTimes_rss(BasicNewsRecipe): + title = 'Financial Times' + __author__ = 'Darko Miletic' + description = "The Financial Times (FT) is one of the world's leading business news and information organisations, recognised internationally for its authority, integrity and accuracy." + publisher = 'The Financial Times Ltd.' + category = 'news, finances, politics, World' oldest_article = 2 - language = 'en' - - max_articles_per_feed = 100 + language = 'en' + max_articles_per_feed = 250 no_stylesheets = True use_embedded_content = False needs_subscription = True - simultaneous_downloads= 1 - delay = 1 + encoding = 'utf8' + publication_type = 'newspaper' + masthead_url = 'http://im.media.ft.com/m/img/masthead_main.jpg' + LOGIN = 'https://registration.ft.com/registration/barrier/login' + INDEX = 'http://www.ft.com' - LOGIN = 'https://registration.ft.com/registration/barrier/login' + conversion_options = { + 'comment' : description + , 'tags' : category + , 'publisher' : publisher + , 'language' : language + , 'linearize_tables' : True + } def get_browser(self): br = BasicNewsRecipe.get_browser() + br.open(self.INDEX) if self.username is not None and self.password is not None: br.open(self.LOGIN) br.select_form(name='loginForm') @@ -35,31 +45,63 @@ class FinancialTimes(BasicNewsRecipe): br.submit() return br - keep_only_tags = [ dict(name='div', attrs={'id':'cont'}) ] - remove_tags_after = dict(name='p', attrs={'class':'copyright'}) + keep_only_tags = [dict(name='div', attrs={'class':['fullstory fullstoryHeader','fullstory fullstoryBody','ft-story-header','ft-story-body','index-detail']})] remove_tags = [ - dict(name='div', attrs={'id':'floating-con'}) + dict(name='div', attrs={'id':'floating-con'}) + ,dict(name=['meta','iframe','base','object','embed','link']) + ,dict(attrs={'class':['storyTools','story-package','screen-copy','story-package separator','expandable-image']}) ] + remove_attributes = ['width','height','lang'] - extra_css = ''' - body{font-family:Arial,Helvetica,sans-serif;} - h2(font-size:large;} - .ft-story-header(font-size:xx-small;} - .ft-story-body(font-size:small;} - a{color:#003399;} + extra_css = """ + body{font-family: Georgia,Times,"Times New Roman",serif} + h2{font-size:large} + .ft-story-header{font-size: x-small} .container{font-size:x-small;} h3{font-size:x-small;color:#003399;} - ''' + .copyright{font-size: x-small} + img{margin-top: 0.8em; display: block} + .lastUpdated{font-family: Arial,Helvetica,sans-serif; font-size: x-small} + .byline,.ft-story-body,.ft-story-header{font-family: Arial,Helvetica,sans-serif} + """ + feeds = [ (u'UK' , u'http://www.ft.com/rss/home/uk' ) ,(u'US' , u'http://www.ft.com/rss/home/us' ) - ,(u'Europe' , u'http://www.ft.com/rss/home/europe' ) ,(u'Asia' , u'http://www.ft.com/rss/home/asia' ) ,(u'Middle East', u'http://www.ft.com/rss/home/middleeast') ] def preprocess_html(self, soup): - content_type = soup.find('meta', {'http-equiv':'Content-Type'}) - if content_type: - content_type['content'] = 'text/html; charset=utf-8' + items = ['promo-box','promo-title', + 'promo-headline','promo-image', + 'promo-intro','promo-link','subhead'] + for item in items: + for it in soup.findAll(item): + it.name = 'div' + it.attrs = [] + for item in soup.findAll(style=True): + del item['style'] + for item in soup.findAll('a'): + limg = item.find('img') + if item.string is not None: + str = item.string + item.replaceWith(str) + else: + if limg: + item.name = 'div' + item.attrs = [] + else: + str = self.tag_to_string(item) + item.replaceWith(str) + for item in soup.findAll('img'): + if not item.has_key('alt'): + item['alt'] = 'image' return soup + + def get_cover_url(self): + cdate = datetime.date.today() + if cdate.isoweekday() == 7: + cdate -= datetime.timedelta(days=1) + return cdate.strftime('http://specials.ft.com/vtf_pdf/%d%m%y_FRONT1_USA.pdf') + \ No newline at end of file diff --git a/recipes/icons/financial_times.png b/recipes/icons/financial_times.png new file mode 100644 index 0000000000000000000000000000000000000000..2a769d9dbb359c6713d0e27e4660c1d06ae22c54 GIT binary patch literal 1470 zcmV;v1ws0WP)$c3DqG>cElz=c@nAnccUFgmPg2^R@rfp60lW)vScNoq3#uY5B{U zx|w*cmv$W^C^9lKK07%7->6ALKK$CGPDerc$Ch+sQ_7@%|Lw5<+M>~@fuxIVLq9us zXIA{uol;Cg;IxUaka1m8NcPB<(6x%Oly#|(aaK=8TUAQ(#FXv7kY-*`=emyIxr~Bt zT8DC7mwsikl5(ewZ}GyCzo>z=m30ytA}K2_EiW)QH#Yyyn*Ga|_{x{}#+B>6kacBL zd}>(Gvxv^7fXt_dt<#+ajs{iAv|Jb7X(VY6pm+!xj&!~YRCMq#8GBYzXN<=WJk?+Bg?!b}kzme>|km|jU z>b#C|Vp4WwRCi@mcV<|h_K9|I6PXT7>n1S_~67;6etpepYp`a!!)v;qh|mwh@~akLAuNK;p6}n1szS@Ah%+!8c00Ix7tggl+1bSh??zuq z&=a4%o2NDI*^+BK*4$1&1s(irUqng8R28{LHga5!W8zX?u~SNH1nv)vz7^cAQmCh@ef|hmSYYTcM z_I%~uf?a`&^NJmtZkW_~91U8GsbFKhnTvB?|APl_zjVEQC6xM30;ph85M05&S?v-o z=T@Z6-y*bdVcT+{d8(&*n!J*IAey@VIt^Un&p{d0(y>jtlh=Rk@y=TtOh?(7UeBolhmpYvS z2gGh>#AyCF5flVb&}kEP+C$*X#N1$z35(w*Px}Yr+8qCms?)00hzFIz7BS<#e7SI77->e$QF97QNjia)e8gWg0inxg4Q0aKue3ofPo+Y Y06ekPz%t>XKmY&$07*qoM6N<$f*Td~BLDyZ literal 0 HcmV?d00001 From a8012b70dc12c89669f3436a4a63ce93012b9bb5 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 26 Jun 2011 13:32:41 -0600 Subject: [PATCH 09/22] Fix #802234 (Updated recipe for Financial times UK edition) --- recipes/financial_times_uk.recipe | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/recipes/financial_times_uk.recipe b/recipes/financial_times_uk.recipe index 6fe1ac6acd..e06eb0dc77 100644 --- a/recipes/financial_times_uk.recipe +++ b/recipes/financial_times_uk.recipe @@ -3,6 +3,8 @@ __copyright__ = '2010-2011, Darko Miletic ' ''' www.ft.com/uk-edition ''' + +import datetime from calibre import strftime from calibre.web.feeds.news import BasicNewsRecipe @@ -20,7 +22,6 @@ class FinancialTimes(BasicNewsRecipe): needs_subscription = True encoding = 'utf8' publication_type = 'newspaper' - cover_url = strftime('http://specials.ft.com/vtf_pdf/%d%m%y_FRONT1_LON.pdf') masthead_url = 'http://im.media.ft.com/m/img/masthead_main.jpg' LOGIN = 'https://registration.ft.com/registration/barrier/login' INDEX = 'http://www.ft.com/uk-edition' @@ -128,3 +129,10 @@ class FinancialTimes(BasicNewsRecipe): if not item.has_key('alt'): item['alt'] = 'image' return soup + + def get_cover_url(self): + cdate = datetime.date.today() + if cdate.isoweekday() == 7: + cdate -= datetime.timedelta(days=1) + return cdate.strftime('http://specials.ft.com/vtf_pdf/%d%m%y_FRONT1_LON.pdf') + \ No newline at end of file From 070ff2198e40dbd3b7283c3f6cab289c3614c8b3 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 26 Jun 2011 13:34:39 -0600 Subject: [PATCH 10/22] Fix #802244 (Add support for iRiver Story HD reader) --- src/calibre/devices/iriver/driver.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/src/calibre/devices/iriver/driver.py b/src/calibre/devices/iriver/driver.py index 0ad540f8a3..21b188e031 100644 --- a/src/calibre/devices/iriver/driver.py +++ b/src/calibre/devices/iriver/driver.py @@ -20,11 +20,11 @@ class IRIVER_STORY(USBMS): FORMATS = ['epub', 'fb2', 'pdf', 'djvu', 'txt'] VENDOR_ID = [0x1006] - PRODUCT_ID = [0x4023, 0x4024, 0x4025] - BCD = [0x0323] + PRODUCT_ID = [0x4023, 0x4024, 0x4025, 0x4034] + BCD = [0x0323, 0x0326] VENDOR_NAME = 'IRIVER' - WINDOWS_MAIN_MEM = ['STORY', 'STORY_EB05', 'STORY_WI-FI'] + WINDOWS_MAIN_MEM = ['STORY', 'STORY_EB05', 'STORY_WI-FI', 'STORY_EB07'] WINDOWS_CARD_A_MEM = ['STORY', 'STORY_SD'] #OSX_MAIN_MEM = 'Kindle Internal Storage Media' From eb0358025d3337720a5c878fcaad41fd3b69803a Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 26 Jun 2011 14:42:16 -0600 Subject: [PATCH 11/22] Add Ming Pao Vancouver and Toronto by Eddie Lau --- recipes/ming_pao.recipe | 334 +++++++++++------ recipes/ming_pao_toronto.recipe | 594 ++++++++++++++++++++++++++++++ recipes/ming_pao_vancouver.recipe | 594 ++++++++++++++++++++++++++++++ 3 files changed, 1414 insertions(+), 108 deletions(-) create mode 100644 recipes/ming_pao_toronto.recipe create mode 100644 recipes/ming_pao_vancouver.recipe diff --git a/recipes/ming_pao.recipe b/recipes/ming_pao.recipe index 08ee20cb15..3566fca667 100644 --- a/recipes/ming_pao.recipe +++ b/recipes/ming_pao.recipe @@ -1,17 +1,23 @@ -# -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = '2010-2011, Eddie Lau' +# Region - Hong Kong, Vancouver, Toronto +__Region__ = 'Hong Kong' # Users of Kindle 3 with limited system-level CJK support # please replace the following "True" with "False". __MakePeriodical__ = True # Turn below to true if your device supports display of CJK titles __UseChineseTitle__ = False -# Trun below to true if you wish to use life.mingpao.com as the main article source +# Set it to False if you want to skip images +__KeepImages__ = True +# (HK only) Turn below to true if you wish to use life.mingpao.com as the main article source __UseLife__ = True + ''' Change Log: +2011/06/26: add fetching Vancouver and Toronto versions of the paper, also provide captions for images using life.mingpao fetch source + provide options to remove all images in the file 2011/05/12: switch the main parse source to life.mingpao.com, which has more photos on the article pages 2011/03/06: add new articles for finance section, also a new section "Columns" 2011/02/28: rearrange the sections @@ -34,21 +40,96 @@ Change Log: import os, datetime, re from calibre.web.feeds.recipes import BasicNewsRecipe from contextlib import nested - - from calibre.ebooks.BeautifulSoup import BeautifulSoup from calibre.ebooks.metadata.opf2 import OPFCreator from calibre.ebooks.metadata.toc import TOC from calibre.ebooks.metadata import MetaInformation -class MPHKRecipe(BasicNewsRecipe): - title = 'Ming Pao - Hong Kong' +# MAIN CLASS +class MPRecipe(BasicNewsRecipe): + if __Region__ == 'Hong Kong': + title = 'Ming Pao - Hong Kong' + description = 'Hong Kong Chinese Newspaper (http://news.mingpao.com)' + category = 'Chinese, News, Hong Kong' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} font>b {font-size:200%; font-weight:bold;}' + masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif' + keep_only_tags = [dict(name='h1'), + dict(name='font', attrs={'style':['font-size:14pt; line-height:160%;']}), # for entertainment page title + dict(name='font', attrs={'color':['AA0000']}), # for column articles title + dict(attrs={'id':['newscontent']}), # entertainment and column page content + dict(attrs={'id':['newscontent01','newscontent02']}), + dict(attrs={'class':['photo']}), + dict(name='table', attrs={'width':['100%'], 'border':['0'], 'cellspacing':['5'], 'cellpadding':['0']}), # content in printed version of life.mingpao.com + dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}) # images for source from life.mingpao.com + ] + if __KeepImages__: + remove_tags = [dict(name='style'), + dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com + dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article + #dict(name='table') # for content fetched from life.mingpao.com + ] + else: + remove_tags = [dict(name='style'), + dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com + dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article + dict(name='img'), + #dict(name='table') # for content fetched from life.mingpao.com + ] + remove_attributes = ['width'] + preprocess_regexps = [ + (re.compile(r'
', re.DOTALL|re.IGNORECASE), + lambda match: '

'), + (re.compile(r'

', re.DOTALL|re.IGNORECASE), + lambda match: ''), + (re.compile(r'

', re.DOTALL|re.IGNORECASE), # for entertainment page + lambda match: ''), + # skip
after title in life.mingpao.com fetched article + (re.compile(r"

", re.DOTALL|re.IGNORECASE), + lambda match: "
"), + (re.compile(r"

", re.DOTALL|re.IGNORECASE), + lambda match: "") + ] + elif __Region__ == 'Vancouver': + title = 'Ming Pao - Vancouver' + description = 'Vancouver Chinese Newspaper (http://www.mingpaovan.com)' + category = 'Chinese, News, Vancouver' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}' + masthead_url = 'http://www.mingpaovan.com/image/mainlogo2_VAN2.gif' + keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}), + dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}), + dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}), + ] + if __KeepImages__: + remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon + else: + remove_tags = [dict(name='img')] + remove_attributes = ['width'] + preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE), + lambda match: ''), + ] + elif __Region__ == 'Toronto': + title = 'Ming Pao - Toronto' + description = 'Toronto Chinese Newspaper (http://www.mingpaotor.com)' + category = 'Chinese, News, Toronto' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}' + masthead_url = 'http://www.mingpaotor.com/image/mainlogo2_TOR2.gif' + keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}), + dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}), + dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}), + ] + if __KeepImages__: + remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon + else: + remove_tags = [dict(name='img')] + remove_attributes = ['width'] + preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE), + lambda match: ''), + ] + oldest_article = 1 max_articles_per_feed = 100 __author__ = 'Eddie Lau' - description = 'Hong Kong Chinese Newspaper (http://news.mingpao.com)' publisher = 'MingPao' - category = 'Chinese, News, Hong Kong' remove_javascript = True use_embedded_content = False no_stylesheets = True @@ -57,33 +138,6 @@ class MPHKRecipe(BasicNewsRecipe): recursions = 0 conversion_options = {'linearize_tables':True} timefmt = '' - extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} font>b {font-size:200%; font-weight:bold;}' - masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif' - keep_only_tags = [dict(name='h1'), - dict(name='font', attrs={'style':['font-size:14pt; line-height:160%;']}), # for entertainment page title - dict(name='font', attrs={'color':['AA0000']}), # for column articles title - dict(attrs={'id':['newscontent']}), # entertainment and column page content - dict(attrs={'id':['newscontent01','newscontent02']}), - dict(attrs={'class':['photo']}), - dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}) # images for source from life.mingpao.com - ] - remove_tags = [dict(name='style'), - dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com - dict(name='table')] # for content fetched from life.mingpao.com - remove_attributes = ['width'] - preprocess_regexps = [ - (re.compile(r'
', re.DOTALL|re.IGNORECASE), - lambda match: '

'), - (re.compile(r'

', re.DOTALL|re.IGNORECASE), - lambda match: ''), - (re.compile(r'

', re.DOTALL|re.IGNORECASE), # for entertainment page - lambda match: ''), - # skip
after title in life.mingpao.com fetched article - (re.compile(r"

", re.DOTALL|re.IGNORECASE), - lambda match: "
"), - (re.compile(r"

", re.DOTALL|re.IGNORECASE), - lambda match: "") - ] def image_url_processor(cls, baseurl, url): # trick: break the url at the first occurance of digit, add an additional @@ -124,8 +178,18 @@ class MPHKRecipe(BasicNewsRecipe): def get_dtlocal(self): dt_utc = datetime.datetime.utcnow() - # convert UTC to local hk time - at around HKT 6.00am, all news are available - dt_local = dt_utc - datetime.timedelta(-2.0/24) + if __Region__ == 'Hong Kong': + # convert UTC to local hk time - at HKT 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(8.0/24) - datetime.timedelta(4.5/24) + # dt_local = dt_utc.astimezone(pytz.timezone('Asia/Hong_Kong')) - datetime.timedelta(4.5/24) + elif __Region__ == 'Vancouver': + # convert UTC to local Vancouver time - at PST time 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(-8.0/24) - datetime.timedelta(4.5/24) + #dt_local = dt_utc.astimezone(pytz.timezone('America/Vancouver')) - datetime.timedelta(4.5/24) + elif __Region__ == 'Toronto': + # convert UTC to local Toronto time - at EST time 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(-5.0/24) - datetime.timedelta(4.5/24) + #dt_local = dt_utc.astimezone(pytz.timezone('America/Toronto')) - datetime.timedelta(4.5/24) return dt_local def get_fetchdate(self): @@ -135,13 +199,15 @@ class MPHKRecipe(BasicNewsRecipe): return self.get_dtlocal().strftime("%Y-%m-%d") def get_fetchday(self): - # dt_utc = datetime.datetime.utcnow() - # convert UTC to local hk time - at around HKT 6.00am, all news are available - # dt_local = dt_utc - datetime.timedelta(-2.0/24) return self.get_dtlocal().strftime("%d") def get_cover_url(self): - cover = 'http://news.mingpao.com/' + self.get_fetchdate() + '/' + self.get_fetchdate() + '_' + self.get_fetchday() + 'gacov.jpg' + if __Region__ == 'Hong Kong': + cover = 'http://news.mingpao.com/' + self.get_fetchdate() + '/' + self.get_fetchdate() + '_' + self.get_fetchday() + 'gacov.jpg' + elif __Region__ == 'Vancouver': + cover = 'http://www.mingpaovan.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgva1s.jpg' + elif __Region__ == 'Toronto': + cover = 'http://www.mingpaotor.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgtas.jpg' br = BasicNewsRecipe.get_browser() try: br.open(cover) @@ -153,76 +219,104 @@ class MPHKRecipe(BasicNewsRecipe): feeds = [] dateStr = self.get_fetchdate() - if __UseLife__: - for title, url, keystr in [(u'\u8981\u805e Headline', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalga', 'nal'), - (u'\u6e2f\u805e Local', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgb', 'nal'), - (u'\u6559\u80b2 Education', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgf', 'nal'), - (u'\u793e\u8a55/\u7b46\u9663 Editorial', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr', 'nal'), - (u'\u8ad6\u58c7 Forum', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalfa', 'nal'), - (u'\u4e2d\u570b China', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalca', 'nal'), - (u'\u570b\u969b World', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalta', 'nal'), - (u'\u7d93\u6fdf Finance', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea', 'nal'), - (u'\u9ad4\u80b2 Sport', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalsp', 'nal'), - (u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal'), - (u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')]: - articles = self.parse_section2(url, keystr) + if __Region__ == 'Hong Kong': + if __UseLife__: + for title, url, keystr in [(u'\u8981\u805e Headline', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalga', 'nal'), + (u'\u6e2f\u805e Local', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgb', 'nal'), + (u'\u6559\u80b2 Education', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgf', 'nal'), + (u'\u793e\u8a55/\u7b46\u9663 Editorial', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr', 'nal'), + (u'\u8ad6\u58c7 Forum', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalfa', 'nal'), + (u'\u4e2d\u570b China', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalca', 'nal'), + (u'\u570b\u969b World', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalta', 'nal'), + (u'\u7d93\u6fdf Finance', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea', 'nal'), + (u'\u9ad4\u80b2 Sport', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalsp', 'nal'), + (u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal'), + (u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')]: + articles = self.parse_section2(url, keystr) + if articles: + feeds.append((title, articles)) + + for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), + (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + else: + for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'), + (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'), + (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special- editorial + ed_articles = self.parse_ed_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr') + if ed_articles: + feeds.append((u'\u793e\u8a55/\u7b46\u9663 Editorial', ed_articles)) + + for title, url in [(u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'), + (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'), + (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special - finance + #fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm') + fin_articles = self.parse_fin_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea') + if fin_articles: + feeds.append((u'\u7d93\u6fdf Finance', fin_articles)) + + for title, url in [('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'), + (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special - entertainment + ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm') + if ent_articles: + feeds.append((u'\u5f71\u8996 Film/TV', ent_articles)) + + for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), + (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + + # special- columns + col_articles = self.parse_col_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn') + if col_articles: + feeds.append((u'\u5c08\u6b04 Columns', col_articles)) + elif __Region__ == 'Vancouver': + for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VAindex.htm'), + (u'\u52a0\u570b Canada', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VBindex.htm'), + (u'\u793e\u5340 Local', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VDindex.htm'), + (u'\u6e2f\u805e Hong Kong', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-VGindex.htm'), + (u'\u570b\u969b World', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VTindex.htm'), + (u'\u4e2d\u570b China', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VCindex.htm'), + (u'\u7d93\u6fdf Economics', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VEindex.htm'), + (u'\u9ad4\u80b2 Sports', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VSindex.htm'), + (u'\u5f71\u8996 Film/TV', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-MAindex.htm'), + (u'\u526f\u520a Supplements', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/WWindex.htm'),]: + articles = self.parse_section3(url, 'http://www.mingpaovan.com/') if articles: feeds.append((title, articles)) - - for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), - (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: - articles = self.parse_section(url) + elif __Region__ == 'Toronto': + for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TAindex.htm'), + (u'\u52a0\u570b Canada', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TDindex.htm'), + (u'\u793e\u5340 Local', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TFindex.htm'), + (u'\u4e2d\u570b China', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TCAindex.htm'), + (u'\u570b\u969b World', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TTAindex.htm'), + (u'\u6e2f\u805e Hong Kong', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-GAindex.htm'), + (u'\u7d93\u6fdf Economics', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/THindex.htm'), + (u'\u9ad4\u80b2 Sports', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TSindex.htm'), + (u'\u5f71\u8996 Film/TV', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-MAindex.htm'), + (u'\u526f\u520a Supplements', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/WWindex.htm'),]: + articles = self.parse_section3(url, 'http://www.mingpaotor.com/') if articles: feeds.append((title, articles)) - else: - for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'), - (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'), - (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm')]: - articles = self.parse_section(url) - if articles: - feeds.append((title, articles)) - - # special- editorial - ed_articles = self.parse_ed_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr') - if ed_articles: - feeds.append((u'\u793e\u8a55/\u7b46\u9663 Editorial', ed_articles)) - - for title, url in [(u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'), - (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'), - (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm')]: - articles = self.parse_section(url) - if articles: - feeds.append((title, articles)) - - # special - finance - #fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm') - fin_articles = self.parse_fin_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea') - if fin_articles: - feeds.append((u'\u7d93\u6fdf Finance', fin_articles)) - - for title, url in [('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'), - (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm')]: - articles = self.parse_section(url) - if articles: - feeds.append((title, articles)) - - # special - entertainment - ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm') - if ent_articles: - feeds.append((u'\u5f71\u8996 Film/TV', ent_articles)) - - for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), - (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: - articles = self.parse_section(url) - if articles: - feeds.append((title, articles)) - - - # special- columns - col_articles = self.parse_col_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn') - if col_articles: - feeds.append((u'\u5c08\u6b04 Columns', col_articles)) - return feeds # parse from news.mingpao.com @@ -256,11 +350,30 @@ class MPHKRecipe(BasicNewsRecipe): title = self.tag_to_string(i) url = 'http://life.mingpao.com/cfm/' + i.get('href', False) if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind(keystr) == -1): + url = url.replace('dailynews3.cfm', 'dailynews3a.cfm') # use printed version of the article current_articles.append({'title': title, 'url': url, 'description': ''}) included_urls.append(url) current_articles.reverse() return current_articles + # parse from www.mingpaovan.com + def parse_section3(self, url, baseUrl): + self.get_fetchdate() + soup = self.index_to_soup(url) + divs = soup.findAll(attrs={'class': ['ListContentLargeLink']}) + current_articles = [] + included_urls = [] + divs.reverse() + for i in divs: + title = self.tag_to_string(i) + urlstr = i.get('href', False) + urlstr = baseUrl + '/' + urlstr.replace('../../../', '') + if urlstr not in included_urls: + current_articles.append({'title': title, 'url': urlstr, 'description': '', 'date': ''}) + included_urls.append(urlstr) + current_articles.reverse() + return current_articles + def parse_ed_section(self, url): self.get_fetchdate() soup = self.index_to_soup(url) @@ -338,7 +451,12 @@ class MPHKRecipe(BasicNewsRecipe): if dir is None: dir = self.output_dir if __UseChineseTitle__ == True: - title = u'\u660e\u5831 (\u9999\u6e2f)' + if __Region__ == 'Hong Kong': + title = u'\u660e\u5831 (\u9999\u6e2f)' + elif __Region__ == 'Vancouver': + title = u'\u660e\u5831 (\u6eab\u54e5\u83ef)' + elif __Region__ == 'Toronto': + title = u'\u660e\u5831 (\u591a\u502b\u591a)' else: title = self.short_title() # if not generating a periodical, force date to apply in title diff --git a/recipes/ming_pao_toronto.recipe b/recipes/ming_pao_toronto.recipe new file mode 100644 index 0000000000..677a8272b0 --- /dev/null +++ b/recipes/ming_pao_toronto.recipe @@ -0,0 +1,594 @@ +__license__ = 'GPL v3' +__copyright__ = '2010-2011, Eddie Lau' + +# Region - Hong Kong, Vancouver, Toronto +__Region__ = 'Toronto' +# Users of Kindle 3 with limited system-level CJK support +# please replace the following "True" with "False". +__MakePeriodical__ = True +# Turn below to true if your device supports display of CJK titles +__UseChineseTitle__ = False +# Set it to False if you want to skip images +__KeepImages__ = True +# (HK only) Turn below to true if you wish to use life.mingpao.com as the main article source +__UseLife__ = True + + +''' +Change Log: +2011/06/26: add fetching Vancouver and Toronto versions of the paper, also provide captions for images using life.mingpao fetch source + provide options to remove all images in the file +2011/05/12: switch the main parse source to life.mingpao.com, which has more photos on the article pages +2011/03/06: add new articles for finance section, also a new section "Columns" +2011/02/28: rearrange the sections + [Disabled until Kindle has better CJK support and can remember last (section,article) read in Sections & Articles + View] make it the same title if generating a periodical, so past issue will be automatically put into "Past Issues" + folder in Kindle 3 +2011/02/20: skip duplicated links in finance section, put photos which may extend a whole page to the back of the articles + clean up the indentation +2010/12/07: add entertainment section, use newspaper front page as ebook cover, suppress date display in section list + (to avoid wrong date display in case the user generates the ebook in a time zone different from HKT) +2010/11/22: add English section, remove eco-news section which is not updated daily, correct + ordering of articles +2010/11/12: add news image and eco-news section +2010/11/08: add parsing of finance section +2010/11/06: temporary work-around for Kindle device having no capability to display unicode + in section/article list. +2010/10/31: skip repeated articles in section pages +''' + +import os, datetime, re +from calibre.web.feeds.recipes import BasicNewsRecipe +from contextlib import nested +from calibre.ebooks.BeautifulSoup import BeautifulSoup +from calibre.ebooks.metadata.opf2 import OPFCreator +from calibre.ebooks.metadata.toc import TOC +from calibre.ebooks.metadata import MetaInformation + +# MAIN CLASS +class MPRecipe(BasicNewsRecipe): + if __Region__ == 'Hong Kong': + title = 'Ming Pao - Hong Kong' + description = 'Hong Kong Chinese Newspaper (http://news.mingpao.com)' + category = 'Chinese, News, Hong Kong' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} font>b {font-size:200%; font-weight:bold;}' + masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif' + keep_only_tags = [dict(name='h1'), + dict(name='font', attrs={'style':['font-size:14pt; line-height:160%;']}), # for entertainment page title + dict(name='font', attrs={'color':['AA0000']}), # for column articles title + dict(attrs={'id':['newscontent']}), # entertainment and column page content + dict(attrs={'id':['newscontent01','newscontent02']}), + dict(attrs={'class':['photo']}), + dict(name='table', attrs={'width':['100%'], 'border':['0'], 'cellspacing':['5'], 'cellpadding':['0']}), # content in printed version of life.mingpao.com + dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}) # images for source from life.mingpao.com + ] + if __KeepImages__: + remove_tags = [dict(name='style'), + dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com + dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article + #dict(name='table') # for content fetched from life.mingpao.com + ] + else: + remove_tags = [dict(name='style'), + dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com + dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article + dict(name='img'), + #dict(name='table') # for content fetched from life.mingpao.com + ] + remove_attributes = ['width'] + preprocess_regexps = [ + (re.compile(r'
', re.DOTALL|re.IGNORECASE), + lambda match: '

'), + (re.compile(r'

', re.DOTALL|re.IGNORECASE), + lambda match: ''), + (re.compile(r'

', re.DOTALL|re.IGNORECASE), # for entertainment page + lambda match: ''), + # skip
after title in life.mingpao.com fetched article + (re.compile(r"

", re.DOTALL|re.IGNORECASE), + lambda match: "
"), + (re.compile(r"

", re.DOTALL|re.IGNORECASE), + lambda match: "") + ] + elif __Region__ == 'Vancouver': + title = 'Ming Pao - Vancouver' + description = 'Vancouver Chinese Newspaper (http://www.mingpaovan.com)' + category = 'Chinese, News, Vancouver' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}' + masthead_url = 'http://www.mingpaovan.com/image/mainlogo2_VAN2.gif' + keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}), + dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}), + dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}), + ] + if __KeepImages__: + remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon + else: + remove_tags = [dict(name='img')] + remove_attributes = ['width'] + preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE), + lambda match: ''), + ] + elif __Region__ == 'Toronto': + title = 'Ming Pao - Toronto' + description = 'Toronto Chinese Newspaper (http://www.mingpaotor.com)' + category = 'Chinese, News, Toronto' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}' + masthead_url = 'http://www.mingpaotor.com/image/mainlogo2_TOR2.gif' + keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}), + dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}), + dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}), + ] + if __KeepImages__: + remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon + else: + remove_tags = [dict(name='img')] + remove_attributes = ['width'] + preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE), + lambda match: ''), + ] + + oldest_article = 1 + max_articles_per_feed = 100 + __author__ = 'Eddie Lau' + publisher = 'MingPao' + remove_javascript = True + use_embedded_content = False + no_stylesheets = True + language = 'zh' + encoding = 'Big5-HKSCS' + recursions = 0 + conversion_options = {'linearize_tables':True} + timefmt = '' + + def image_url_processor(cls, baseurl, url): + # trick: break the url at the first occurance of digit, add an additional + # '_' at the front + # not working, may need to move this to preprocess_html() method +# minIdx = 10000 +# i0 = url.find('0') +# if i0 >= 0 and i0 < minIdx: +# minIdx = i0 +# i1 = url.find('1') +# if i1 >= 0 and i1 < minIdx: +# minIdx = i1 +# i2 = url.find('2') +# if i2 >= 0 and i2 < minIdx: +# minIdx = i2 +# i3 = url.find('3') +# if i3 >= 0 and i0 < minIdx: +# minIdx = i3 +# i4 = url.find('4') +# if i4 >= 0 and i4 < minIdx: +# minIdx = i4 +# i5 = url.find('5') +# if i5 >= 0 and i5 < minIdx: +# minIdx = i5 +# i6 = url.find('6') +# if i6 >= 0 and i6 < minIdx: +# minIdx = i6 +# i7 = url.find('7') +# if i7 >= 0 and i7 < minIdx: +# minIdx = i7 +# i8 = url.find('8') +# if i8 >= 0 and i8 < minIdx: +# minIdx = i8 +# i9 = url.find('9') +# if i9 >= 0 and i9 < minIdx: +# minIdx = i9 + return url + + def get_dtlocal(self): + dt_utc = datetime.datetime.utcnow() + if __Region__ == 'Hong Kong': + # convert UTC to local hk time - at HKT 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(8.0/24) - datetime.timedelta(4.5/24) + # dt_local = dt_utc.astimezone(pytz.timezone('Asia/Hong_Kong')) - datetime.timedelta(4.5/24) + elif __Region__ == 'Vancouver': + # convert UTC to local Vancouver time - at PST time 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(-8.0/24) - datetime.timedelta(4.5/24) + #dt_local = dt_utc.astimezone(pytz.timezone('America/Vancouver')) - datetime.timedelta(4.5/24) + elif __Region__ == 'Toronto': + # convert UTC to local Toronto time - at EST time 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(-5.0/24) - datetime.timedelta(4.5/24) + #dt_local = dt_utc.astimezone(pytz.timezone('America/Toronto')) - datetime.timedelta(4.5/24) + return dt_local + + def get_fetchdate(self): + return self.get_dtlocal().strftime("%Y%m%d") + + def get_fetchformatteddate(self): + return self.get_dtlocal().strftime("%Y-%m-%d") + + def get_fetchday(self): + return self.get_dtlocal().strftime("%d") + + def get_cover_url(self): + if __Region__ == 'Hong Kong': + cover = 'http://news.mingpao.com/' + self.get_fetchdate() + '/' + self.get_fetchdate() + '_' + self.get_fetchday() + 'gacov.jpg' + elif __Region__ == 'Vancouver': + cover = 'http://www.mingpaovan.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgva1s.jpg' + elif __Region__ == 'Toronto': + cover = 'http://www.mingpaotor.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgtas.jpg' + br = BasicNewsRecipe.get_browser() + try: + br.open(cover) + except: + cover = None + return cover + + def parse_index(self): + feeds = [] + dateStr = self.get_fetchdate() + + if __Region__ == 'Hong Kong': + if __UseLife__: + for title, url, keystr in [(u'\u8981\u805e Headline', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalga', 'nal'), + (u'\u6e2f\u805e Local', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgb', 'nal'), + (u'\u6559\u80b2 Education', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgf', 'nal'), + (u'\u793e\u8a55/\u7b46\u9663 Editorial', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr', 'nal'), + (u'\u8ad6\u58c7 Forum', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalfa', 'nal'), + (u'\u4e2d\u570b China', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalca', 'nal'), + (u'\u570b\u969b World', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalta', 'nal'), + (u'\u7d93\u6fdf Finance', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea', 'nal'), + (u'\u9ad4\u80b2 Sport', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalsp', 'nal'), + (u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal'), + (u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')]: + articles = self.parse_section2(url, keystr) + if articles: + feeds.append((title, articles)) + + for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), + (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + else: + for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'), + (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'), + (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special- editorial + ed_articles = self.parse_ed_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr') + if ed_articles: + feeds.append((u'\u793e\u8a55/\u7b46\u9663 Editorial', ed_articles)) + + for title, url in [(u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'), + (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'), + (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special - finance + #fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm') + fin_articles = self.parse_fin_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea') + if fin_articles: + feeds.append((u'\u7d93\u6fdf Finance', fin_articles)) + + for title, url in [('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'), + (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special - entertainment + ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm') + if ent_articles: + feeds.append((u'\u5f71\u8996 Film/TV', ent_articles)) + + for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), + (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + + # special- columns + col_articles = self.parse_col_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn') + if col_articles: + feeds.append((u'\u5c08\u6b04 Columns', col_articles)) + elif __Region__ == 'Vancouver': + for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VAindex.htm'), + (u'\u52a0\u570b Canada', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VBindex.htm'), + (u'\u793e\u5340 Local', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VDindex.htm'), + (u'\u6e2f\u805e Hong Kong', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-VGindex.htm'), + (u'\u570b\u969b World', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VTindex.htm'), + (u'\u4e2d\u570b China', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VCindex.htm'), + (u'\u7d93\u6fdf Economics', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VEindex.htm'), + (u'\u9ad4\u80b2 Sports', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VSindex.htm'), + (u'\u5f71\u8996 Film/TV', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-MAindex.htm'), + (u'\u526f\u520a Supplements', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/WWindex.htm'),]: + articles = self.parse_section3(url, 'http://www.mingpaovan.com/') + if articles: + feeds.append((title, articles)) + elif __Region__ == 'Toronto': + for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TAindex.htm'), + (u'\u52a0\u570b Canada', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TDindex.htm'), + (u'\u793e\u5340 Local', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TFindex.htm'), + (u'\u4e2d\u570b China', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TCAindex.htm'), + (u'\u570b\u969b World', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TTAindex.htm'), + (u'\u6e2f\u805e Hong Kong', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-GAindex.htm'), + (u'\u7d93\u6fdf Economics', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/THindex.htm'), + (u'\u9ad4\u80b2 Sports', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TSindex.htm'), + (u'\u5f71\u8996 Film/TV', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-MAindex.htm'), + (u'\u526f\u520a Supplements', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/WWindex.htm'),]: + articles = self.parse_section3(url, 'http://www.mingpaotor.com/') + if articles: + feeds.append((title, articles)) + return feeds + + # parse from news.mingpao.com + def parse_section(self, url): + dateStr = self.get_fetchdate() + soup = self.index_to_soup(url) + divs = soup.findAll(attrs={'class': ['bullet','bullet_grey']}) + current_articles = [] + included_urls = [] + divs.reverse() + for i in divs: + a = i.find('a', href = True) + title = self.tag_to_string(a) + url = a.get('href', False) + url = 'http://news.mingpao.com/' + dateStr + '/' +url + if url not in included_urls and url.rfind('Redirect') == -1: + current_articles.append({'title': title, 'url': url, 'description':'', 'date':''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + # parse from life.mingpao.com + def parse_section2(self, url, keystr): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind(keystr) == -1): + url = url.replace('dailynews3.cfm', 'dailynews3a.cfm') # use printed version of the article + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + # parse from www.mingpaovan.com + def parse_section3(self, url, baseUrl): + self.get_fetchdate() + soup = self.index_to_soup(url) + divs = soup.findAll(attrs={'class': ['ListContentLargeLink']}) + current_articles = [] + included_urls = [] + divs.reverse() + for i in divs: + title = self.tag_to_string(i) + urlstr = i.get('href', False) + urlstr = baseUrl + '/' + urlstr.replace('../../../', '') + if urlstr not in included_urls: + current_articles.append({'title': title, 'url': urlstr, 'description': '', 'date': ''}) + included_urls.append(urlstr) + current_articles.reverse() + return current_articles + + def parse_ed_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('nal') == -1): + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + def parse_fin_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href= True) + current_articles = [] + included_urls = [] + for i in a: + #url = 'http://www.mpfinance.com/cfm/' + i.get('href', False) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + #if url not in included_urls and not url.rfind(dateStr) == -1 and url.rfind('index') == -1: + if url not in included_urls and (not url.rfind('txt') == -1) and (not url.rfind('nal') == -1): + title = self.tag_to_string(i) + current_articles.append({'title': title, 'url': url, 'description':''}) + included_urls.append(url) + return current_articles + + def parse_ent_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://ol.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('star') == -1): + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + def parse_col_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('ncl') == -1): + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + for item in soup.findAll(style=True): + del item['width'] + for item in soup.findAll(stype=True): + del item['absmiddle'] + return soup + + def create_opf(self, feeds, dir=None): + if dir is None: + dir = self.output_dir + if __UseChineseTitle__ == True: + if __Region__ == 'Hong Kong': + title = u'\u660e\u5831 (\u9999\u6e2f)' + elif __Region__ == 'Vancouver': + title = u'\u660e\u5831 (\u6eab\u54e5\u83ef)' + elif __Region__ == 'Toronto': + title = u'\u660e\u5831 (\u591a\u502b\u591a)' + else: + title = self.short_title() + # if not generating a periodical, force date to apply in title + if __MakePeriodical__ == False: + title = title + ' ' + self.get_fetchformatteddate() + if True: + mi = MetaInformation(title, [self.publisher]) + mi.publisher = self.publisher + mi.author_sort = self.publisher + if __MakePeriodical__ == True: + mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title() + else: + mi.publication_type = self.publication_type+':'+self.short_title() + #mi.timestamp = nowf() + mi.timestamp = self.get_dtlocal() + mi.comments = self.description + if not isinstance(mi.comments, unicode): + mi.comments = mi.comments.decode('utf-8', 'replace') + #mi.pubdate = nowf() + mi.pubdate = self.get_dtlocal() + opf_path = os.path.join(dir, 'index.opf') + ncx_path = os.path.join(dir, 'index.ncx') + opf = OPFCreator(dir, mi) + # Add mastheadImage entry to section + mp = getattr(self, 'masthead_path', None) + if mp is not None and os.access(mp, os.R_OK): + from calibre.ebooks.metadata.opf2 import Guide + ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu()) + ref.type = 'masthead' + ref.title = 'Masthead Image' + opf.guide.append(ref) + + manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))] + manifest.append(os.path.join(dir, 'index.html')) + manifest.append(os.path.join(dir, 'index.ncx')) + + # Get cover + cpath = getattr(self, 'cover_path', None) + if cpath is None: + pf = open(os.path.join(dir, 'cover.jpg'), 'wb') + if self.default_cover(pf): + cpath = pf.name + if cpath is not None and os.access(cpath, os.R_OK): + opf.cover = cpath + manifest.append(cpath) + + # Get masthead + mpath = getattr(self, 'masthead_path', None) + if mpath is not None and os.access(mpath, os.R_OK): + manifest.append(mpath) + + opf.create_manifest_from_files_in(manifest) + for mani in opf.manifest: + if mani.path.endswith('.ncx'): + mani.id = 'ncx' + if mani.path.endswith('mastheadImage.jpg'): + mani.id = 'masthead-image' + entries = ['index.html'] + toc = TOC(base_path=dir) + self.play_order_counter = 0 + self.play_order_map = {} + + def feed_index(num, parent): + f = feeds[num] + for j, a in enumerate(f): + if getattr(a, 'downloaded', False): + adir = 'feed_%d/article_%d/'%(num, j) + auth = a.author + if not auth: + auth = None + desc = a.text_summary + if not desc: + desc = None + else: + desc = self.description_limiter(desc) + entries.append('%sindex.html'%adir) + po = self.play_order_map.get(entries[-1], None) + if po is None: + self.play_order_counter += 1 + po = self.play_order_counter + parent.add_item('%sindex.html'%adir, None, a.title if a.title else _('Untitled Article'), + play_order=po, author=auth, description=desc) + last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep)) + for sp in a.sub_pages: + prefix = os.path.commonprefix([opf_path, sp]) + relp = sp[len(prefix):] + entries.append(relp.replace(os.sep, '/')) + last = sp + + if os.path.exists(last): + with open(last, 'rb') as fi: + src = fi.read().decode('utf-8') + soup = BeautifulSoup(src) + body = soup.find('body') + if body is not None: + prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last)))) + templ = self.navbar.generate(True, num, j, len(f), + not self.has_single_feed, + a.orig_url, self.publisher, prefix=prefix, + center=self.center_navbar) + elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div') + body.insert(len(body.contents), elem) + with open(last, 'wb') as fi: + fi.write(unicode(soup).encode('utf-8')) + if len(feeds) == 0: + raise Exception('All feeds are empty, aborting.') + + if len(feeds) > 1: + for i, f in enumerate(feeds): + entries.append('feed_%d/index.html'%i) + po = self.play_order_map.get(entries[-1], None) + if po is None: + self.play_order_counter += 1 + po = self.play_order_counter + auth = getattr(f, 'author', None) + if not auth: + auth = None + desc = getattr(f, 'description', None) + if not desc: + desc = None + feed_index(i, toc.add_item('feed_%d/index.html'%i, None, + f.title, play_order=po, description=desc, author=auth)) + + else: + entries.append('feed_%d/index.html'%0) + feed_index(0, toc) + + for i, p in enumerate(entries): + entries[i] = os.path.join(dir, p.replace('/', os.sep)) + opf.create_spine(entries) + opf.set_toc(toc) + + with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file): + opf.render(opf_file, ncx_file) + diff --git a/recipes/ming_pao_vancouver.recipe b/recipes/ming_pao_vancouver.recipe new file mode 100644 index 0000000000..3312c8f7b8 --- /dev/null +++ b/recipes/ming_pao_vancouver.recipe @@ -0,0 +1,594 @@ +__license__ = 'GPL v3' +__copyright__ = '2010-2011, Eddie Lau' + +# Region - Hong Kong, Vancouver, Toronto +__Region__ = 'Vancouver' +# Users of Kindle 3 with limited system-level CJK support +# please replace the following "True" with "False". +__MakePeriodical__ = True +# Turn below to true if your device supports display of CJK titles +__UseChineseTitle__ = False +# Set it to False if you want to skip images +__KeepImages__ = True +# (HK only) Turn below to true if you wish to use life.mingpao.com as the main article source +__UseLife__ = True + + +''' +Change Log: +2011/06/26: add fetching Vancouver and Toronto versions of the paper, also provide captions for images using life.mingpao fetch source + provide options to remove all images in the file +2011/05/12: switch the main parse source to life.mingpao.com, which has more photos on the article pages +2011/03/06: add new articles for finance section, also a new section "Columns" +2011/02/28: rearrange the sections + [Disabled until Kindle has better CJK support and can remember last (section,article) read in Sections & Articles + View] make it the same title if generating a periodical, so past issue will be automatically put into "Past Issues" + folder in Kindle 3 +2011/02/20: skip duplicated links in finance section, put photos which may extend a whole page to the back of the articles + clean up the indentation +2010/12/07: add entertainment section, use newspaper front page as ebook cover, suppress date display in section list + (to avoid wrong date display in case the user generates the ebook in a time zone different from HKT) +2010/11/22: add English section, remove eco-news section which is not updated daily, correct + ordering of articles +2010/11/12: add news image and eco-news section +2010/11/08: add parsing of finance section +2010/11/06: temporary work-around for Kindle device having no capability to display unicode + in section/article list. +2010/10/31: skip repeated articles in section pages +''' + +import os, datetime, re +from calibre.web.feeds.recipes import BasicNewsRecipe +from contextlib import nested +from calibre.ebooks.BeautifulSoup import BeautifulSoup +from calibre.ebooks.metadata.opf2 import OPFCreator +from calibre.ebooks.metadata.toc import TOC +from calibre.ebooks.metadata import MetaInformation + +# MAIN CLASS +class MPRecipe(BasicNewsRecipe): + if __Region__ == 'Hong Kong': + title = 'Ming Pao - Hong Kong' + description = 'Hong Kong Chinese Newspaper (http://news.mingpao.com)' + category = 'Chinese, News, Hong Kong' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} font>b {font-size:200%; font-weight:bold;}' + masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif' + keep_only_tags = [dict(name='h1'), + dict(name='font', attrs={'style':['font-size:14pt; line-height:160%;']}), # for entertainment page title + dict(name='font', attrs={'color':['AA0000']}), # for column articles title + dict(attrs={'id':['newscontent']}), # entertainment and column page content + dict(attrs={'id':['newscontent01','newscontent02']}), + dict(attrs={'class':['photo']}), + dict(name='table', attrs={'width':['100%'], 'border':['0'], 'cellspacing':['5'], 'cellpadding':['0']}), # content in printed version of life.mingpao.com + dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}) # images for source from life.mingpao.com + ] + if __KeepImages__: + remove_tags = [dict(name='style'), + dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com + dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article + #dict(name='table') # for content fetched from life.mingpao.com + ] + else: + remove_tags = [dict(name='style'), + dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com + dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article + dict(name='img'), + #dict(name='table') # for content fetched from life.mingpao.com + ] + remove_attributes = ['width'] + preprocess_regexps = [ + (re.compile(r'
', re.DOTALL|re.IGNORECASE), + lambda match: '

'), + (re.compile(r'

', re.DOTALL|re.IGNORECASE), + lambda match: ''), + (re.compile(r'

', re.DOTALL|re.IGNORECASE), # for entertainment page + lambda match: ''), + # skip
after title in life.mingpao.com fetched article + (re.compile(r"

", re.DOTALL|re.IGNORECASE), + lambda match: "
"), + (re.compile(r"

", re.DOTALL|re.IGNORECASE), + lambda match: "") + ] + elif __Region__ == 'Vancouver': + title = 'Ming Pao - Vancouver' + description = 'Vancouver Chinese Newspaper (http://www.mingpaovan.com)' + category = 'Chinese, News, Vancouver' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}' + masthead_url = 'http://www.mingpaovan.com/image/mainlogo2_VAN2.gif' + keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}), + dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}), + dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}), + ] + if __KeepImages__: + remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon + else: + remove_tags = [dict(name='img')] + remove_attributes = ['width'] + preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE), + lambda match: ''), + ] + elif __Region__ == 'Toronto': + title = 'Ming Pao - Toronto' + description = 'Toronto Chinese Newspaper (http://www.mingpaotor.com)' + category = 'Chinese, News, Toronto' + extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}' + masthead_url = 'http://www.mingpaotor.com/image/mainlogo2_TOR2.gif' + keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}), + dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}), + dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}), + ] + if __KeepImages__: + remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon + else: + remove_tags = [dict(name='img')] + remove_attributes = ['width'] + preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE), + lambda match: ''), + ] + + oldest_article = 1 + max_articles_per_feed = 100 + __author__ = 'Eddie Lau' + publisher = 'MingPao' + remove_javascript = True + use_embedded_content = False + no_stylesheets = True + language = 'zh' + encoding = 'Big5-HKSCS' + recursions = 0 + conversion_options = {'linearize_tables':True} + timefmt = '' + + def image_url_processor(cls, baseurl, url): + # trick: break the url at the first occurance of digit, add an additional + # '_' at the front + # not working, may need to move this to preprocess_html() method +# minIdx = 10000 +# i0 = url.find('0') +# if i0 >= 0 and i0 < minIdx: +# minIdx = i0 +# i1 = url.find('1') +# if i1 >= 0 and i1 < minIdx: +# minIdx = i1 +# i2 = url.find('2') +# if i2 >= 0 and i2 < minIdx: +# minIdx = i2 +# i3 = url.find('3') +# if i3 >= 0 and i0 < minIdx: +# minIdx = i3 +# i4 = url.find('4') +# if i4 >= 0 and i4 < minIdx: +# minIdx = i4 +# i5 = url.find('5') +# if i5 >= 0 and i5 < minIdx: +# minIdx = i5 +# i6 = url.find('6') +# if i6 >= 0 and i6 < minIdx: +# minIdx = i6 +# i7 = url.find('7') +# if i7 >= 0 and i7 < minIdx: +# minIdx = i7 +# i8 = url.find('8') +# if i8 >= 0 and i8 < minIdx: +# minIdx = i8 +# i9 = url.find('9') +# if i9 >= 0 and i9 < minIdx: +# minIdx = i9 + return url + + def get_dtlocal(self): + dt_utc = datetime.datetime.utcnow() + if __Region__ == 'Hong Kong': + # convert UTC to local hk time - at HKT 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(8.0/24) - datetime.timedelta(4.5/24) + # dt_local = dt_utc.astimezone(pytz.timezone('Asia/Hong_Kong')) - datetime.timedelta(4.5/24) + elif __Region__ == 'Vancouver': + # convert UTC to local Vancouver time - at PST time 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(-8.0/24) - datetime.timedelta(4.5/24) + #dt_local = dt_utc.astimezone(pytz.timezone('America/Vancouver')) - datetime.timedelta(4.5/24) + elif __Region__ == 'Toronto': + # convert UTC to local Toronto time - at EST time 4.30am, all news are available + dt_local = dt_utc + datetime.timedelta(-5.0/24) - datetime.timedelta(4.5/24) + #dt_local = dt_utc.astimezone(pytz.timezone('America/Toronto')) - datetime.timedelta(4.5/24) + return dt_local + + def get_fetchdate(self): + return self.get_dtlocal().strftime("%Y%m%d") + + def get_fetchformatteddate(self): + return self.get_dtlocal().strftime("%Y-%m-%d") + + def get_fetchday(self): + return self.get_dtlocal().strftime("%d") + + def get_cover_url(self): + if __Region__ == 'Hong Kong': + cover = 'http://news.mingpao.com/' + self.get_fetchdate() + '/' + self.get_fetchdate() + '_' + self.get_fetchday() + 'gacov.jpg' + elif __Region__ == 'Vancouver': + cover = 'http://www.mingpaovan.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgva1s.jpg' + elif __Region__ == 'Toronto': + cover = 'http://www.mingpaotor.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgtas.jpg' + br = BasicNewsRecipe.get_browser() + try: + br.open(cover) + except: + cover = None + return cover + + def parse_index(self): + feeds = [] + dateStr = self.get_fetchdate() + + if __Region__ == 'Hong Kong': + if __UseLife__: + for title, url, keystr in [(u'\u8981\u805e Headline', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalga', 'nal'), + (u'\u6e2f\u805e Local', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgb', 'nal'), + (u'\u6559\u80b2 Education', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgf', 'nal'), + (u'\u793e\u8a55/\u7b46\u9663 Editorial', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr', 'nal'), + (u'\u8ad6\u58c7 Forum', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalfa', 'nal'), + (u'\u4e2d\u570b China', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalca', 'nal'), + (u'\u570b\u969b World', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalta', 'nal'), + (u'\u7d93\u6fdf Finance', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea', 'nal'), + (u'\u9ad4\u80b2 Sport', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalsp', 'nal'), + (u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal'), + (u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')]: + articles = self.parse_section2(url, keystr) + if articles: + feeds.append((title, articles)) + + for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), + (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + else: + for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'), + (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'), + (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special- editorial + ed_articles = self.parse_ed_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr') + if ed_articles: + feeds.append((u'\u793e\u8a55/\u7b46\u9663 Editorial', ed_articles)) + + for title, url in [(u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'), + (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'), + (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special - finance + #fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm') + fin_articles = self.parse_fin_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea') + if fin_articles: + feeds.append((u'\u7d93\u6fdf Finance', fin_articles)) + + for title, url in [('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'), + (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + # special - entertainment + ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm') + if ent_articles: + feeds.append((u'\u5f71\u8996 Film/TV', ent_articles)) + + for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'), + (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]: + articles = self.parse_section(url) + if articles: + feeds.append((title, articles)) + + + # special- columns + col_articles = self.parse_col_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn') + if col_articles: + feeds.append((u'\u5c08\u6b04 Columns', col_articles)) + elif __Region__ == 'Vancouver': + for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VAindex.htm'), + (u'\u52a0\u570b Canada', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VBindex.htm'), + (u'\u793e\u5340 Local', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VDindex.htm'), + (u'\u6e2f\u805e Hong Kong', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-VGindex.htm'), + (u'\u570b\u969b World', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VTindex.htm'), + (u'\u4e2d\u570b China', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VCindex.htm'), + (u'\u7d93\u6fdf Economics', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VEindex.htm'), + (u'\u9ad4\u80b2 Sports', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VSindex.htm'), + (u'\u5f71\u8996 Film/TV', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-MAindex.htm'), + (u'\u526f\u520a Supplements', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/WWindex.htm'),]: + articles = self.parse_section3(url, 'http://www.mingpaovan.com/') + if articles: + feeds.append((title, articles)) + elif __Region__ == 'Toronto': + for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TAindex.htm'), + (u'\u52a0\u570b Canada', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TDindex.htm'), + (u'\u793e\u5340 Local', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TFindex.htm'), + (u'\u4e2d\u570b China', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TCAindex.htm'), + (u'\u570b\u969b World', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TTAindex.htm'), + (u'\u6e2f\u805e Hong Kong', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-GAindex.htm'), + (u'\u7d93\u6fdf Economics', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/THindex.htm'), + (u'\u9ad4\u80b2 Sports', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TSindex.htm'), + (u'\u5f71\u8996 Film/TV', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-MAindex.htm'), + (u'\u526f\u520a Supplements', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/WWindex.htm'),]: + articles = self.parse_section3(url, 'http://www.mingpaotor.com/') + if articles: + feeds.append((title, articles)) + return feeds + + # parse from news.mingpao.com + def parse_section(self, url): + dateStr = self.get_fetchdate() + soup = self.index_to_soup(url) + divs = soup.findAll(attrs={'class': ['bullet','bullet_grey']}) + current_articles = [] + included_urls = [] + divs.reverse() + for i in divs: + a = i.find('a', href = True) + title = self.tag_to_string(a) + url = a.get('href', False) + url = 'http://news.mingpao.com/' + dateStr + '/' +url + if url not in included_urls and url.rfind('Redirect') == -1: + current_articles.append({'title': title, 'url': url, 'description':'', 'date':''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + # parse from life.mingpao.com + def parse_section2(self, url, keystr): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind(keystr) == -1): + url = url.replace('dailynews3.cfm', 'dailynews3a.cfm') # use printed version of the article + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + # parse from www.mingpaovan.com + def parse_section3(self, url, baseUrl): + self.get_fetchdate() + soup = self.index_to_soup(url) + divs = soup.findAll(attrs={'class': ['ListContentLargeLink']}) + current_articles = [] + included_urls = [] + divs.reverse() + for i in divs: + title = self.tag_to_string(i) + urlstr = i.get('href', False) + urlstr = baseUrl + '/' + urlstr.replace('../../../', '') + if urlstr not in included_urls: + current_articles.append({'title': title, 'url': urlstr, 'description': '', 'date': ''}) + included_urls.append(urlstr) + current_articles.reverse() + return current_articles + + def parse_ed_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('nal') == -1): + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + def parse_fin_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href= True) + current_articles = [] + included_urls = [] + for i in a: + #url = 'http://www.mpfinance.com/cfm/' + i.get('href', False) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + #if url not in included_urls and not url.rfind(dateStr) == -1 and url.rfind('index') == -1: + if url not in included_urls and (not url.rfind('txt') == -1) and (not url.rfind('nal') == -1): + title = self.tag_to_string(i) + current_articles.append({'title': title, 'url': url, 'description':''}) + included_urls.append(url) + return current_articles + + def parse_ent_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://ol.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('star') == -1): + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + def parse_col_section(self, url): + self.get_fetchdate() + soup = self.index_to_soup(url) + a = soup.findAll('a', href=True) + a.reverse() + current_articles = [] + included_urls = [] + for i in a: + title = self.tag_to_string(i) + url = 'http://life.mingpao.com/cfm/' + i.get('href', False) + if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('ncl') == -1): + current_articles.append({'title': title, 'url': url, 'description': ''}) + included_urls.append(url) + current_articles.reverse() + return current_articles + + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + for item in soup.findAll(style=True): + del item['width'] + for item in soup.findAll(stype=True): + del item['absmiddle'] + return soup + + def create_opf(self, feeds, dir=None): + if dir is None: + dir = self.output_dir + if __UseChineseTitle__ == True: + if __Region__ == 'Hong Kong': + title = u'\u660e\u5831 (\u9999\u6e2f)' + elif __Region__ == 'Vancouver': + title = u'\u660e\u5831 (\u6eab\u54e5\u83ef)' + elif __Region__ == 'Toronto': + title = u'\u660e\u5831 (\u591a\u502b\u591a)' + else: + title = self.short_title() + # if not generating a periodical, force date to apply in title + if __MakePeriodical__ == False: + title = title + ' ' + self.get_fetchformatteddate() + if True: + mi = MetaInformation(title, [self.publisher]) + mi.publisher = self.publisher + mi.author_sort = self.publisher + if __MakePeriodical__ == True: + mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title() + else: + mi.publication_type = self.publication_type+':'+self.short_title() + #mi.timestamp = nowf() + mi.timestamp = self.get_dtlocal() + mi.comments = self.description + if not isinstance(mi.comments, unicode): + mi.comments = mi.comments.decode('utf-8', 'replace') + #mi.pubdate = nowf() + mi.pubdate = self.get_dtlocal() + opf_path = os.path.join(dir, 'index.opf') + ncx_path = os.path.join(dir, 'index.ncx') + opf = OPFCreator(dir, mi) + # Add mastheadImage entry to section + mp = getattr(self, 'masthead_path', None) + if mp is not None and os.access(mp, os.R_OK): + from calibre.ebooks.metadata.opf2 import Guide + ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu()) + ref.type = 'masthead' + ref.title = 'Masthead Image' + opf.guide.append(ref) + + manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))] + manifest.append(os.path.join(dir, 'index.html')) + manifest.append(os.path.join(dir, 'index.ncx')) + + # Get cover + cpath = getattr(self, 'cover_path', None) + if cpath is None: + pf = open(os.path.join(dir, 'cover.jpg'), 'wb') + if self.default_cover(pf): + cpath = pf.name + if cpath is not None and os.access(cpath, os.R_OK): + opf.cover = cpath + manifest.append(cpath) + + # Get masthead + mpath = getattr(self, 'masthead_path', None) + if mpath is not None and os.access(mpath, os.R_OK): + manifest.append(mpath) + + opf.create_manifest_from_files_in(manifest) + for mani in opf.manifest: + if mani.path.endswith('.ncx'): + mani.id = 'ncx' + if mani.path.endswith('mastheadImage.jpg'): + mani.id = 'masthead-image' + entries = ['index.html'] + toc = TOC(base_path=dir) + self.play_order_counter = 0 + self.play_order_map = {} + + def feed_index(num, parent): + f = feeds[num] + for j, a in enumerate(f): + if getattr(a, 'downloaded', False): + adir = 'feed_%d/article_%d/'%(num, j) + auth = a.author + if not auth: + auth = None + desc = a.text_summary + if not desc: + desc = None + else: + desc = self.description_limiter(desc) + entries.append('%sindex.html'%adir) + po = self.play_order_map.get(entries[-1], None) + if po is None: + self.play_order_counter += 1 + po = self.play_order_counter + parent.add_item('%sindex.html'%adir, None, a.title if a.title else _('Untitled Article'), + play_order=po, author=auth, description=desc) + last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep)) + for sp in a.sub_pages: + prefix = os.path.commonprefix([opf_path, sp]) + relp = sp[len(prefix):] + entries.append(relp.replace(os.sep, '/')) + last = sp + + if os.path.exists(last): + with open(last, 'rb') as fi: + src = fi.read().decode('utf-8') + soup = BeautifulSoup(src) + body = soup.find('body') + if body is not None: + prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last)))) + templ = self.navbar.generate(True, num, j, len(f), + not self.has_single_feed, + a.orig_url, self.publisher, prefix=prefix, + center=self.center_navbar) + elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div') + body.insert(len(body.contents), elem) + with open(last, 'wb') as fi: + fi.write(unicode(soup).encode('utf-8')) + if len(feeds) == 0: + raise Exception('All feeds are empty, aborting.') + + if len(feeds) > 1: + for i, f in enumerate(feeds): + entries.append('feed_%d/index.html'%i) + po = self.play_order_map.get(entries[-1], None) + if po is None: + self.play_order_counter += 1 + po = self.play_order_counter + auth = getattr(f, 'author', None) + if not auth: + auth = None + desc = getattr(f, 'description', None) + if not desc: + desc = None + feed_index(i, toc.add_item('feed_%d/index.html'%i, None, + f.title, play_order=po, description=desc, author=auth)) + + else: + entries.append('feed_%d/index.html'%0) + feed_index(0, toc) + + for i, p in enumerate(entries): + entries[i] = os.path.join(dir, p.replace('/', os.sep)) + opf.create_spine(entries) + opf.set_toc(toc) + + with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file): + opf.render(opf_file, ncx_file) + From 38364443a7c9cbacdec724bd197e453ba89c1ffc Mon Sep 17 00:00:00 2001 From: John Schember Date: Sun, 26 Jun 2011 20:56:43 -0400 Subject: [PATCH 12/22] OpenSearch: rewrite module to use lxml and remove the modified feed parser as it causes all avaliable file descriptors to be used. Store: Rework opensearch class to use the changes to the opensearch module. --- src/calibre/gui2/store/opensearch_store.py | 81 +- .../gui2/store/stores/archive_org_plugin.py | 1 + src/calibre/utils/opensearch/__init__.py | 4 - src/calibre/utils/opensearch/client.py | 39 - src/calibre/utils/opensearch/description.py | 135 +- src/calibre/utils/opensearch/osfeedparser.py | 2837 ----------------- src/calibre/utils/opensearch/query.py | 32 +- src/calibre/utils/opensearch/results.py | 131 - src/calibre/utils/opensearch/url.py | 14 +- 9 files changed, 144 insertions(+), 3130 deletions(-) delete mode 100644 src/calibre/utils/opensearch/client.py delete mode 100644 src/calibre/utils/opensearch/osfeedparser.py delete mode 100644 src/calibre/utils/opensearch/results.py diff --git a/src/calibre/gui2/store/opensearch_store.py b/src/calibre/gui2/store/opensearch_store.py index 8a25a80132..456b6a7461 100644 --- a/src/calibre/gui2/store/opensearch_store.py +++ b/src/calibre/gui2/store/opensearch_store.py @@ -8,14 +8,20 @@ __docformat__ = 'restructuredtext en' import mimetypes import urllib +from contextlib import closing + +from lxml import etree from PyQt4.Qt import QUrl +from calibre import browser from calibre.gui2 import open_url from calibre.gui2.store import StorePlugin from calibre.gui2.store.search_result import SearchResult from calibre.gui2.store.web_store_dialog import WebStoreDialog -from calibre.utils.opensearch import Client +#from calibre.utils.opensearch import Client +from calibre.utils.opensearch.description import Description +from calibre.utils.opensearch.query import Query class OpenSearchStore(StorePlugin): @@ -38,38 +44,51 @@ class OpenSearchStore(StorePlugin): if not hasattr(self, 'open_search_url'): return - client = Client(self.open_search_url) - results = client.search(urllib.quote_plus(query), max_results) + description = Description(self.open_search_url) + url_template = description.get_best_template() + if not url_template: + return + oquery = Query(url_template) + + # set up initial values + oquery.searchTerms = urllib.quote_plus(query) + oquery.count = max_results + url = oquery.url() counter = max_results - for r in results: - if counter <= 0: - break - counter -= 1 + br = browser() + with closing(br.open(url, timeout=timeout)) as f: + doc = etree.fromstring(f.read()) + for data in doc.xpath('//*[local-name() = "entry"]'): + if counter <= 0: + break - s = SearchResult() - - s.detail_item = r.get('id', '') - - links = r.get('links', None) - for l in links: - if l.get('rel', None): - if l['rel'] in ('http://opds-spec.org/thumbnail', 'http://opds-spec.org/image/thumbnail'): - s.cover_url = l.get('href', '') - elif l['rel'] == u'http://opds-spec.org/acquisition/buy': - s.detail_item = l.get('href', s.detail_item) - elif l['rel'] == u'http://opds-spec.org/acquisition': - mime = l.get('type', '') - if mime: - ext = mimetypes.guess_extension(mime) - if ext: - ext = ext[1:].upper() - s.downloads[ext] = l.get('href', '') + counter -= 1 + + s = SearchResult() + + s.detail_item = ''.join(data.xpath('./*[local-name() = "id"]/text()')) - s.formats = ', '.join(s.downloads.keys()) + for link in data.xpath('./*[local-name() = "link"]'): + rel = link.get('rel') + href = link.get('href') + type = link.get('type') + + if rel and href and type: + if rel in ('http://opds-spec.org/thumbnail', 'http://opds-spec.org/image/thumbnail'): + s.cover_url = href + elif rel == u'http://opds-spec.org/acquisition/buy': + s.detail_item = href + elif rel == u'http://opds-spec.org/acquisition': + if type: + ext = mimetypes.guess_extension(type) + if ext: + ext = ext[1:].upper() + s.downloads[ext] = href + s.formats = ', '.join(s.downloads.keys()) + + s.title = ' '.join(data.xpath('./*[local-name() = "title"]//text()')) + s.author = ', '.join(data.xpath('./*[local-name() = "author"]//*[local-name() = "name"]//text()')) + s.price = ' '.join(data.xpath('.//*[local-name() = "price"]//text()')) - s.title = r.get('title', '') - s.author = r.get('author', '') - s.price = r.get('price', '') - - yield s + yield s diff --git a/src/calibre/gui2/store/stores/archive_org_plugin.py b/src/calibre/gui2/store/stores/archive_org_plugin.py index 944b7aeba1..208b4c1aba 100644 --- a/src/calibre/gui2/store/stores/archive_org_plugin.py +++ b/src/calibre/gui2/store/stores/archive_org_plugin.py @@ -28,6 +28,7 @@ class ArchiveOrgStore(BasicStoreConfig, OpenSearchStore): s.price = '$0.00' s.drm = SearchResult.DRM_UNLOCKED yield s + ''' def get_details(self, search_result, timeout): br = browser() diff --git a/src/calibre/utils/opensearch/__init__.py b/src/calibre/utils/opensearch/__init__.py index f2d51febc4..e69de29bb2 100644 --- a/src/calibre/utils/opensearch/__init__.py +++ b/src/calibre/utils/opensearch/__init__.py @@ -1,4 +0,0 @@ -from description import Description -from query import Query -from client import Client -from results import Results diff --git a/src/calibre/utils/opensearch/client.py b/src/calibre/utils/opensearch/client.py deleted file mode 100644 index 434e921568..0000000000 --- a/src/calibre/utils/opensearch/client.py +++ /dev/null @@ -1,39 +0,0 @@ -from description import Description -from query import Query -from results import Results - -class Client: - - """This is the class you'll probably want to be using. You simply - pass the constructor the url for the service description file and - issue a search and get back results as an iterable Results object. - - The neat thing about a Results object is that it will seamlessly - handle fetching more results from the opensearch server when it can... - so you just need to iterate and can let the paging be taken care of - for you. - - from opensearch import Client - client = Client(description_url) - results = client.search("computer") - for result in results: - print result.title - """ - - def __init__(self, url, agent="python-opensearch "): - self.agent = agent - self.description = Description(url, self.agent) - - def search(self, search_terms, page_size=25): - """Perform a search and get back a results object - """ - url = self.description.get_best_template() - query = Query(url) - - # set up initial values - query.searchTerms = search_terms - query.count = page_size - - # run the results - return Results(query, agent=self.agent) - diff --git a/src/calibre/utils/opensearch/description.py b/src/calibre/utils/opensearch/description.py index 2909dbceb3..0b5afd8a7e 100644 --- a/src/calibre/utils/opensearch/description.py +++ b/src/calibre/utils/opensearch/description.py @@ -1,71 +1,95 @@ -from urllib2 import urlopen, Request -from xml.dom.minidom import parse -from url import URL +# -*- coding: utf-8 -*- -class Description: - """A class for representing OpenSearch Description files. - """ +from __future__ import (unicode_literals, division, absolute_import, print_function) - def __init__(self, url="", agent=""): - """The constructor which may pass an optional url to load from. +__license__ = 'GPL 3' +__copyright__ = ''' +2011, John Schember , +2006, Ed Summers +''' +__docformat__ = 'restructuredtext en' + +from contextlib import closing + +from lxml import etree + +from calibre import browser +from calibre.utils.opensearch.url import URL + +class Description(object): + ''' + A class for representing OpenSearch Description files. + ''' + + def __init__(self, url=""): + ''' + The constructor which may pass an optional url to load from. d = Description("http://www.example.com/description") - """ - self.agent = agent + ''' if url: self.load(url) def load(self, url): - """For loading up a description object from a url. Normally + ''' + For loading up a description object from a url. Normally you'll probably just want to pass a URL into the constructor. - """ - req = Request(url, headers={'User-Agent':self.agent}) - self.dom = parse(urlopen(req)) - + ''' + br = browser() + with closing(br.open(url, timeout=15)) as f: + doc = etree.fromstring(f.read()) + # version 1.1 has repeating Url elements - self.urls = self._get_urls() + self.urls = [] + for element in doc.xpath('//*[local-name() = "Url"]'): + template = element.get('template') + type = element.get('type') + if template and type: + url = URL() + url.template = template + url.type = type + self.urls.append(url) # this is version 1.0 specific - self.url = self._get_element_text('Url') - self.format = self._get_element_text('Format') + self.url = ''.join(doc.xpath('//*[local-name() = "Url"][1]//text()')) + self.format = ''.join(doc.xpath('//*[local-name() = "Format"][1]//text()')) - self.shortname = self._get_element_text('ShortName') - self.longname = self._get_element_text('LongName') - self.description = self._get_element_text('Description') - self.image = self._get_element_text('Image') - self.samplesearch = self._get_element_text('SampleSearch') - self.developer = self._get_element_text('Developer') - self.contact = self._get_element_text('Contact') - self.attribution = self._get_element_text('Attribution') - self.syndicationright = self._get_element_text('SyndicationRight') + self.shortname = ''.join(doc.xpath('//*[local-name() = "ShortName"][1]//text()')) + self.longname = ''.join(doc.xpath('//*[local-name() = "LongName"][1]//text()')) + self.description = ''.join(doc.xpath('//*[local-name() = "Description"][1]//text()')) + self.image = ''.join(doc.xpath('//*[local-name() = "Image"][1]//text()')) + self.sameplesearch = ''.join(doc.xpath('//*[local-name() = "SampleSearch"][1]//text()')) + self.developer = ''.join(doc.xpath('//*[local-name() = "Developer"][1]//text()')) + self.contact = ''.join(doc.xpath('/*[local-name() = "Contact"][1]//text()')) + self.attribution = ''.join(doc.xpath('//*[local-name() = "Attribution"][1]//text()')) + self.syndicationright = ''.join(doc.xpath('//*[local-name() = "SyndicationRight"][1]//text()')) - tag_text = self._get_element_text('Tags') + tag_text = ' '.join(doc.xpath('//*[local-name() = "Tags"]//text()')) if tag_text != None: - self.tags = tag_text.split(" ") + self.tags = tag_text.split(' ') - if self._get_element_text('AdultContent') == 'true': - self.adultcontent = True - else: - self.adultcontent = False + self.adultcontent = doc.xpath('boolean(//*[local-name() = "AdultContent" and contains(., "true")])') def get_url_by_type(self, type): - """Walks available urls and returns them by type. Only + ''' + Walks available urls and returns them by type. Only appropriate in opensearch v1.1 where there can be multiple query targets. Returns none if no such type is found. url = description.get_url_by_type('application/rss+xml') - """ + ''' for url in self.urls: if url.type == type: return url return None def get_best_template(self): - """OK, best is a value judgement, but so be it. You'll get + ''' + OK, best is a value judgement, but so be it. You'll get back either the atom, rss or first template available. This method handles the main difference between opensearch v1.0 and v1.1 - """ + ''' # version 1.0 if self.url: return self.url @@ -88,40 +112,3 @@ class Description: # out of luck return None - - - # these are internal methods for querying xml - - def _get_element_text(self, tag): - elements = self._get_elements(tag) - if not elements: - return None - return self._get_text(elements[0].childNodes) - - def _get_attribute_text(self, tag, attribute): - elements = self._get_elements(tag) - if not elements: - return '' - return elements[0].getAttribute('template') - - def _get_elements(self, tag): - return self.dom.getElementsByTagName(tag) - - def _get_text(self, nodes): - text = '' - for node in nodes: - if node.nodeType == node.TEXT_NODE: - text += node.data - return text.strip() - - def _get_urls(self): - urls = [] - for element in self._get_elements('Url'): - template = element.getAttribute('template') - type = element.getAttribute('type') - if template and type: - url = URL() - url.template = template - url.type = type - urls.append(url) - return urls diff --git a/src/calibre/utils/opensearch/osfeedparser.py b/src/calibre/utils/opensearch/osfeedparser.py deleted file mode 100644 index ed894cb572..0000000000 --- a/src/calibre/utils/opensearch/osfeedparser.py +++ /dev/null @@ -1,2837 +0,0 @@ -#!/usr/bin/env python -"""Universal feed parser - -Handles RSS 0.9x, RSS 1.0, RSS 2.0, CDF, Atom 0.3, and Atom 1.0 feeds - -Visit http://feedparser.org/ for the latest version -Visit http://feedparser.org/docs/ for the latest documentation - -Required: Python 2.1 or later -Recommended: Python 2.3 or later -Recommended: CJKCodecs and iconv_codec -""" - -__version__ = "4.0.2"# + "$Revision: 1.88 $"[11:15] + "-cvs" -__license__ = """Copyright (c) 2002-2005, Mark Pilgrim, All rights reserved. - -Redistribution and use in source and binary forms, with or without modification, -are permitted provided that the following conditions are met: - -* Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. -* Redistributions in binary form must reproduce the above copyright notice, - this list of conditions and the following disclaimer in the documentation - and/or other materials provided with the distribution. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS' -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE.""" -__author__ = "Mark Pilgrim " -__contributors__ = ["Jason Diamond ", - "John Beimler ", - "Fazal Majid ", - "Aaron Swartz ", - "Kevin Marks "] -_debug = 0 - -# HTTP "User-Agent" header to send to servers when downloading feeds. -# If you are embedding feedparser in a larger application, you should -# change this to your application name and URL. -# Changed by John Schember -from calibre import USER_AGENT -USER_AGENT = USER_AGENT - -# HTTP "Accept" header to send to servers when downloading feeds. If you don't -# want to send an Accept header, set this to None. -ACCEPT_HEADER = "application/atom+xml,application/rdf+xml,application/rss+xml,application/x-netcdf,application/xml;q=0.9,text/xml;q=0.2,*/*;q=0.1" - -# List of preferred XML parsers, by SAX driver name. These will be tried first, -# but if they're not installed, Python will keep searching through its own list -# of pre-installed parsers until it finds one that supports everything we need. -PREFERRED_XML_PARSERS = ["drv_libxml2"] - -# If you want feedparser to automatically run HTML markup through HTML Tidy, set -# this to 1. Requires mxTidy -# or utidylib . -TIDY_MARKUP = 0 - -# List of Python interfaces for HTML Tidy, in order of preference. Only useful -# if TIDY_MARKUP = 1 -PREFERRED_TIDY_INTERFACES = ["uTidy", "mxTidy"] - -# ---------- required modules (should come with any Python distribution) ---------- -import sgmllib, re, sys, copy, urlparse, time, rfc822, types, cgi -try: - from cStringIO import StringIO as _StringIO -except: - from StringIO import StringIO as _StringIO - -# ---------- optional modules (feedparser will work without these, but with reduced functionality) ---------- - -# gzip is included with most Python distributions, but may not be available if you compiled your own -try: - import gzip -except: - gzip = None -try: - import zlib -except: - zlib = None - -# timeoutsocket allows feedparser to time out rather than hang forever on ultra-slow servers. -# Python 2.3 now has this functionality available in the standard socket library, so under -# 2.3 or later you don't need to install anything. In fact, under Python 2.4, timeoutsocket -# write all sorts of crazy errors to stderr while running my unit tests, so it's probably -# outlived its usefulness. -import socket -if hasattr(socket, 'setdefaulttimeout'): - socket.setdefaulttimeout(20) -else: - try: - import timeoutsocket # http://www.timo-tasi.org/python/timeoutsocket.py - timeoutsocket.setDefaultSocketTimeout(20) - except ImportError: - pass -import urllib, urllib2 - -# If a real XML parser is available, feedparser will attempt to use it. feedparser has -# been tested with the built-in SAX parser, PyXML, and libxml2. On platforms where the -# Python distribution does not come with an XML parser (such as Mac OS X 10.2 and some -# versions of FreeBSD), feedparser will quietly fall back on regex-based parsing. -try: - import xml.sax - xml.sax.make_parser(PREFERRED_XML_PARSERS) # test for valid parsers - from xml.sax.saxutils import escape as _xmlescape - _XML_AVAILABLE = 1 -except: - _XML_AVAILABLE = 0 - def _xmlescape(data): - data = data.replace('&', '&') - data = data.replace('>', '>') - data = data.replace('<', '<') - return data - -# base64 support for Atom feeds that contain embedded binary data -try: - import base64, binascii -except: - base64 = binascii = None - -# cjkcodecs and iconv_codec provide support for more character encodings. -# Both are available from http://cjkpython.i18n.org/ -try: - import cjkcodecs.aliases -except: - pass -try: - import iconv_codec -except: - pass - -# ---------- don't touch these ---------- -class ThingsNobodyCaresAboutButMe(Exception): pass -class CharacterEncodingOverride(ThingsNobodyCaresAboutButMe): pass -class CharacterEncodingUnknown(ThingsNobodyCaresAboutButMe): pass -class NonXMLContentType(ThingsNobodyCaresAboutButMe): pass -class UndeclaredNamespace(Exception): pass - -sgmllib.tagfind = re.compile('[a-zA-Z][-_.:a-zA-Z0-9]*') -sgmllib.special = re.compile('' % (tag, ''.join([' %s="%s"' % t for t in attrs])), escape=0) - - # match namespaces - if tag.find(':') <> -1: - prefix, suffix = tag.split(':', 1) - else: - prefix, suffix = '', tag - prefix = self.namespacemap.get(prefix, prefix) - if prefix: - prefix = prefix + '_' - - # special hack for better tracking of empty textinput/image elements in illformed feeds - if (not prefix) and tag not in ('title', 'link', 'description', 'name'): - self.intextinput = 0 - if (not prefix) and tag not in ('title', 'link', 'description', 'url', 'href', 'width', 'height'): - self.inimage = 0 - - # call special handler (if defined) or default handler - methodname = '_start_' + prefix + suffix - try: - method = getattr(self, methodname) - return method(attrsD) - except AttributeError: - return self.push(prefix + suffix, 1) - - def unknown_endtag(self, tag): - if _debug: sys.stderr.write('end %s\n' % tag) - # match namespaces - if tag.find(':') <> -1: - prefix, suffix = tag.split(':', 1) - else: - prefix, suffix = '', tag - prefix = self.namespacemap.get(prefix, prefix) - if prefix: - prefix = prefix + '_' - - # call special handler (if defined) or default handler - methodname = '_end_' + prefix + suffix - try: - method = getattr(self, methodname) - method() - except AttributeError: - self.pop(prefix + suffix) - - # track inline content - if self.incontent and self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'): - # element declared itself as escaped markup, but it isn't really - self.contentparams['type'] = 'application/xhtml+xml' - if self.incontent and self.contentparams.get('type') == 'application/xhtml+xml': - tag = tag.split(':')[-1] - self.handle_data('' % tag, escape=0) - - # track xml:base and xml:lang going out of scope - if self.basestack: - self.basestack.pop() - if self.basestack and self.basestack[-1]: - self.baseuri = self.basestack[-1] - if self.langstack: - self.langstack.pop() - if self.langstack: # and (self.langstack[-1] is not None): - self.lang = self.langstack[-1] - - def handle_charref(self, ref): - # called for each character reference, e.g. for ' ', ref will be '160' - if not self.elementstack: return - ref = ref.lower() - if ref in ('34', '38', '39', '60', '62', 'x22', 'x26', 'x27', 'x3c', 'x3e'): - text = '&#%s;' % ref - else: - if ref[0] == 'x': - c = int(ref[1:], 16) - else: - c = int(ref) - text = unichr(c).encode('utf-8') - self.elementstack[-1][2].append(text) - - def handle_entityref(self, ref): - # called for each entity reference, e.g. for '©', ref will be 'copy' - if not self.elementstack: return - if _debug: sys.stderr.write('entering handle_entityref with %s\n' % ref) - if ref in ('lt', 'gt', 'quot', 'amp', 'apos'): - text = '&%s;' % ref - else: - # entity resolution graciously donated by Aaron Swartz - def name2cp(k): - import htmlentitydefs - if hasattr(htmlentitydefs, 'name2codepoint'): # requires Python 2.3 - return htmlentitydefs.name2codepoint[k] - k = htmlentitydefs.entitydefs[k] - if k.startswith('&#') and k.endswith(';'): - return int(k[2:-1]) # not in latin-1 - return ord(k) - try: name2cp(ref) - except KeyError: text = '&%s;' % ref - else: text = unichr(name2cp(ref)).encode('utf-8') - self.elementstack[-1][2].append(text) - - def handle_data(self, text, escape=1): - # called for each block of plain text, i.e. outside of any tag and - # not containing any character or entity references - if not self.elementstack: return - if escape and self.contentparams.get('type') == 'application/xhtml+xml': - text = _xmlescape(text) - self.elementstack[-1][2].append(text) - - def handle_comment(self, text): - # called for each comment, e.g. - pass - - def handle_pi(self, text): - # called for each processing instruction, e.g. - pass - - def handle_decl(self, text): - pass - - def parse_declaration(self, i): - # override internal declaration handler to handle CDATA blocks - if _debug: sys.stderr.write('entering parse_declaration\n') - if self.rawdata[i:i+9] == '', i) - if k == -1: k = len(self.rawdata) - self.handle_data(_xmlescape(self.rawdata[i+9:k]), 0) - return k+3 - else: - k = self.rawdata.find('>', i) - return k+1 - - def mapContentType(self, contentType): - contentType = contentType.lower() - if contentType == 'text': - contentType = 'text/plain' - elif contentType == 'html': - contentType = 'text/html' - elif contentType == 'xhtml': - contentType = 'application/xhtml+xml' - return contentType - - def trackNamespace(self, prefix, uri): - loweruri = uri.lower() - if (prefix, loweruri) == (None, 'http://my.netscape.com/rdf/simple/0.9/') and not self.version: - self.version = 'rss090' - if loweruri == 'http://purl.org/rss/1.0/' and not self.version: - self.version = 'rss10' - if loweruri == 'http://www.w3.org/2005/atom' and not self.version: - self.version = 'atom10' - if loweruri.find('backend.userland.com/rss') <> -1: - # match any backend.userland.com namespace - uri = 'http://backend.userland.com/rss' - loweruri = uri - if self._matchnamespaces.has_key(loweruri): - self.namespacemap[prefix] = self._matchnamespaces[loweruri] - self.namespacesInUse[self._matchnamespaces[loweruri]] = uri - else: - self.namespacesInUse[prefix or ''] = uri - - def resolveURI(self, uri): - return _urljoin(self.baseuri or '', uri) - - def decodeEntities(self, element, data): - return data - - def push(self, element, expectingText): - self.elementstack.append([element, expectingText, []]) - - def pop(self, element, stripWhitespace=1): - if not self.elementstack: return - if self.elementstack[-1][0] != element: return - - element, expectingText, pieces = self.elementstack.pop() - output = ''.join(pieces) - if stripWhitespace: - output = output.strip() - if not expectingText: return output - - # decode base64 content - if base64 and self.contentparams.get('base64', 0): - try: - output = base64.decodestring(output) - except binascii.Error: - pass - except binascii.Incomplete: - pass - - # resolve relative URIs - if (element in self.can_be_relative_uri) and output: - output = self.resolveURI(output) - - # decode entities within embedded markup - if not self.contentparams.get('base64', 0): - output = self.decodeEntities(element, output) - - # remove temporary cruft from contentparams - try: - del self.contentparams['mode'] - except KeyError: - pass - try: - del self.contentparams['base64'] - except KeyError: - pass - - # resolve relative URIs within embedded markup - if self.mapContentType(self.contentparams.get('type', 'text/html')) in self.html_types: - if element in self.can_contain_relative_uris: - output = _resolveRelativeURIs(output, self.baseuri, self.encoding) - - # sanitize embedded markup - if self.mapContentType(self.contentparams.get('type', 'text/html')) in self.html_types: - if element in self.can_contain_dangerous_markup: - output = _sanitizeHTML(output, self.encoding) - - if self.encoding and type(output) != type(u''): - try: - output = unicode(output, self.encoding) - except: - pass - - # categories/tags/keywords/whatever are handled in _end_category - if element == 'category': - return output - - # store output in appropriate place(s) - if self.inentry and not self.insource: - if element == 'content': - self.entries[-1].setdefault(element, []) - contentparams = copy.deepcopy(self.contentparams) - contentparams['value'] = output - self.entries[-1][element].append(contentparams) - elif element == 'link': - self.entries[-1][element] = output - if output: - self.entries[-1]['links'][-1]['href'] = output - else: - if element == 'description': - element = 'summary' - self.entries[-1][element] = output - if self.incontent: - contentparams = copy.deepcopy(self.contentparams) - contentparams['value'] = output - self.entries[-1][element + '_detail'] = contentparams - elif (self.infeed or self.insource) and (not self.intextinput) and (not self.inimage): - context = self._getContext() - if element == 'description': - element = 'subtitle' - context[element] = output - if element == 'link': - context['links'][-1]['href'] = output - elif self.incontent: - contentparams = copy.deepcopy(self.contentparams) - contentparams['value'] = output - context[element + '_detail'] = contentparams - return output - - def pushContent(self, tag, attrsD, defaultContentType, expectingText): - self.incontent += 1 - self.contentparams = FeedParserDict({ - 'type': self.mapContentType(attrsD.get('type', defaultContentType)), - 'language': self.lang, - 'base': self.baseuri}) - self.contentparams['base64'] = self._isBase64(attrsD, self.contentparams) - self.push(tag, expectingText) - - def popContent(self, tag): - value = self.pop(tag) - self.incontent -= 1 - self.contentparams.clear() - return value - - def _mapToStandardPrefix(self, name): - colonpos = name.find(':') - if colonpos <> -1: - prefix = name[:colonpos] - suffix = name[colonpos+1:] - prefix = self.namespacemap.get(prefix, prefix) - name = prefix + ':' + suffix - return name - - def _getAttribute(self, attrsD, name): - return attrsD.get(self._mapToStandardPrefix(name)) - - def _isBase64(self, attrsD, contentparams): - if attrsD.get('mode', '') == 'base64': - return 1 - if self.contentparams['type'].startswith('text/'): - return 0 - if self.contentparams['type'].endswith('+xml'): - return 0 - if self.contentparams['type'].endswith('/xml'): - return 0 - return 1 - - def _itsAnHrefDamnIt(self, attrsD): - href = attrsD.get('url', attrsD.get('uri', attrsD.get('href', None))) - if href: - try: - del attrsD['url'] - except KeyError: - pass - try: - del attrsD['uri'] - except KeyError: - pass - attrsD['href'] = href - return attrsD - - def _save(self, key, value): - context = self._getContext() - context.setdefault(key, value) - - def _start_rss(self, attrsD): - versionmap = {'0.91': 'rss091u', - '0.92': 'rss092', - '0.93': 'rss093', - '0.94': 'rss094'} - if not self.version: - attr_version = attrsD.get('version', '') - version = versionmap.get(attr_version) - if version: - self.version = version - elif attr_version.startswith('2.'): - self.version = 'rss20' - else: - self.version = 'rss' - - def _start_dlhottitles(self, attrsD): - self.version = 'hotrss' - - def _start_channel(self, attrsD): - self.infeed = 1 - self._cdf_common(attrsD) - _start_feedinfo = _start_channel - - def _cdf_common(self, attrsD): - if attrsD.has_key('lastmod'): - self._start_modified({}) - self.elementstack[-1][-1] = attrsD['lastmod'] - self._end_modified() - if attrsD.has_key('href'): - self._start_link({}) - self.elementstack[-1][-1] = attrsD['href'] - self._end_link() - - def _start_feed(self, attrsD): - self.infeed = 1 - versionmap = {'0.1': 'atom01', - '0.2': 'atom02', - '0.3': 'atom03'} - if not self.version: - attr_version = attrsD.get('version') - version = versionmap.get(attr_version) - if version: - self.version = version - else: - self.version = 'atom' - - def _end_channel(self): - self.infeed = 0 - _end_feed = _end_channel - - def _start_image(self, attrsD): - self.inimage = 1 - self.push('image', 0) - context = self._getContext() - context.setdefault('image', FeedParserDict()) - - def _end_image(self): - self.pop('image') - self.inimage = 0 - - def _start_textinput(self, attrsD): - self.intextinput = 1 - self.push('textinput', 0) - context = self._getContext() - context.setdefault('textinput', FeedParserDict()) - _start_textInput = _start_textinput - - def _end_textinput(self): - self.pop('textinput') - self.intextinput = 0 - _end_textInput = _end_textinput - - def _start_author(self, attrsD): - self.inauthor = 1 - self.push('author', 1) - _start_managingeditor = _start_author - _start_dc_author = _start_author - _start_dc_creator = _start_author - _start_itunes_author = _start_author - - def _end_author(self): - self.pop('author') - self.inauthor = 0 - self._sync_author_detail() - _end_managingeditor = _end_author - _end_dc_author = _end_author - _end_dc_creator = _end_author - _end_itunes_author = _end_author - - def _start_itunes_owner(self, attrsD): - self.inpublisher = 1 - self.push('publisher', 0) - - def _end_itunes_owner(self): - self.pop('publisher') - self.inpublisher = 0 - self._sync_author_detail('publisher') - - def _start_contributor(self, attrsD): - self.incontributor = 1 - context = self._getContext() - context.setdefault('contributors', []) - context['contributors'].append(FeedParserDict()) - self.push('contributor', 0) - - def _end_contributor(self): - self.pop('contributor') - self.incontributor = 0 - - def _start_dc_contributor(self, attrsD): - self.incontributor = 1 - context = self._getContext() - context.setdefault('contributors', []) - context['contributors'].append(FeedParserDict()) - self.push('name', 0) - - def _end_dc_contributor(self): - self._end_name() - self.incontributor = 0 - - def _start_name(self, attrsD): - self.push('name', 0) - _start_itunes_name = _start_name - - def _end_name(self): - value = self.pop('name') - if self.inpublisher: - self._save_author('name', value, 'publisher') - elif self.inauthor: - self._save_author('name', value) - elif self.incontributor: - self._save_contributor('name', value) - elif self.intextinput: - context = self._getContext() - context['textinput']['name'] = value - _end_itunes_name = _end_name - - def _start_width(self, attrsD): - self.push('width', 0) - - def _end_width(self): - value = self.pop('width') - try: - value = int(value) - except: - value = 0 - if self.inimage: - context = self._getContext() - context['image']['width'] = value - - def _start_height(self, attrsD): - self.push('height', 0) - - def _end_height(self): - value = self.pop('height') - try: - value = int(value) - except: - value = 0 - if self.inimage: - context = self._getContext() - context['image']['height'] = value - - def _start_url(self, attrsD): - self.push('href', 1) - _start_homepage = _start_url - _start_uri = _start_url - - def _end_url(self): - value = self.pop('href') - if self.inauthor: - self._save_author('href', value) - elif self.incontributor: - self._save_contributor('href', value) - elif self.inimage: - context = self._getContext() - context['image']['href'] = value - elif self.intextinput: - context = self._getContext() - context['textinput']['link'] = value - _end_homepage = _end_url - _end_uri = _end_url - - def _start_email(self, attrsD): - self.push('email', 0) - _start_itunes_email = _start_email - - def _end_email(self): - value = self.pop('email') - if self.inpublisher: - self._save_author('email', value, 'publisher') - elif self.inauthor: - self._save_author('email', value) - elif self.incontributor: - self._save_contributor('email', value) - _end_itunes_email = _end_email - - def _getContext(self): - if self.insource: - context = self.sourcedata - elif self.inentry: - context = self.entries[-1] - else: - context = self.feeddata - return context - - def _save_author(self, key, value, prefix='author'): - context = self._getContext() - context.setdefault(prefix + '_detail', FeedParserDict()) - context[prefix + '_detail'][key] = value - self._sync_author_detail() - - def _save_contributor(self, key, value): - context = self._getContext() - context.setdefault('contributors', [FeedParserDict()]) - context['contributors'][-1][key] = value - - def _sync_author_detail(self, key='author'): - context = self._getContext() - detail = context.get('%s_detail' % key) - if detail: - name = detail.get('name') - email = detail.get('email') - if name and email: - context[key] = '%s (%s)' % (name, email) - elif name: - context[key] = name - elif email: - context[key] = email - else: - author = context.get(key) - if not author: return - emailmatch = re.search(r'''(([a-zA-Z0-9\_\-\.\+]+)@((\[[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.)|(([a-zA-Z0-9\-]+\.)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\]?))''', author) - if not emailmatch: return - email = emailmatch.group(0) - # probably a better way to do the following, but it passes all the tests - author = author.replace(email, '') - author = author.replace('()', '') - author = author.strip() - if author and (author[0] == '('): - author = author[1:] - if author and (author[-1] == ')'): - author = author[:-1] - author = author.strip() - context.setdefault('%s_detail' % key, FeedParserDict()) - context['%s_detail' % key]['name'] = author - context['%s_detail' % key]['email'] = email - - def _start_subtitle(self, attrsD): - self.pushContent('subtitle', attrsD, 'text/plain', 1) - _start_tagline = _start_subtitle - _start_itunes_subtitle = _start_subtitle - - def _end_subtitle(self): - self.popContent('subtitle') - _end_tagline = _end_subtitle - _end_itunes_subtitle = _end_subtitle - - def _start_rights(self, attrsD): - self.pushContent('rights', attrsD, 'text/plain', 1) - _start_dc_rights = _start_rights - _start_copyright = _start_rights - - def _end_rights(self): - self.popContent('rights') - _end_dc_rights = _end_rights - _end_copyright = _end_rights - - def _start_item(self, attrsD): - self.entries.append(FeedParserDict()) - self.push('item', 0) - self.inentry = 1 - self.guidislink = 0 - id = self._getAttribute(attrsD, 'rdf:about') - if id: - context = self._getContext() - context['id'] = id - self._cdf_common(attrsD) - _start_entry = _start_item - _start_product = _start_item - - def _end_item(self): - self.pop('item') - self.inentry = 0 - _end_entry = _end_item - - def _start_dc_language(self, attrsD): - self.push('language', 1) - _start_language = _start_dc_language - - def _end_dc_language(self): - self.lang = self.pop('language') - _end_language = _end_dc_language - - def _start_dc_publisher(self, attrsD): - self.push('publisher', 1) - _start_webmaster = _start_dc_publisher - - def _end_dc_publisher(self): - self.pop('publisher') - self._sync_author_detail('publisher') - _end_webmaster = _end_dc_publisher - - def _start_published(self, attrsD): - self.push('published', 1) - _start_dcterms_issued = _start_published - _start_issued = _start_published - - def _end_published(self): - value = self.pop('published') - self._save('published_parsed', _parse_date(value)) - _end_dcterms_issued = _end_published - _end_issued = _end_published - - def _start_updated(self, attrsD): - self.push('updated', 1) - _start_modified = _start_updated - _start_dcterms_modified = _start_updated - _start_pubdate = _start_updated - _start_dc_date = _start_updated - - def _end_updated(self): - value = self.pop('updated') - parsed_value = _parse_date(value) - self._save('updated_parsed', parsed_value) - _end_modified = _end_updated - _end_dcterms_modified = _end_updated - _end_pubdate = _end_updated - _end_dc_date = _end_updated - - def _start_created(self, attrsD): - self.push('created', 1) - _start_dcterms_created = _start_created - - def _end_created(self): - value = self.pop('created') - self._save('created_parsed', _parse_date(value)) - _end_dcterms_created = _end_created - - def _start_expirationdate(self, attrsD): - self.push('expired', 1) - - def _end_expirationdate(self): - self._save('expired_parsed', _parse_date(self.pop('expired'))) - - def _start_cc_license(self, attrsD): - self.push('license', 1) - value = self._getAttribute(attrsD, 'rdf:resource') - if value: - self.elementstack[-1][2].append(value) - self.pop('license') - - def _start_creativecommons_license(self, attrsD): - self.push('license', 1) - - def _end_creativecommons_license(self): - self.pop('license') - - def _addTag(self, term, scheme, label): - context = self._getContext() - tags = context.setdefault('tags', []) - if (not term) and (not scheme) and (not label): return - value = FeedParserDict({'term': term, 'scheme': scheme, 'label': label}) - if value not in tags: - tags.append(FeedParserDict({'term': term, 'scheme': scheme, 'label': label})) - - def _start_category(self, attrsD): - if _debug: sys.stderr.write('entering _start_category with %s\n' % repr(attrsD)) - term = attrsD.get('term') - scheme = attrsD.get('scheme', attrsD.get('domain')) - label = attrsD.get('label') - self._addTag(term, scheme, label) - self.push('category', 1) - _start_dc_subject = _start_category - _start_keywords = _start_category - - def _end_itunes_keywords(self): - for term in self.pop('itunes_keywords').split(): - self._addTag(term, 'http://www.itunes.com/', None) - - def _start_itunes_category(self, attrsD): - self._addTag(attrsD.get('text'), 'http://www.itunes.com/', None) - self.push('category', 1) - - def _end_category(self): - value = self.pop('category') - if not value: return - context = self._getContext() - tags = context['tags'] - if value and len(tags) and not tags[-1]['term']: - tags[-1]['term'] = value - else: - self._addTag(value, None, None) - _end_dc_subject = _end_category - _end_keywords = _end_category - _end_itunes_category = _end_category - - def _start_cloud(self, attrsD): - self._getContext()['cloud'] = FeedParserDict(attrsD) - - def _start_link(self, attrsD): - attrsD.setdefault('rel', 'alternate') - attrsD.setdefault('type', 'text/html') - attrsD = self._itsAnHrefDamnIt(attrsD) - if attrsD.has_key('href'): - attrsD['href'] = self.resolveURI(attrsD['href']) - expectingText = self.infeed or self.inentry or self.insource - context = self._getContext() - context.setdefault('links', []) - context['links'].append(FeedParserDict(attrsD)) - if attrsD['rel'] == 'enclosure': - self._start_enclosure(attrsD) - if attrsD.has_key('href'): - expectingText = 0 - if (attrsD.get('rel') == 'alternate') and (self.mapContentType(attrsD.get('type')) in self.html_types): - context['link'] = attrsD['href'] - else: - self.push('link', expectingText) - _start_producturl = _start_link - - def _end_link(self): - value = self.pop('link') - context = self._getContext() - if self.intextinput: - context['textinput']['link'] = value - if self.inimage: - context['image']['link'] = value - _end_producturl = _end_link - - def _start_guid(self, attrsD): - self.guidislink = (attrsD.get('ispermalink', 'true') == 'true') - self.push('id', 1) - - def _end_guid(self): - value = self.pop('id') - self._save('guidislink', self.guidislink and not self._getContext().has_key('link')) - if self.guidislink: - # guid acts as link, but only if 'ispermalink' is not present or is 'true', - # and only if the item doesn't already have a link element - self._save('link', value) - - def _start_title(self, attrsD): - self.pushContent('title', attrsD, 'text/plain', self.infeed or self.inentry or self.insource) - _start_dc_title = _start_title - _start_media_title = _start_title - - def _end_title(self): - value = self.popContent('title') - context = self._getContext() - if self.intextinput: - context['textinput']['title'] = value - elif self.inimage: - context['image']['title'] = value - _end_dc_title = _end_title - _end_media_title = _end_title - - def _start_description(self, attrsD): - context = self._getContext() - if context.has_key('summary'): - self._summaryKey = 'content' - self._start_content(attrsD) - else: - self.pushContent('description', attrsD, 'text/html', self.infeed or self.inentry or self.insource) - - def _start_abstract(self, attrsD): - self.pushContent('description', attrsD, 'text/plain', self.infeed or self.inentry or self.insource) - - def _end_description(self): - if self._summaryKey == 'content': - self._end_content() - else: - value = self.popContent('description') - context = self._getContext() - if self.intextinput: - context['textinput']['description'] = value - elif self.inimage: - context['image']['description'] = value - self._summaryKey = None - _end_abstract = _end_description - - def _start_info(self, attrsD): - self.pushContent('info', attrsD, 'text/plain', 1) - _start_feedburner_browserfriendly = _start_info - - def _end_info(self): - self.popContent('info') - _end_feedburner_browserfriendly = _end_info - - def _start_generator(self, attrsD): - if attrsD: - attrsD = self._itsAnHrefDamnIt(attrsD) - if attrsD.has_key('href'): - attrsD['href'] = self.resolveURI(attrsD['href']) - self._getContext()['generator_detail'] = FeedParserDict(attrsD) - self.push('generator', 1) - - def _end_generator(self): - value = self.pop('generator') - context = self._getContext() - if context.has_key('generator_detail'): - context['generator_detail']['name'] = value - - def _start_admin_generatoragent(self, attrsD): - self.push('generator', 1) - value = self._getAttribute(attrsD, 'rdf:resource') - if value: - self.elementstack[-1][2].append(value) - self.pop('generator') - self._getContext()['generator_detail'] = FeedParserDict({'href': value}) - - def _start_admin_errorreportsto(self, attrsD): - self.push('errorreportsto', 1) - value = self._getAttribute(attrsD, 'rdf:resource') - if value: - self.elementstack[-1][2].append(value) - self.pop('errorreportsto') - - def _start_summary(self, attrsD): - context = self._getContext() - if context.has_key('summary'): - self._summaryKey = 'content' - self._start_content(attrsD) - else: - self._summaryKey = 'summary' - self.pushContent(self._summaryKey, attrsD, 'text/plain', 1) - _start_itunes_summary = _start_summary - - def _end_summary(self): - if self._summaryKey == 'content': - self._end_content() - else: - self.popContent(self._summaryKey or 'summary') - self._summaryKey = None - _end_itunes_summary = _end_summary - - def _start_enclosure(self, attrsD): - attrsD = self._itsAnHrefDamnIt(attrsD) - self._getContext().setdefault('enclosures', []).append(FeedParserDict(attrsD)) - href = attrsD.get('href') - if href: - context = self._getContext() - if not context.get('id'): - context['id'] = href - - def _start_source(self, attrsD): - self.insource = 1 - - def _end_source(self): - self.insource = 0 - self._getContext()['source'] = copy.deepcopy(self.sourcedata) - self.sourcedata.clear() - - def _start_content(self, attrsD): - self.pushContent('content', attrsD, 'text/plain', 1) - src = attrsD.get('src') - if src: - self.contentparams['src'] = src - self.push('content', 1) - - def _start_prodlink(self, attrsD): - self.pushContent('content', attrsD, 'text/html', 1) - - def _start_body(self, attrsD): - self.pushContent('content', attrsD, 'application/xhtml+xml', 1) - _start_xhtml_body = _start_body - - def _start_content_encoded(self, attrsD): - self.pushContent('content', attrsD, 'text/html', 1) - _start_fullitem = _start_content_encoded - - def _end_content(self): - copyToDescription = self.mapContentType(self.contentparams.get('type')) in (['text/plain'] + self.html_types) - value = self.popContent('content') - if copyToDescription: - self._save('description', value) - _end_body = _end_content - _end_xhtml_body = _end_content - _end_content_encoded = _end_content - _end_fullitem = _end_content - _end_prodlink = _end_content - - def _start_itunes_image(self, attrsD): - self.push('itunes_image', 0) - self._getContext()['image'] = FeedParserDict({'href': attrsD.get('href')}) - _start_itunes_link = _start_itunes_image - - def _end_itunes_block(self): - value = self.pop('itunes_block', 0) - self._getContext()['itunes_block'] = (value == 'yes') and 1 or 0 - - def _end_itunes_explicit(self): - value = self.pop('itunes_explicit', 0) - self._getContext()['itunes_explicit'] = (value == 'yes') and 1 or 0 - -if _XML_AVAILABLE: - class _StrictFeedParser(_FeedParserMixin, xml.sax.handler.ContentHandler): - def __init__(self, baseuri, baselang, encoding): - if _debug: sys.stderr.write('trying StrictFeedParser\n') - xml.sax.handler.ContentHandler.__init__(self) - _FeedParserMixin.__init__(self, baseuri, baselang, encoding) - self.bozo = 0 - self.exc = None - - def startPrefixMapping(self, prefix, uri): - self.trackNamespace(prefix, uri) - - def startElementNS(self, name, qname, attrs): - namespace, localname = name - lowernamespace = str(namespace or '').lower() - if lowernamespace.find('backend.userland.com/rss') <> -1: - # match any backend.userland.com namespace - namespace = 'http://backend.userland.com/rss' - lowernamespace = namespace - if qname and qname.find(':') > 0: - givenprefix = qname.split(':')[0] - else: - givenprefix = None - prefix = self._matchnamespaces.get(lowernamespace, givenprefix) - if givenprefix and (prefix == None or (prefix == '' and lowernamespace == '')) and not self.namespacesInUse.has_key(givenprefix): - raise UndeclaredNamespace, "'%s' is not associated with a namespace" % givenprefix - if prefix: - localname = prefix + ':' + localname - localname = str(localname).lower() - if _debug: sys.stderr.write('startElementNS: qname = %s, namespace = %s, givenprefix = %s, prefix = %s, attrs = %s, localname = %s\n' % (qname, namespace, givenprefix, prefix, attrs.items(), localname)) - - # qname implementation is horribly broken in Python 2.1 (it - # doesn't report any), and slightly broken in Python 2.2 (it - # doesn't report the xml: namespace). So we match up namespaces - # with a known list first, and then possibly override them with - # the qnames the SAX parser gives us (if indeed it gives us any - # at all). Thanks to MatejC for helping me test this and - # tirelessly telling me that it didn't work yet. - attrsD = {} - for (namespace, attrlocalname), attrvalue in attrs._attrs.items(): - lowernamespace = (namespace or '').lower() - prefix = self._matchnamespaces.get(lowernamespace, '') - if prefix: - attrlocalname = prefix + ':' + attrlocalname - attrsD[str(attrlocalname).lower()] = attrvalue - for qname in attrs.getQNames(): - attrsD[str(qname).lower()] = attrs.getValueByQName(qname) - self.unknown_starttag(localname, attrsD.items()) - - def characters(self, text): - self.handle_data(text) - - def endElementNS(self, name, qname): - namespace, localname = name - lowernamespace = str(namespace or '').lower() - if qname and qname.find(':') > 0: - givenprefix = qname.split(':')[0] - else: - givenprefix = '' - prefix = self._matchnamespaces.get(lowernamespace, givenprefix) - if prefix: - localname = prefix + ':' + localname - localname = str(localname).lower() - self.unknown_endtag(localname) - - def error(self, exc): - self.bozo = 1 - self.exc = exc - - def fatalError(self, exc): - self.error(exc) - raise exc - -class _BaseHTMLProcessor(sgmllib.SGMLParser): - elements_no_end_tag = ['area', 'base', 'basefont', 'br', 'col', 'frame', 'hr', - 'img', 'input', 'isindex', 'link', 'meta', 'param'] - - def __init__(self, encoding): - self.encoding = encoding - if _debug: sys.stderr.write('entering BaseHTMLProcessor, encoding=%s\n' % self.encoding) - sgmllib.SGMLParser.__init__(self) - - def reset(self): - self.pieces = [] - sgmllib.SGMLParser.reset(self) - - def _shorttag_replace(self, match): - tag = match.group(1) - if tag in self.elements_no_end_tag: - return '<' + tag + ' />' - else: - return '<' + tag + '>' - - def feed(self, data): - data = re.compile(r'', self._shorttag_replace, data) - data = data.replace(''', "'") - data = data.replace('"', '"') - if self.encoding and type(data) == type(u''): - data = data.encode(self.encoding) - sgmllib.SGMLParser.feed(self, data) - - def normalize_attrs(self, attrs): - # utility method to be called by descendants - attrs = [(k.lower(), v) for k, v in attrs] - attrs = [(k, k in ('rel', 'type') and v.lower() or v) for k, v in attrs] - return attrs - - def unknown_starttag(self, tag, attrs): - # called for each start tag - # attrs is a list of (attr, value) tuples - # e.g. for 
, tag='pre', attrs=[('class', 'screen')]
-        if _debug: sys.stderr.write('_BaseHTMLProcessor, unknown_starttag, tag=%s\n' % tag)
-        uattrs = []
-        # thanks to Kevin Marks for this breathtaking hack to deal with (valid) high-bit attribute values in UTF-8 feeds
-        for key, value in attrs:
-            if type(value) != type(u''):
-                value = unicode(value, self.encoding)
-            uattrs.append((unicode(key, self.encoding), value))
-        strattrs = u''.join([u' %s="%s"' % (key, value) for key, value in uattrs]).encode(self.encoding)
-        if tag in self.elements_no_end_tag:
-            self.pieces.append('<%(tag)s%(strattrs)s />' % locals())
-        else:
-            self.pieces.append('<%(tag)s%(strattrs)s>' % locals())
-
-    def unknown_endtag(self, tag):
-        # called for each end tag, e.g. for
, tag will be 'pre' - # Reconstruct the original end tag. - if tag not in self.elements_no_end_tag: - self.pieces.append("" % locals()) - - def handle_charref(self, ref): - # called for each character reference, e.g. for ' ', ref will be '160' - # Reconstruct the original character reference. - self.pieces.append('&#%(ref)s;' % locals()) - - def handle_entityref(self, ref): - # called for each entity reference, e.g. for '©', ref will be 'copy' - # Reconstruct the original entity reference. - self.pieces.append('&%(ref)s;' % locals()) - - def handle_data(self, text): - # called for each block of plain text, i.e. outside of any tag and - # not containing any character or entity references - # Store the original text verbatim. - if _debug: sys.stderr.write('_BaseHTMLProcessor, handle_text, text=%s\n' % text) - self.pieces.append(text) - - def handle_comment(self, text): - # called for each HTML comment, e.g. - # Reconstruct the original comment. - self.pieces.append('' % locals()) - - def handle_pi(self, text): - # called for each processing instruction, e.g. - # Reconstruct original processing instruction. - self.pieces.append('' % locals()) - - def handle_decl(self, text): - # called for the DOCTYPE, if present, e.g. - # - # Reconstruct original DOCTYPE - self.pieces.append('' % locals()) - - _new_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9:]*\s*').match - def _scan_name(self, i, declstartpos): - rawdata = self.rawdata - n = len(rawdata) - if i == n: - return None, -1 - m = self._new_declname_match(rawdata, i) - if m: - s = m.group() - name = s.strip() - if (i + len(s)) == n: - return None, -1 # end of buffer - return name.lower(), m.end() - else: - self.handle_data(rawdata) -# self.updatepos(declstartpos, i) - return None, -1 - - def output(self): - '''Return processed HTML as a single string''' - return ''.join([str(p) for p in self.pieces]) - -class _LooseFeedParser(_FeedParserMixin, _BaseHTMLProcessor): - def __init__(self, baseuri, baselang, encoding): - sgmllib.SGMLParser.__init__(self) - _FeedParserMixin.__init__(self, baseuri, baselang, encoding) - - def decodeEntities(self, element, data): - data = data.replace('<', '<') - data = data.replace('<', '<') - data = data.replace('>', '>') - data = data.replace('>', '>') - data = data.replace('&', '&') - data = data.replace('&', '&') - data = data.replace('"', '"') - data = data.replace('"', '"') - data = data.replace(''', ''') - data = data.replace(''', ''') - if self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'): - data = data.replace('<', '<') - data = data.replace('>', '>') - data = data.replace('&', '&') - data = data.replace('"', '"') - data = data.replace(''', "'") - return data - -class _RelativeURIResolver(_BaseHTMLProcessor): - relative_uris = [('a', 'href'), - ('applet', 'codebase'), - ('area', 'href'), - ('blockquote', 'cite'), - ('body', 'background'), - ('del', 'cite'), - ('form', 'action'), - ('frame', 'longdesc'), - ('frame', 'src'), - ('iframe', 'longdesc'), - ('iframe', 'src'), - ('head', 'profile'), - ('img', 'longdesc'), - ('img', 'src'), - ('img', 'usemap'), - ('input', 'src'), - ('input', 'usemap'), - ('ins', 'cite'), - ('link', 'href'), - ('object', 'classid'), - ('object', 'codebase'), - ('object', 'data'), - ('object', 'usemap'), - ('q', 'cite'), - ('script', 'src')] - - def __init__(self, baseuri, encoding): - _BaseHTMLProcessor.__init__(self, encoding) - self.baseuri = baseuri - - def resolveURI(self, uri): - return _urljoin(self.baseuri, uri) - - def unknown_starttag(self, tag, attrs): - attrs = self.normalize_attrs(attrs) - attrs = [(key, ((tag, key) in self.relative_uris) and self.resolveURI(value) or value) for key, value in attrs] - _BaseHTMLProcessor.unknown_starttag(self, tag, attrs) - -def _resolveRelativeURIs(htmlSource, baseURI, encoding): - if _debug: sys.stderr.write('entering _resolveRelativeURIs\n') - p = _RelativeURIResolver(baseURI, encoding) - p.feed(htmlSource) - return p.output() - -class _HTMLSanitizer(_BaseHTMLProcessor): - acceptable_elements = ['a', 'abbr', 'acronym', 'address', 'area', 'b', 'big', - 'blockquote', 'br', 'button', 'caption', 'center', 'cite', 'code', 'col', - 'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt', 'em', 'fieldset', - 'font', 'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input', - 'ins', 'kbd', 'label', 'legend', 'li', 'map', 'menu', 'ol', 'optgroup', - 'option', 'p', 'pre', 'q', 's', 'samp', 'select', 'small', 'span', 'strike', - 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'tfoot', 'th', - 'thead', 'tr', 'tt', 'u', 'ul', 'var'] - - acceptable_attributes = ['abbr', 'accept', 'accept-charset', 'accesskey', - 'action', 'align', 'alt', 'axis', 'border', 'cellpadding', 'cellspacing', - 'char', 'charoff', 'charset', 'checked', 'cite', 'class', 'clear', 'cols', - 'colspan', 'color', 'compact', 'coords', 'datetime', 'dir', 'disabled', - 'enctype', 'for', 'frame', 'headers', 'height', 'href', 'hreflang', 'hspace', - 'id', 'ismap', 'label', 'lang', 'longdesc', 'maxlength', 'media', 'method', - 'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'prompt', 'readonly', - 'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', 'selected', 'shape', 'size', - 'span', 'src', 'start', 'summary', 'tabindex', 'target', 'title', 'type', - 'usemap', 'valign', 'value', 'vspace', 'width'] - - unacceptable_elements_with_end_tag = ['script', 'applet'] - - def reset(self): - _BaseHTMLProcessor.reset(self) - self.unacceptablestack = 0 - - def unknown_starttag(self, tag, attrs): - if not tag in self.acceptable_elements: - if tag in self.unacceptable_elements_with_end_tag: - self.unacceptablestack += 1 - return - attrs = self.normalize_attrs(attrs) - attrs = [(key, value) for key, value in attrs if key in self.acceptable_attributes] - _BaseHTMLProcessor.unknown_starttag(self, tag, attrs) - - def unknown_endtag(self, tag): - if not tag in self.acceptable_elements: - if tag in self.unacceptable_elements_with_end_tag: - self.unacceptablestack -= 1 - return - _BaseHTMLProcessor.unknown_endtag(self, tag) - - def handle_pi(self, text): - pass - - def handle_decl(self, text): - pass - - def handle_data(self, text): - if not self.unacceptablestack: - _BaseHTMLProcessor.handle_data(self, text) - -def _sanitizeHTML(htmlSource, encoding): - p = _HTMLSanitizer(encoding) - p.feed(htmlSource) - data = p.output() - if TIDY_MARKUP: - # loop through list of preferred Tidy interfaces looking for one that's installed, - # then set up a common _tidy function to wrap the interface-specific API. - _tidy = None - for tidy_interface in PREFERRED_TIDY_INTERFACES: - try: - if tidy_interface == "uTidy": - from tidy import parseString as _utidy - def _tidy(data, **kwargs): - return str(_utidy(data, **kwargs)) - break - elif tidy_interface == "mxTidy": - from mx.Tidy import Tidy as _mxtidy - def _tidy(data, **kwargs): - nerrors, nwarnings, data, errordata = _mxtidy.tidy(data, **kwargs) - return data - break - except: - pass - if _tidy: - utf8 = type(data) == type(u'') - if utf8: - data = data.encode('utf-8') - data = _tidy(data, output_xhtml=1, numeric_entities=1, wrap=0, char_encoding="utf8") - if utf8: - data = unicode(data, 'utf-8') - if data.count(''): - data = data.split('>', 1)[1] - if data.count('= '2.3.3' - assert base64 != None - user, passw = base64.decodestring(req.headers['Authorization'].split(' ')[1]).split(':') - realm = re.findall('realm="([^"]*)"', headers['WWW-Authenticate'])[0] - self.add_password(realm, host, user, passw) - retry = self.http_error_auth_reqed('www-authenticate', host, req, headers) - self.reset_retry_count() - return retry - except: - return self.http_error_default(req, fp, code, msg, headers) - -def _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers): - """URL, filename, or string --> stream - - This function lets you define parsers that take any input source - (URL, pathname to local or network file, or actual data as a string) - and deal with it in a uniform manner. Returned object is guaranteed - to have all the basic stdio read methods (read, readline, readlines). - Just .close() the object when you're done with it. - - If the etag argument is supplied, it will be used as the value of an - If-None-Match request header. - - If the modified argument is supplied, it must be a tuple of 9 integers - as returned by gmtime() in the standard Python time module. This MUST - be in GMT (Greenwich Mean Time). The formatted date/time will be used - as the value of an If-Modified-Since request header. - - If the agent argument is supplied, it will be used as the value of a - User-Agent request header. - - If the referrer argument is supplied, it will be used as the value of a - Referer[sic] request header. - - If handlers is supplied, it is a list of handlers used to build a - urllib2 opener. - """ - - if hasattr(url_file_stream_or_string, 'read'): - return url_file_stream_or_string - - if url_file_stream_or_string == '-': - return sys.stdin - - if urlparse.urlparse(url_file_stream_or_string)[0] in ('http', 'https', 'ftp'): - if not agent: - agent = USER_AGENT - # test for inline user:password for basic auth - auth = None - if base64: - urltype, rest = urllib.splittype(url_file_stream_or_string) - realhost, rest = urllib.splithost(rest) - if realhost: - user_passwd, realhost = urllib.splituser(realhost) - if user_passwd: - url_file_stream_or_string = '%s://%s%s' % (urltype, realhost, rest) - auth = base64.encodestring(user_passwd).strip() - # try to open with urllib2 (to use optional headers) - request = urllib2.Request(url_file_stream_or_string) - request.add_header('User-Agent', agent) - if etag: - request.add_header('If-None-Match', etag) - if modified: - # format into an RFC 1123-compliant timestamp. We can't use - # time.strftime() since the %a and %b directives can be affected - # by the current locale, but RFC 2616 states that dates must be - # in English. - short_weekdays = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'] - months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'] - request.add_header('If-Modified-Since', '%s, %02d %s %04d %02d:%02d:%02d GMT' % (short_weekdays[modified[6]], modified[2], months[modified[1] - 1], modified[0], modified[3], modified[4], modified[5])) - if referrer: - request.add_header('Referer', referrer) - if gzip and zlib: - request.add_header('Accept-encoding', 'gzip, deflate') - elif gzip: - request.add_header('Accept-encoding', 'gzip') - elif zlib: - request.add_header('Accept-encoding', 'deflate') - else: - request.add_header('Accept-encoding', '') - if auth: - request.add_header('Authorization', 'Basic %s' % auth) - if ACCEPT_HEADER: - request.add_header('Accept', ACCEPT_HEADER) - request.add_header('A-IM', 'feed') # RFC 3229 support - opener = apply(urllib2.build_opener, tuple([_FeedURLHandler()] + handlers)) - opener.addheaders = [] # RMK - must clear so we only send our custom User-Agent - try: - return opener.open(request) - finally: - opener.close() # JohnD - - # try to open with native open function (if url_file_stream_or_string is a filename) - try: - return open(url_file_stream_or_string) - except: - pass - - # treat url_file_stream_or_string as string - return _StringIO(str(url_file_stream_or_string)) - -_date_handlers = [] -def registerDateHandler(func): - '''Register a date handler function (takes string, returns 9-tuple date in GMT)''' - _date_handlers.insert(0, func) - -# ISO-8601 date parsing routines written by Fazal Majid. -# The ISO 8601 standard is very convoluted and irregular - a full ISO 8601 -# parser is beyond the scope of feedparser and would be a worthwhile addition -# to the Python library. -# A single regular expression cannot parse ISO 8601 date formats into groups -# as the standard is highly irregular (for instance is 030104 2003-01-04 or -# 0301-04-01), so we use templates instead. -# Please note the order in templates is significant because we need a -# greedy match. -_iso8601_tmpl = ['YYYY-?MM-?DD', 'YYYY-MM', 'YYYY-?OOO', - 'YY-?MM-?DD', 'YY-?OOO', 'YYYY', - '-YY-?MM', '-OOO', '-YY', - '--MM-?DD', '--MM', - '---DD', - 'CC', ''] -_iso8601_re = [ - tmpl.replace( - 'YYYY', r'(?P\d{4})').replace( - 'YY', r'(?P\d\d)').replace( - 'MM', r'(?P[01]\d)').replace( - 'DD', r'(?P[0123]\d)').replace( - 'OOO', r'(?P[0123]\d\d)').replace( - 'CC', r'(?P\d\d$)') - + r'(T?(?P\d{2}):(?P\d{2})' - + r'(:(?P\d{2}))?' - + r'(?P[+-](?P\d{2})(:(?P\d{2}))?|Z)?)?' - for tmpl in _iso8601_tmpl] -del tmpl -_iso8601_matches = [re.compile(regex).match for regex in _iso8601_re] -del regex -def _parse_date_iso8601(dateString): - '''Parse a variety of ISO-8601-compatible formats like 20040105''' - m = None - for _iso8601_match in _iso8601_matches: - m = _iso8601_match(dateString) - if m: break - if not m: return - if m.span() == (0, 0): return - params = m.groupdict() - ordinal = params.get('ordinal', 0) - if ordinal: - ordinal = int(ordinal) - else: - ordinal = 0 - year = params.get('year', '--') - if not year or year == '--': - year = time.gmtime()[0] - elif len(year) == 2: - # ISO 8601 assumes current century, i.e. 93 -> 2093, NOT 1993 - year = 100 * int(time.gmtime()[0] / 100) + int(year) - else: - year = int(year) - month = params.get('month', '-') - if not month or month == '-': - # ordinals are NOT normalized by mktime, we simulate them - # by setting month=1, day=ordinal - if ordinal: - month = 1 - else: - month = time.gmtime()[1] - month = int(month) - day = params.get('day', 0) - if not day: - # see above - if ordinal: - day = ordinal - elif params.get('century', 0) or \ - params.get('year', 0) or params.get('month', 0): - day = 1 - else: - day = time.gmtime()[2] - else: - day = int(day) - # special case of the century - is the first year of the 21st century - # 2000 or 2001 ? The debate goes on... - if 'century' in params.keys(): - year = (int(params['century']) - 1) * 100 + 1 - # in ISO 8601 most fields are optional - for field in ['hour', 'minute', 'second', 'tzhour', 'tzmin']: - if not params.get(field, None): - params[field] = 0 - hour = int(params.get('hour', 0)) - minute = int(params.get('minute', 0)) - second = int(params.get('second', 0)) - # weekday is normalized by mktime(), we can ignore it - weekday = 0 - # daylight savings is complex, but not needed for feedparser's purposes - # as time zones, if specified, include mention of whether it is active - # (e.g. PST vs. PDT, CET). Using -1 is implementation-dependent and - # and most implementations have DST bugs - daylight_savings_flag = 0 - tm = [year, month, day, hour, minute, second, weekday, - ordinal, daylight_savings_flag] - # ISO 8601 time zone adjustments - tz = params.get('tz') - if tz and tz != 'Z': - if tz[0] == '-': - tm[3] += int(params.get('tzhour', 0)) - tm[4] += int(params.get('tzmin', 0)) - elif tz[0] == '+': - tm[3] -= int(params.get('tzhour', 0)) - tm[4] -= int(params.get('tzmin', 0)) - else: - return None - # Python's time.mktime() is a wrapper around the ANSI C mktime(3c) - # which is guaranteed to normalize d/m/y/h/m/s. - # Many implementations have bugs, but we'll pretend they don't. - return time.localtime(time.mktime(tm)) -registerDateHandler(_parse_date_iso8601) - -# 8-bit date handling routines written by ytrewq1. -_korean_year = u'\ub144' # b3e2 in euc-kr -_korean_month = u'\uc6d4' # bff9 in euc-kr -_korean_day = u'\uc77c' # c0cf in euc-kr -_korean_am = u'\uc624\uc804' # bfc0 c0fc in euc-kr -_korean_pm = u'\uc624\ud6c4' # bfc0 c8c4 in euc-kr - -_korean_onblog_date_re = \ - re.compile('(\d{4})%s\s+(\d{2})%s\s+(\d{2})%s\s+(\d{2}):(\d{2}):(\d{2})' % \ - (_korean_year, _korean_month, _korean_day)) -_korean_nate_date_re = \ - re.compile(u'(\d{4})-(\d{2})-(\d{2})\s+(%s|%s)\s+(\d{,2}):(\d{,2}):(\d{,2})' % \ - (_korean_am, _korean_pm)) -def _parse_date_onblog(dateString): - '''Parse a string according to the OnBlog 8-bit date format''' - m = _korean_onblog_date_re.match(dateString) - if not m: return - w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \ - {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\ - 'hour': m.group(4), 'minute': m.group(5), 'second': m.group(6),\ - 'zonediff': '+09:00'} - if _debug: sys.stderr.write('OnBlog date parsed as: %s\n' % w3dtfdate) - return _parse_date_w3dtf(w3dtfdate) -registerDateHandler(_parse_date_onblog) - -def _parse_date_nate(dateString): - '''Parse a string according to the Nate 8-bit date format''' - m = _korean_nate_date_re.match(dateString) - if not m: return - hour = int(m.group(5)) - ampm = m.group(4) - if (ampm == _korean_pm): - hour += 12 - hour = str(hour) - if len(hour) == 1: - hour = '0' + hour - w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \ - {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\ - 'hour': hour, 'minute': m.group(6), 'second': m.group(7),\ - 'zonediff': '+09:00'} - if _debug: sys.stderr.write('Nate date parsed as: %s\n' % w3dtfdate) - return _parse_date_w3dtf(w3dtfdate) -registerDateHandler(_parse_date_nate) - -_mssql_date_re = \ - re.compile('(\d{4})-(\d{2})-(\d{2})\s+(\d{2}):(\d{2}):(\d{2})(\.\d+)?') -def _parse_date_mssql(dateString): - '''Parse a string according to the MS SQL date format''' - m = _mssql_date_re.match(dateString) - if not m: return - w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \ - {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\ - 'hour': m.group(4), 'minute': m.group(5), 'second': m.group(6),\ - 'zonediff': '+09:00'} - if _debug: sys.stderr.write('MS SQL date parsed as: %s\n' % w3dtfdate) - return _parse_date_w3dtf(w3dtfdate) -registerDateHandler(_parse_date_mssql) - -# Unicode strings for Greek date strings -_greek_months = \ - { \ - u'\u0399\u03b1\u03bd': u'Jan', # c9e1ed in iso-8859-7 - u'\u03a6\u03b5\u03b2': u'Feb', # d6e5e2 in iso-8859-7 - u'\u039c\u03ac\u03ce': u'Mar', # ccdcfe in iso-8859-7 - u'\u039c\u03b1\u03ce': u'Mar', # cce1fe in iso-8859-7 - u'\u0391\u03c0\u03c1': u'Apr', # c1f0f1 in iso-8859-7 - u'\u039c\u03ac\u03b9': u'May', # ccdce9 in iso-8859-7 - u'\u039c\u03b1\u03ca': u'May', # cce1fa in iso-8859-7 - u'\u039c\u03b1\u03b9': u'May', # cce1e9 in iso-8859-7 - u'\u0399\u03bf\u03cd\u03bd': u'Jun', # c9effded in iso-8859-7 - u'\u0399\u03bf\u03bd': u'Jun', # c9efed in iso-8859-7 - u'\u0399\u03bf\u03cd\u03bb': u'Jul', # c9effdeb in iso-8859-7 - u'\u0399\u03bf\u03bb': u'Jul', # c9f9eb in iso-8859-7 - u'\u0391\u03cd\u03b3': u'Aug', # c1fde3 in iso-8859-7 - u'\u0391\u03c5\u03b3': u'Aug', # c1f5e3 in iso-8859-7 - u'\u03a3\u03b5\u03c0': u'Sep', # d3e5f0 in iso-8859-7 - u'\u039f\u03ba\u03c4': u'Oct', # cfeaf4 in iso-8859-7 - u'\u039d\u03bf\u03ad': u'Nov', # cdefdd in iso-8859-7 - u'\u039d\u03bf\u03b5': u'Nov', # cdefe5 in iso-8859-7 - u'\u0394\u03b5\u03ba': u'Dec', # c4e5ea in iso-8859-7 - } - -_greek_wdays = \ - { \ - u'\u039a\u03c5\u03c1': u'Sun', # caf5f1 in iso-8859-7 - u'\u0394\u03b5\u03c5': u'Mon', # c4e5f5 in iso-8859-7 - u'\u03a4\u03c1\u03b9': u'Tue', # d4f1e9 in iso-8859-7 - u'\u03a4\u03b5\u03c4': u'Wed', # d4e5f4 in iso-8859-7 - u'\u03a0\u03b5\u03bc': u'Thu', # d0e5ec in iso-8859-7 - u'\u03a0\u03b1\u03c1': u'Fri', # d0e1f1 in iso-8859-7 - u'\u03a3\u03b1\u03b2': u'Sat', # d3e1e2 in iso-8859-7 - } - -_greek_date_format_re = \ - re.compile(u'([^,]+),\s+(\d{2})\s+([^\s]+)\s+(\d{4})\s+(\d{2}):(\d{2}):(\d{2})\s+([^\s]+)') - -def _parse_date_greek(dateString): - '''Parse a string according to a Greek 8-bit date format.''' - m = _greek_date_format_re.match(dateString) - if not m: return - try: - wday = _greek_wdays[m.group(1)] - month = _greek_months[m.group(3)] - except: - return - rfc822date = '%(wday)s, %(day)s %(month)s %(year)s %(hour)s:%(minute)s:%(second)s %(zonediff)s' % \ - {'wday': wday, 'day': m.group(2), 'month': month, 'year': m.group(4),\ - 'hour': m.group(5), 'minute': m.group(6), 'second': m.group(7),\ - 'zonediff': m.group(8)} - if _debug: sys.stderr.write('Greek date parsed as: %s\n' % rfc822date) - return _parse_date_rfc822(rfc822date) -registerDateHandler(_parse_date_greek) - -# Unicode strings for Hungarian date strings -_hungarian_months = \ - { \ - u'janu\u00e1r': u'01', # e1 in iso-8859-2 - u'febru\u00e1ri': u'02', # e1 in iso-8859-2 - u'm\u00e1rcius': u'03', # e1 in iso-8859-2 - u'\u00e1prilis': u'04', # e1 in iso-8859-2 - u'm\u00e1ujus': u'05', # e1 in iso-8859-2 - u'j\u00fanius': u'06', # fa in iso-8859-2 - u'j\u00falius': u'07', # fa in iso-8859-2 - u'augusztus': u'08', - u'szeptember': u'09', - u'okt\u00f3ber': u'10', # f3 in iso-8859-2 - u'november': u'11', - u'december': u'12', - } - -_hungarian_date_format_re = \ - re.compile(u'(\d{4})-([^-]+)-(\d{,2})T(\d{,2}):(\d{2})((\+|-)(\d{,2}:\d{2}))') - -def _parse_date_hungarian(dateString): - '''Parse a string according to a Hungarian 8-bit date format.''' - m = _hungarian_date_format_re.match(dateString) - if not m: return - try: - month = _hungarian_months[m.group(2)] - day = m.group(3) - if len(day) == 1: - day = '0' + day - hour = m.group(4) - if len(hour) == 1: - hour = '0' + hour - except: - return - w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s%(zonediff)s' % \ - {'year': m.group(1), 'month': month, 'day': day,\ - 'hour': hour, 'minute': m.group(5),\ - 'zonediff': m.group(6)} - if _debug: sys.stderr.write('Hungarian date parsed as: %s\n' % w3dtfdate) - return _parse_date_w3dtf(w3dtfdate) -registerDateHandler(_parse_date_hungarian) - -# W3DTF-style date parsing adapted from PyXML xml.utils.iso8601, written by -# Drake and licensed under the Python license. Removed all range checking -# for month, day, hour, minute, and second, since mktime will normalize -# these later -def _parse_date_w3dtf(dateString): - def __extract_date(m): - year = int(m.group('year')) - if year < 100: - year = 100 * int(time.gmtime()[0] / 100) + int(year) - if year < 1000: - return 0, 0, 0 - julian = m.group('julian') - if julian: - julian = int(julian) - month = julian / 30 + 1 - day = julian % 30 + 1 - jday = None - while jday != julian: - t = time.mktime((year, month, day, 0, 0, 0, 0, 0, 0)) - jday = time.gmtime(t)[-2] - diff = abs(jday - julian) - if jday > julian: - if diff < day: - day = day - diff - else: - month = month - 1 - day = 31 - elif jday < julian: - if day + diff < 28: - day = day + diff - else: - month = month + 1 - return year, month, day - month = m.group('month') - day = 1 - if month is None: - month = 1 - else: - month = int(month) - day = m.group('day') - if day: - day = int(day) - else: - day = 1 - return year, month, day - - def __extract_time(m): - if not m: - return 0, 0, 0 - hours = m.group('hours') - if not hours: - return 0, 0, 0 - hours = int(hours) - minutes = int(m.group('minutes')) - seconds = m.group('seconds') - if seconds: - seconds = int(seconds) - else: - seconds = 0 - return hours, minutes, seconds - - def __extract_tzd(m): - '''Return the Time Zone Designator as an offset in seconds from UTC.''' - if not m: - return 0 - tzd = m.group('tzd') - if not tzd: - return 0 - if tzd == 'Z': - return 0 - hours = int(m.group('tzdhours')) - minutes = m.group('tzdminutes') - if minutes: - minutes = int(minutes) - else: - minutes = 0 - offset = (hours*60 + minutes) * 60 - if tzd[0] == '+': - return -offset - return offset - - __date_re = ('(?P\d\d\d\d)' - '(?:(?P-|)' - '(?:(?P\d\d\d)' - '|(?P\d\d)(?:(?P=dsep)(?P\d\d))?))?') - __tzd_re = '(?P[-+](?P\d\d)(?::?(?P\d\d))|Z)' - __tzd_rx = re.compile(__tzd_re) - __time_re = ('(?P\d\d)(?P:|)(?P\d\d)' - '(?:(?P=tsep)(?P\d\d(?:[.,]\d+)?))?' - + __tzd_re) - __datetime_re = '%s(?:T%s)?' % (__date_re, __time_re) - __datetime_rx = re.compile(__datetime_re) - m = __datetime_rx.match(dateString) - if (m is None) or (m.group() != dateString): return - gmt = __extract_date(m) + __extract_time(m) + (0, 0, 0) - if gmt[0] == 0: return - return time.gmtime(time.mktime(gmt) + __extract_tzd(m) - time.timezone) -registerDateHandler(_parse_date_w3dtf) - -def _parse_date_rfc822(dateString): - '''Parse an RFC822, RFC1123, RFC2822, or asctime-style date''' - data = dateString.split() - if data[0][-1] in (',', '.') or data[0].lower() in rfc822._daynames: - del data[0] - if len(data) == 4: - s = data[3] - i = s.find('+') - if i > 0: - data[3:] = [s[:i], s[i+1:]] - else: - data.append('') - dateString = " ".join(data) - if len(data) < 5: - dateString += ' 00:00:00 GMT' - tm = rfc822.parsedate_tz(dateString) - if tm: - return time.gmtime(rfc822.mktime_tz(tm)) -# rfc822.py defines several time zones, but we define some extra ones. -# 'ET' is equivalent to 'EST', etc. -_additional_timezones = {'AT': -400, 'ET': -500, 'CT': -600, 'MT': -700, 'PT': -800} -rfc822._timezones.update(_additional_timezones) -registerDateHandler(_parse_date_rfc822) - -def _parse_date(dateString): - '''Parses a variety of date formats into a 9-tuple in GMT''' - for handler in _date_handlers: - try: - date9tuple = handler(dateString) - if not date9tuple: continue - if len(date9tuple) != 9: - if _debug: sys.stderr.write('date handler function must return 9-tuple\n') - raise ValueError - map(int, date9tuple) - return date9tuple - except Exception, e: - if _debug: sys.stderr.write('%s raised %s\n' % (handler.__name__, repr(e))) - pass - return None - -def _getCharacterEncoding(http_headers, xml_data): - '''Get the character encoding of the XML document - - http_headers is a dictionary - xml_data is a raw string (not Unicode) - - This is so much trickier than it sounds, it's not even funny. - According to RFC 3023 ('XML Media Types'), if the HTTP Content-Type - is application/xml, application/*+xml, - application/xml-external-parsed-entity, or application/xml-dtd, - the encoding given in the charset parameter of the HTTP Content-Type - takes precedence over the encoding given in the XML prefix within the - document, and defaults to 'utf-8' if neither are specified. But, if - the HTTP Content-Type is text/xml, text/*+xml, or - text/xml-external-parsed-entity, the encoding given in the XML prefix - within the document is ALWAYS IGNORED and only the encoding given in - the charset parameter of the HTTP Content-Type header should be - respected, and it defaults to 'us-ascii' if not specified. - - Furthermore, discussion on the atom-syntax mailing list with the - author of RFC 3023 leads me to the conclusion that any document - served with a Content-Type of text/* and no charset parameter - must be treated as us-ascii. (We now do this.) And also that it - must always be flagged as non-well-formed. (We now do this too.) - - If Content-Type is unspecified (input was local file or non-HTTP source) - or unrecognized (server just got it totally wrong), then go by the - encoding given in the XML prefix of the document and default to - 'iso-8859-1' as per the HTTP specification (RFC 2616). - - Then, assuming we didn't find a character encoding in the HTTP headers - (and the HTTP Content-type allowed us to look in the body), we need - to sniff the first few bytes of the XML data and try to determine - whether the encoding is ASCII-compatible. Section F of the XML - specification shows the way here: - http://www.w3.org/TR/REC-xml/#sec-guessing-no-ext-info - - If the sniffed encoding is not ASCII-compatible, we need to make it - ASCII compatible so that we can sniff further into the XML declaration - to find the encoding attribute, which will tell us the true encoding. - - Of course, none of this guarantees that we will be able to parse the - feed in the declared character encoding (assuming it was declared - correctly, which many are not). CJKCodecs and iconv_codec help a lot; - you should definitely install them if you can. - http://cjkpython.i18n.org/ - ''' - - def _parseHTTPContentType(content_type): - '''takes HTTP Content-Type header and returns (content type, charset) - - If no charset is specified, returns (content type, '') - If no content type is specified, returns ('', '') - Both return parameters are guaranteed to be lowercase strings - ''' - content_type = content_type or '' - content_type, params = cgi.parse_header(content_type) - return content_type, params.get('charset', '').replace("'", '') - - sniffed_xml_encoding = '' - xml_encoding = '' - true_encoding = '' - http_content_type, http_encoding = _parseHTTPContentType(http_headers.get('content-type')) - # Must sniff for non-ASCII-compatible character encodings before - # searching for XML declaration. This heuristic is defined in - # section F of the XML specification: - # http://www.w3.org/TR/REC-xml/#sec-guessing-no-ext-info - try: - if xml_data[:4] == '\x4c\x6f\xa7\x94': - # EBCDIC - xml_data = _ebcdic_to_ascii(xml_data) - elif xml_data[:4] == '\x00\x3c\x00\x3f': - # UTF-16BE - sniffed_xml_encoding = 'utf-16be' - xml_data = unicode(xml_data, 'utf-16be').encode('utf-8') - elif (len(xml_data) >= 4) and (xml_data[:2] == '\xfe\xff') and (xml_data[2:4] != '\x00\x00'): - # UTF-16BE with BOM - sniffed_xml_encoding = 'utf-16be' - xml_data = unicode(xml_data[2:], 'utf-16be').encode('utf-8') - elif xml_data[:4] == '\x3c\x00\x3f\x00': - # UTF-16LE - sniffed_xml_encoding = 'utf-16le' - xml_data = unicode(xml_data, 'utf-16le').encode('utf-8') - elif (len(xml_data) >= 4) and (xml_data[:2] == '\xff\xfe') and (xml_data[2:4] != '\x00\x00'): - # UTF-16LE with BOM - sniffed_xml_encoding = 'utf-16le' - xml_data = unicode(xml_data[2:], 'utf-16le').encode('utf-8') - elif xml_data[:4] == '\x00\x00\x00\x3c': - # UTF-32BE - sniffed_xml_encoding = 'utf-32be' - xml_data = unicode(xml_data, 'utf-32be').encode('utf-8') - elif xml_data[:4] == '\x3c\x00\x00\x00': - # UTF-32LE - sniffed_xml_encoding = 'utf-32le' - xml_data = unicode(xml_data, 'utf-32le').encode('utf-8') - elif xml_data[:4] == '\x00\x00\xfe\xff': - # UTF-32BE with BOM - sniffed_xml_encoding = 'utf-32be' - xml_data = unicode(xml_data[4:], 'utf-32be').encode('utf-8') - elif xml_data[:4] == '\xff\xfe\x00\x00': - # UTF-32LE with BOM - sniffed_xml_encoding = 'utf-32le' - xml_data = unicode(xml_data[4:], 'utf-32le').encode('utf-8') - elif xml_data[:3] == '\xef\xbb\xbf': - # UTF-8 with BOM - sniffed_xml_encoding = 'utf-8' - xml_data = unicode(xml_data[3:], 'utf-8').encode('utf-8') - else: - # ASCII-compatible - pass - xml_encoding_match = re.compile('^<\?.*encoding=[\'"](.*?)[\'"].*\?>').match(xml_data) - except: - xml_encoding_match = None - if xml_encoding_match: - xml_encoding = xml_encoding_match.groups()[0].lower() - if sniffed_xml_encoding and (xml_encoding in ('iso-10646-ucs-2', 'ucs-2', 'csunicode', 'iso-10646-ucs-4', 'ucs-4', 'csucs4', 'utf-16', 'utf-32', 'utf_16', 'utf_32', 'utf16', 'u16')): - xml_encoding = sniffed_xml_encoding - acceptable_content_type = 0 - application_content_types = ('application/xml', 'application/xml-dtd', 'application/xml-external-parsed-entity') - text_content_types = ('text/xml', 'text/xml-external-parsed-entity') - if (http_content_type in application_content_types) or \ - (http_content_type.startswith('application/') and http_content_type.endswith('+xml')): - acceptable_content_type = 1 - true_encoding = http_encoding or xml_encoding or 'utf-8' - elif (http_content_type in text_content_types) or \ - (http_content_type.startswith('text/')) and http_content_type.endswith('+xml'): - acceptable_content_type = 1 - true_encoding = http_encoding or 'us-ascii' - elif http_content_type.startswith('text/'): - true_encoding = http_encoding or 'us-ascii' - elif http_headers and (not http_headers.has_key('content-type')): - true_encoding = xml_encoding or 'iso-8859-1' - else: - true_encoding = xml_encoding or 'utf-8' - return true_encoding, http_encoding, xml_encoding, sniffed_xml_encoding, acceptable_content_type - -def _toUTF8(data, encoding): - '''Changes an XML data stream on the fly to specify a new encoding - - data is a raw sequence of bytes (not Unicode) that is presumed to be in %encoding already - encoding is a string recognized by encodings.aliases - ''' - if _debug: sys.stderr.write('entering _toUTF8, trying encoding %s\n' % encoding) - # strip Byte Order Mark (if present) - if (len(data) >= 4) and (data[:2] == '\xfe\xff') and (data[2:4] != '\x00\x00'): - if _debug: - sys.stderr.write('stripping BOM\n') - if encoding != 'utf-16be': - sys.stderr.write('trying utf-16be instead\n') - encoding = 'utf-16be' - data = data[2:] - elif (len(data) >= 4) and (data[:2] == '\xff\xfe') and (data[2:4] != '\x00\x00'): - if _debug: - sys.stderr.write('stripping BOM\n') - if encoding != 'utf-16le': - sys.stderr.write('trying utf-16le instead\n') - encoding = 'utf-16le' - data = data[2:] - elif data[:3] == '\xef\xbb\xbf': - if _debug: - sys.stderr.write('stripping BOM\n') - if encoding != 'utf-8': - sys.stderr.write('trying utf-8 instead\n') - encoding = 'utf-8' - data = data[3:] - elif data[:4] == '\x00\x00\xfe\xff': - if _debug: - sys.stderr.write('stripping BOM\n') - if encoding != 'utf-32be': - sys.stderr.write('trying utf-32be instead\n') - encoding = 'utf-32be' - data = data[4:] - elif data[:4] == '\xff\xfe\x00\x00': - if _debug: - sys.stderr.write('stripping BOM\n') - if encoding != 'utf-32le': - sys.stderr.write('trying utf-32le instead\n') - encoding = 'utf-32le' - data = data[4:] - newdata = unicode(data, encoding) - if _debug: sys.stderr.write('successfully converted %s data to unicode\n' % encoding) - declmatch = re.compile('^<\?xml[^>]*?>') - newdecl = '''''' - if declmatch.search(newdata): - newdata = declmatch.sub(newdecl, newdata) - else: - newdata = newdecl + u'\n' + newdata - return newdata.encode('utf-8') - -def _stripDoctype(data): - '''Strips DOCTYPE from XML document, returns (rss_version, stripped_data) - - rss_version may be 'rss091n' or None - stripped_data is the same XML document, minus the DOCTYPE - ''' - entity_pattern = re.compile(r']*?)>', re.MULTILINE) - data = entity_pattern.sub('', data) - doctype_pattern = re.compile(r']*?)>', re.MULTILINE) - doctype_results = doctype_pattern.findall(data) - doctype = doctype_results and doctype_results[0] or '' - if doctype.lower().count('netscape'): - version = 'rss091n' - else: - version = None - data = doctype_pattern.sub('', data) - return version, data - -def opensearch_parse(url_file_stream_or_string, etag=None, modified=None, agent=None, referrer=None, handlers=[]): - '''Parse a feed from a URL, file, stream, or string''' - result = FeedParserDict() - result['feed'] = FeedParserDict() - result['entries'] = [] - if _XML_AVAILABLE: - result['bozo'] = 0 - if type(handlers) == types.InstanceType: - handlers = [handlers] - try: - f = _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers) - data = f.read() - except Exception, e: - result['bozo'] = 1 - result['bozo_exception'] = e - data = '' - f = None - - # if feed is gzip-compressed, decompress it - if f and data and hasattr(f, 'headers'): - if gzip and f.headers.get('content-encoding', '') == 'gzip': - try: - data = gzip.GzipFile(fileobj=_StringIO(data)).read() - except Exception, e: - # Some feeds claim to be gzipped but they're not, so - # we get garbage. Ideally, we should re-request the - # feed without the 'Accept-encoding: gzip' header, - # but we don't. - result['bozo'] = 1 - result['bozo_exception'] = e - data = '' - elif zlib and f.headers.get('content-encoding', '') == 'deflate': - try: - data = zlib.decompress(data, -zlib.MAX_WBITS) - except Exception, e: - result['bozo'] = 1 - result['bozo_exception'] = e - data = '' - - # save HTTP headers - if hasattr(f, 'info'): - info = f.info() - result['etag'] = info.getheader('ETag') - last_modified = info.getheader('Last-Modified') - if last_modified: - result['modified'] = _parse_date(last_modified) - if hasattr(f, 'url'): - result['href'] = f.url - result['status'] = 200 - if hasattr(f, 'status'): - result['status'] = f.status - if hasattr(f, 'headers'): - result['headers'] = f.headers.dict - if hasattr(f, 'close'): - f.close() - - # there are four encodings to keep track of: - # - http_encoding is the encoding declared in the Content-Type HTTP header - # - xml_encoding is the encoding declared in the ; changed -# project name -#2.5 - 7/25/2003 - MAP - changed to Python license (all contributors agree); -# removed unnecessary urllib code -- urllib2 should always be available anyway; -# return actual url, status, and full HTTP headers (as result['url'], -# result['status'], and result['headers']) if parsing a remote feed over HTTP -- -# this should pass all the HTTP tests at ; -# added the latest namespace-of-the-week for RSS 2.0 -#2.5.1 - 7/26/2003 - RMK - clear opener.addheaders so we only send our custom -# User-Agent (otherwise urllib2 sends two, which confuses some servers) -#2.5.2 - 7/28/2003 - MAP - entity-decode inline xml properly; added support for -# inline and as used in some RSS 2.0 feeds -#2.5.3 - 8/6/2003 - TvdV - patch to track whether we're inside an image or -# textInput, and also to return the character encoding (if specified) -#2.6 - 1/1/2004 - MAP - dc:author support (MarekK); fixed bug tracking -# nested divs within content (JohnD); fixed missing sys import (JohanS); -# fixed regular expression to capture XML character encoding (Andrei); -# added support for Atom 0.3-style links; fixed bug with textInput tracking; -# added support for cloud (MartijnP); added support for multiple -# category/dc:subject (MartijnP); normalize content model: 'description' gets -# description (which can come from description, summary, or full content if no -# description), 'content' gets dict of base/language/type/value (which can come -# from content:encoded, xhtml:body, content, or fullitem); -# fixed bug matching arbitrary Userland namespaces; added xml:base and xml:lang -# tracking; fixed bug tracking unknown tags; fixed bug tracking content when -# element is not in default namespace (like Pocketsoap feed); -# resolve relative URLs in link, guid, docs, url, comments, wfw:comment, -# wfw:commentRSS; resolve relative URLs within embedded HTML markup in -# description, xhtml:body, content, content:encoded, title, subtitle, -# summary, info, tagline, and copyright; added support for pingback and -# trackback namespaces -#2.7 - 1/5/2004 - MAP - really added support for trackback and pingback -# namespaces, as opposed to 2.6 when I said I did but didn't really; -# sanitize HTML markup within some elements; added mxTidy support (if -# installed) to tidy HTML markup within some elements; fixed indentation -# bug in _parse_date (FazalM); use socket.setdefaulttimeout if available -# (FazalM); universal date parsing and normalization (FazalM): 'created', modified', -# 'issued' are parsed into 9-tuple date format and stored in 'created_parsed', -# 'modified_parsed', and 'issued_parsed'; 'date' is duplicated in 'modified' -# and vice-versa; 'date_parsed' is duplicated in 'modified_parsed' and vice-versa -#2.7.1 - 1/9/2004 - MAP - fixed bug handling " and '. fixed memory -# leak not closing url opener (JohnD); added dc:publisher support (MarekK); -# added admin:errorReportsTo support (MarekK); Python 2.1 dict support (MarekK) -#2.7.4 - 1/14/2004 - MAP - added workaround for improperly formed
tags in -# encoded HTML (skadz); fixed unicode handling in normalize_attrs (ChrisL); -# fixed relative URI processing for guid (skadz); added ICBM support; added -# base64 support -#2.7.5 - 1/15/2004 - MAP - added workaround for malformed DOCTYPE (seen on many -# blogspot.com sites); added _debug variable -#2.7.6 - 1/16/2004 - MAP - fixed bug with StringIO importing -#3.0b3 - 1/23/2004 - MAP - parse entire feed with real XML parser (if available); -# added several new supported namespaces; fixed bug tracking naked markup in -# description; added support for enclosure; added support for source; re-added -# support for cloud which got dropped somehow; added support for expirationDate -#3.0b4 - 1/26/2004 - MAP - fixed xml:lang inheritance; fixed multiple bugs tracking -# xml:base URI, one for documents that don't define one explicitly and one for -# documents that define an outer and an inner xml:base that goes out of scope -# before the end of the document -#3.0b5 - 1/26/2004 - MAP - fixed bug parsing multiple links at feed level -#3.0b6 - 1/27/2004 - MAP - added feed type and version detection, result['version'] -# will be one of SUPPORTED_VERSIONS.keys() or empty string if unrecognized; -# added support for creativeCommons:license and cc:license; added support for -# full Atom content model in title, tagline, info, copyright, summary; fixed bug -# with gzip encoding (not always telling server we support it when we do) -#3.0b7 - 1/28/2004 - MAP - support Atom-style author element in author_detail -# (dictionary of 'name', 'url', 'email'); map author to author_detail if author -# contains name + email address -#3.0b8 - 1/28/2004 - MAP - added support for contributor -#3.0b9 - 1/29/2004 - MAP - fixed check for presence of dict function; added -# support for summary -#3.0b10 - 1/31/2004 - MAP - incorporated ISO-8601 date parsing routines from -# xml.util.iso8601 -#3.0b11 - 2/2/2004 - MAP - added 'rights' to list of elements that can contain -# dangerous markup; fiddled with decodeEntities (not right); liberalized -# date parsing even further -#3.0b12 - 2/6/2004 - MAP - fiddled with decodeEntities (still not right); -# added support to Atom 0.2 subtitle; added support for Atom content model -# in copyright; better sanitizing of dangerous HTML elements with end tags -# (script, frameset) -#3.0b13 - 2/8/2004 - MAP - better handling of empty HTML tags (br, hr, img, -# etc.) in embedded markup, in either HTML or XHTML form (
,
,
) -#3.0b14 - 2/8/2004 - MAP - fixed CDATA handling in non-wellformed feeds under -# Python 2.1 -#3.0b15 - 2/11/2004 - MAP - fixed bug resolving relative links in wfw:commentRSS; -# fixed bug capturing author and contributor URL; fixed bug resolving relative -# links in author and contributor URL; fixed bug resolvin relative links in -# generator URL; added support for recognizing RSS 1.0; passed Simon Fell's -# namespace tests, and included them permanently in the test suite with his -# permission; fixed namespace handling under Python 2.1 -#3.0b16 - 2/12/2004 - MAP - fixed support for RSS 0.90 (broken in b15) -#3.0b17 - 2/13/2004 - MAP - determine character encoding as per RFC 3023 -#3.0b18 - 2/17/2004 - MAP - always map description to summary_detail (Andrei); -# use libxml2 (if available) -#3.0b19 - 3/15/2004 - MAP - fixed bug exploding author information when author -# name was in parentheses; removed ultra-problematic mxTidy support; patch to -# workaround crash in PyXML/expat when encountering invalid entities -# (MarkMoraes); support for textinput/textInput -#3.0b20 - 4/7/2004 - MAP - added CDF support -#3.0b21 - 4/14/2004 - MAP - added Hot RSS support -#3.0b22 - 4/19/2004 - MAP - changed 'channel' to 'feed', 'item' to 'entries' in -# results dict; changed results dict to allow getting values with results.key -# as well as results[key]; work around embedded illformed HTML with half -# a DOCTYPE; work around malformed Content-Type header; if character encoding -# is wrong, try several common ones before falling back to regexes (if this -# works, bozo_exception is set to CharacterEncodingOverride); fixed character -# encoding issues in BaseHTMLProcessor by tracking encoding and converting -# from Unicode to raw strings before feeding data to sgmllib.SGMLParser; -# convert each value in results to Unicode (if possible), even if using -# regex-based parsing -#3.0b23 - 4/21/2004 - MAP - fixed UnicodeDecodeError for feeds that contain -# high-bit characters in attributes in embedded HTML in description (thanks -# Thijs van de Vossen); moved guid, date, and date_parsed to mapped keys in -# FeedParserDict; tweaked FeedParserDict.has_key to return True if asking -# about a mapped key -#3.0fc1 - 4/23/2004 - MAP - made results.entries[0].links[0] and -# results.entries[0].enclosures[0] into FeedParserDict; fixed typo that could -# cause the same encoding to be tried twice (even if it failed the first time); -# fixed DOCTYPE stripping when DOCTYPE contained entity declarations; -# better textinput and image tracking in illformed RSS 1.0 feeds -#3.0fc2 - 5/10/2004 - MAP - added and passed Sam's amp tests; added and passed -# my blink tag tests -#3.0fc3 - 6/18/2004 - MAP - fixed bug in _changeEncodingDeclaration that -# failed to parse utf-16 encoded feeds; made source into a FeedParserDict; -# duplicate admin:generatorAgent/@rdf:resource in generator_detail.url; -# added support for image; refactored parse() fallback logic to try other -# encodings if SAX parsing fails (previously it would only try other encodings -# if re-encoding failed); remove unichr madness in normalize_attrs now that -# we're properly tracking encoding in and out of BaseHTMLProcessor; set -# feed.language from root-level xml:lang; set entry.id from rdf:about; -# send Accept header -#3.0 - 6/21/2004 - MAP - don't try iso-8859-1 (can't distinguish between -# iso-8859-1 and windows-1252 anyway, and most incorrectly marked feeds are -# windows-1252); fixed regression that could cause the same encoding to be -# tried twice (even if it failed the first time) -#3.0.1 - 6/22/2004 - MAP - default to us-ascii for all text/* content types; -# recover from malformed content-type header parameter with no equals sign -# ('text/xml; charset:iso-8859-1') -#3.1 - 6/28/2004 - MAP - added and passed tests for converting HTML entities -# to Unicode equivalents in illformed feeds (aaronsw); added and -# passed tests for converting character entities to Unicode equivalents -# in illformed feeds (aaronsw); test for valid parsers when setting -# XML_AVAILABLE; make version and encoding available when server returns -# a 304; add handlers parameter to pass arbitrary urllib2 handlers (like -# digest auth or proxy support); add code to parse username/password -# out of url and send as basic authentication; expose downloading-related -# exceptions in bozo_exception (aaronsw); added __contains__ method to -# FeedParserDict (aaronsw); added publisher_detail (aaronsw) -#3.2 - 7/3/2004 - MAP - use cjkcodecs and iconv_codec if available; always -# convert feed to UTF-8 before passing to XML parser; completely revamped -# logic for determining character encoding and attempting XML parsing -# (much faster); increased default timeout to 20 seconds; test for presence -# of Location header on redirects; added tests for many alternate character -# encodings; support various EBCDIC encodings; support UTF-16BE and -# UTF16-LE with or without a BOM; support UTF-8 with a BOM; support -# UTF-32BE and UTF-32LE with or without a BOM; fixed crashing bug if no -# XML parsers are available; added support for 'Content-encoding: deflate'; -# send blank 'Accept-encoding: ' header if neither gzip nor zlib modules -# are available -#3.3 - 7/15/2004 - MAP - optimize EBCDIC to ASCII conversion; fix obscure -# problem tracking xml:base and xml:lang if element declares it, child -# doesn't, first grandchild redeclares it, and second grandchild doesn't; -# refactored date parsing; defined public registerDateHandler so callers -# can add support for additional date formats at runtime; added support -# for OnBlog, Nate, MSSQL, Greek, and Hungarian dates (ytrewq1); added -# zopeCompatibilityHack() which turns FeedParserDict into a regular -# dictionary, required for Zope compatibility, and also makes command- -# line debugging easier because pprint module formats real dictionaries -# better than dictionary-like objects; added NonXMLContentType exception, -# which is stored in bozo_exception when a feed is served with a non-XML -# media type such as 'text/plain'; respect Content-Language as default -# language if not xml:lang is present; cloud dict is now FeedParserDict; -# generator dict is now FeedParserDict; better tracking of xml:lang, -# including support for xml:lang='' to unset the current language; -# recognize RSS 1.0 feeds even when RSS 1.0 namespace is not the default -# namespace; don't overwrite final status on redirects (scenarios: -# redirecting to a URL that returns 304, redirecting to a URL that -# redirects to another URL with a different type of redirect); add -# support for HTTP 303 redirects -#4.0 - MAP - support for relative URIs in xml:base attribute; fixed -# encoding issue with mxTidy (phopkins); preliminary support for RFC 3229; -# support for Atom 1.0; support for iTunes extensions; new 'tags' for -# categories/keywords/etc. as array of dict -# {'term': term, 'scheme': scheme, 'label': label} to match Atom 1.0 -# terminology; parse RFC 822-style dates with no time; lots of other -# bug fixes diff --git a/src/calibre/utils/opensearch/query.py b/src/calibre/utils/opensearch/query.py index 31c37ca923..d87eb0145f 100644 --- a/src/calibre/utils/opensearch/query.py +++ b/src/calibre/utils/opensearch/query.py @@ -1,10 +1,17 @@ -from urlparse import urlparse, urlunparse -from urllib import urlencode -from cgi import parse_qs +# -*- coding: utf-8 -*- -class Query: - """Represents an opensearch query. Used internally by the Client to - construct an opensearch url to request. Really this class is just a +from __future__ import (unicode_literals, division, absolute_import, print_function) + +__license__ = 'GPL 3' +__copyright__ = '2006, Ed Summers ' +__docformat__ = 'restructuredtext en' + +from urlparse import urlparse, urlunparse, parse_qs +from urllib import urlencode + +class Query(object): + ''' + Represents an opensearch query Really this class is just a helper for substituting values into the macros in a format. format = 'http://beta.indeed.com/opensearch?q={searchTerms}&start={startIndex}&limit={count}' @@ -12,16 +19,17 @@ class Query: q.searchTerms('zx81') q.startIndex = 1 q.count = 25 - print q.to_url() - """ + print q.url() + ''' - standard_macros = ['searchTerms','count','startIndex','startPage', + standard_macros = ['searchTerms', 'count', 'startIndex', 'startPage', 'language', 'outputEncoding', 'inputEncoding'] def __init__(self, format): - """Create a query object by passing it the url format obtained + ''' + Create a query object by passing it the url format obtained from the opensearch Description. - """ + ''' self.format = format # unpack the url to a tuple @@ -37,7 +45,7 @@ class Query: for key,values in self.query_string.items(): # TODO eventually optional/required params should be # distinguished somehow (the ones with/without trailing ? - macro = values[0].replace('{','').replace('}','').replace('?','') + macro = values[0].replace('{', '').replace('}', '').replace('?', '') if macro in Query.standard_macros: self.macro_map[macro] = key diff --git a/src/calibre/utils/opensearch/results.py b/src/calibre/utils/opensearch/results.py deleted file mode 100644 index 1922848e22..0000000000 --- a/src/calibre/utils/opensearch/results.py +++ /dev/null @@ -1,131 +0,0 @@ -import osfeedparser - -class Results(object): - - def __init__(self, query, agent=None): - self.agent = agent - self._fetch(query) - self._iter = 0 - - def __iter__(self): - self._iter = 0 - return self - - def __len__(self): - return self.totalResults - - def next(self): - - # just keep going like the energizer bunny - while True: - - # return any item we haven't returned - if self._iter < len(self.items): - self._iter += 1 - return self.items[self._iter-1] - - # if there appears to be more to fetch - if \ - self.totalResults != 0 \ - and self.totalResults > self.startIndex + self.itemsPerPage - 1: - - # get the next query - next_query = self._get_next_query() - - # if we got one executed it and go back to the beginning - if next_query: - self._fetch(next_query) - # very important to reset this counter - # or else the return will fail - self._iter = 0 - - else: - raise StopIteration - - - def _fetch(self, query): - feed = osfeedparser.opensearch_parse(query.url(), agent=self.agent) - self.feed = feed - - # general channel stuff - channel = feed['feed'] - self.title = _pick(channel,'title') - self.link = _pick(channel,'link') - self.description = _pick(channel,'description') - self.language = _pick(channel,'language') - self.copyright = _pick(channel,'copyright') - - # get back opensearch specific values - self.totalResults = _pick(channel,'opensearch_totalresults',0) - self.startIndex = _pick(channel,'opensearch_startindex',1) - self.itemsPerPage = _pick(channel,'opensearch_itemsperpage',0) - - # alias items from the feed to our results object - self.items = feed['items'] - - # set default values if necessary - if self.startIndex == 0: - self.startIndex = 1 - if self.itemsPerPage == 0 and len(self.items) > 0: - self.itemsPerPage = len(self.items) - - # store away query for calculating next results - # if necessary - self.last_query = query - - - def _get_next_query(self): - # update our query to get the next set of records - query = self.last_query - - # use start page if the query supports it - if query.has_macro('startPage'): - # if the query already defined the startPage - # we just need to increment it - if hasattr(query, 'startPage'): - query.startPage += 1 - # to issue the first query startPage might not have - # been specified, so set it to 2 - else: - query.startPage = 2 - return query - - # otherwise the query should support startIndex - elif query.has_macro('startIndex'): - # if startIndex was used before we just add the - # items per page to it to get the next set - if hasattr(query, 'startIndex'): - query.startIndex += self.itemsPerPage - # to issue the first query the startIndex may have - # been left blank in that case we assume it to be - # the item just after the last one on this page - else: - query.startIndex = self.itemsPerPage + 1 - return query - - # doesn't look like there is another stage to this query - return None - - -# helper for pulling values out of a dictionary if they're there -# and returning a default value if they're not -def _pick(d,key,default=None): - - # get the value out - value = d.get(key) - - # if it wasn't there return the default - if value == None: - return default - - # if they want an int try to convert to an int - # and return default if it fails - if type(default) == int: - try: - return int(d[key]) - except: - return default - - # otherwise we're good to return the value - return value - diff --git a/src/calibre/utils/opensearch/url.py b/src/calibre/utils/opensearch/url.py index 665c024ef3..f05ec3205a 100644 --- a/src/calibre/utils/opensearch/url.py +++ b/src/calibre/utils/opensearch/url.py @@ -1,5 +1,15 @@ -class URL: - """Class for representing a URL in an opensearch v1.1 query""" +# -*- coding: utf-8 -*- + +from __future__ import (unicode_literals, division, absolute_import, print_function) + +__license__ = 'GPL 3' +__copyright__ = '2006, Ed Summers ' +__docformat__ = 'restructuredtext en' + +class URL(object): + ''' + Class for representing a URL in an opensearch v1.1 query + ''' def __init__(self, type='', template='', method='GET'): self.type = type From e4adfb044056b175d258974e67c377bd12fde3e4 Mon Sep 17 00:00:00 2001 From: John Schember Date: Sun, 26 Jun 2011 21:05:54 -0400 Subject: [PATCH 13/22] Store: opensearch fix showing price. --- src/calibre/gui2/store/opensearch_store.py | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/src/calibre/gui2/store/opensearch_store.py b/src/calibre/gui2/store/opensearch_store.py index 456b6a7461..e7aa30a85c 100644 --- a/src/calibre/gui2/store/opensearch_store.py +++ b/src/calibre/gui2/store/opensearch_store.py @@ -67,7 +67,7 @@ class OpenSearchStore(StorePlugin): s = SearchResult() - s.detail_item = ''.join(data.xpath('./*[local-name() = "id"]/text()')) + s.detail_item = ''.join(data.xpath('./*[local-name() = "id"]/text()')).strip() for link in data.xpath('./*[local-name() = "link"]'): rel = link.get('rel') @@ -83,12 +83,20 @@ class OpenSearchStore(StorePlugin): if type: ext = mimetypes.guess_extension(type) if ext: - ext = ext[1:].upper() + ext = ext[1:].upper().strip() s.downloads[ext] = href - s.formats = ', '.join(s.downloads.keys()) + s.formats = ', '.join(s.downloads.keys()).strip() + + s.title = ' '.join(data.xpath('./*[local-name() = "title"]//text()')).strip() + s.author = ', '.join(data.xpath('./*[local-name() = "author"]//*[local-name() = "name"]//text()')).strip() + + price_e = data.xpath('.//*[local-name() = "price"][1]') + if price_e: + price_e = price_e[0] + currency_code = price_e.get('currencycode', '') + price = ''.join(price_e.xpath('.//text()')).strip() + s.price = currency_code + ' ' + price + s.price = s.price.strip() - s.title = ' '.join(data.xpath('./*[local-name() = "title"]//text()')) - s.author = ', '.join(data.xpath('./*[local-name() = "author"]//*[local-name() = "name"]//text()')) - s.price = ' '.join(data.xpath('.//*[local-name() = "price"]//text()')) yield s From 075468484d482f27477aa8511f9d313df67e848e Mon Sep 17 00:00:00 2001 From: John Schember Date: Sun, 26 Jun 2011 21:07:31 -0400 Subject: [PATCH 14/22] ... --- src/calibre/gui2/store/opensearch_store.py | 1 - src/calibre/gui2/store/stores/archive_org_plugin.py | 6 ++++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/src/calibre/gui2/store/opensearch_store.py b/src/calibre/gui2/store/opensearch_store.py index e7aa30a85c..54fedbd002 100644 --- a/src/calibre/gui2/store/opensearch_store.py +++ b/src/calibre/gui2/store/opensearch_store.py @@ -19,7 +19,6 @@ from calibre.gui2 import open_url from calibre.gui2.store import StorePlugin from calibre.gui2.store.search_result import SearchResult from calibre.gui2.store.web_store_dialog import WebStoreDialog -#from calibre.utils.opensearch import Client from calibre.utils.opensearch.description import Description from calibre.utils.opensearch.query import Query diff --git a/src/calibre/gui2/store/stores/archive_org_plugin.py b/src/calibre/gui2/store/stores/archive_org_plugin.py index 208b4c1aba..691f819e8c 100644 --- a/src/calibre/gui2/store/stores/archive_org_plugin.py +++ b/src/calibre/gui2/store/stores/archive_org_plugin.py @@ -29,8 +29,11 @@ class ArchiveOrgStore(BasicStoreConfig, OpenSearchStore): s.drm = SearchResult.DRM_UNLOCKED yield s -''' def get_details(self, search_result, timeout): + ''' + The opensearch feed only returns a subset of formats that are available. + We want to get a list of all formats that the user can get. + ''' br = browser() with closing(br.open(search_result.detail_item, timeout=timeout)) as nf: idata = html.fromstring(nf.read()) @@ -38,4 +41,3 @@ class ArchiveOrgStore(BasicStoreConfig, OpenSearchStore): search_result.formats = formats.upper() return True -''' From f5c8e0c2643556767ef9ee4589baf804af326954 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 26 Jun 2011 20:39:35 -0600 Subject: [PATCH 15/22] Updated wprost --- recipes/wprost.recipe | 136 +++++++++++++++++++++--------------------- 1 file changed, 69 insertions(+), 67 deletions(-) diff --git a/recipes/wprost.recipe b/recipes/wprost.recipe index b317571981..b271665125 100644 --- a/recipes/wprost.recipe +++ b/recipes/wprost.recipe @@ -2,90 +2,92 @@ __license__ = 'GPL v3' __copyright__ = '2010, matek09, matek09@gmail.com' +__copyright__ = 'Modified 2011, Mariusz Wolek ' from calibre.web.feeds.news import BasicNewsRecipe import re class Wprost(BasicNewsRecipe): - EDITION = 0 - FIND_LAST_FULL_ISSUE = True - EXCLUDE_LOCKED = True - ICO_BLOCKED = 'http://www.wprost.pl/G/icons/ico_blocked.gif' + EDITION = 0 + FIND_LAST_FULL_ISSUE = True + EXCLUDE_LOCKED = True + ICO_BLOCKED = 'http://www.wprost.pl/G/icons/ico_blocked.gif' - title = u'Wprost' - __author__ = 'matek09' - description = 'Weekly magazine' - encoding = 'ISO-8859-2' - no_stylesheets = True - language = 'pl' - remove_javascript = True + title = u'Wprost' + __author__ = 'matek09' + description = 'Weekly magazine' + encoding = 'ISO-8859-2' + no_stylesheets = True + language = 'pl' + remove_javascript = True - remove_tags_before = dict(dict(name = 'div', attrs = {'id' : 'print-layer'})) - remove_tags_after = dict(dict(name = 'div', attrs = {'id' : 'print-layer'})) + remove_tags_before = dict(dict(name = 'div', attrs = {'id' : 'print-layer'})) + remove_tags_after = dict(dict(name = 'div', attrs = {'id' : 'print-layer'})) - '''keep_only_tags =[] - keep_only_tags.append(dict(name = 'table', attrs = {'id' : 'title-table'})) - keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-header'})) - keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-content'})) - keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'def element-autor'}))''' + '''keep_only_tags =[] + keep_only_tags.append(dict(name = 'table', attrs = {'id' : 'title-table'})) + keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-header'})) + keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-content'})) + keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'def element-autor'}))''' - preprocess_regexps = [(re.compile(r'style="display: none;"'), lambda match: ''), - (re.compile(r'display: block;'), lambda match: '')] + preprocess_regexps = [(re.compile(r'style="display: none;"'), lambda match: ''), + (re.compile(r'display: block;'), lambda match: ''), + (re.compile(r'\\\<\/table\>'), lambda match: ''), + (re.compile(r'\'), lambda match: ''), + (re.compile(r'\'), lambda match: ''), + (re.compile(r'\
'), lambda match: '')] + remove_tags =[] + remove_tags.append(dict(name = 'div', attrs = {'class' : 'def element-date'})) + remove_tags.append(dict(name = 'div', attrs = {'class' : 'def silver'})) + remove_tags.append(dict(name = 'div', attrs = {'id' : 'content-main-column-right'})) - remove_tags =[] - remove_tags.append(dict(name = 'div', attrs = {'class' : 'def element-date'})) - remove_tags.append(dict(name = 'div', attrs = {'class' : 'def silver'})) - remove_tags.append(dict(name = 'div', attrs = {'id' : 'content-main-column-right'})) - - - extra_css = ''' - .div-header {font-size: x-small; font-weight: bold} - ''' + extra_css = ''' + .div-header {font-size: x-small; font-weight: bold} + ''' #h2 {font-size: x-large; font-weight: bold} - def is_blocked(self, a): - if a.findNextSibling('img') is None: - return False - else: - return True + def is_blocked(self, a): + if a.findNextSibling('img') is None: + return False + else: + return True - def find_last_issue(self): - soup = self.index_to_soup('http://www.wprost.pl/archiwum/') - a = 0 - if self.FIND_LAST_FULL_ISSUE: - ico_blocked = soup.findAll('img', attrs={'src' : self.ICO_BLOCKED}) - a = ico_blocked[-1].findNext('a', attrs={'title' : re.compile('Zobacz spis tre.ci')}) - else: - a = soup.find('a', attrs={'title' : re.compile('Zobacz spis tre.ci')}) - self.EDITION = a['href'].replace('/tygodnik/?I=', '') - self.cover_url = a.img['src'] + def find_last_issue(self): + soup = self.index_to_soup('http://www.wprost.pl/archiwum/') + a = 0 + if self.FIND_LAST_FULL_ISSUE: + ico_blocked = soup.findAll('img', attrs={'src' : self.ICO_BLOCKED}) + a = ico_blocked[-1].findNext('a', attrs={'title' : re.compile('Zobacz spis tre.ci')}) + else: + a = soup.find('a', attrs={'title' : re.compile('Zobacz spis tre.ci')}) + self.EDITION = a['href'].replace('/tygodnik/?I=', '') + self.cover_url = a.img['src'] - def parse_index(self): - self.find_last_issue() - soup = self.index_to_soup('http://www.wprost.pl/tygodnik/?I=' + self.EDITION) - feeds = [] - for main_block in soup.findAll(attrs={'class':'main-block-s3 s3-head head-red3'}): - articles = list(self.find_articles(main_block)) - if len(articles) > 0: - section = self.tag_to_string(main_block) - feeds.append((section, articles)) - return feeds - - def find_articles(self, main_block): - for a in main_block.findAllNext( attrs={'style':['','padding-top: 15px;']}): - if a.name in "td": - break - if self.EXCLUDE_LOCKED & self.is_blocked(a): - continue - yield { - 'title' : self.tag_to_string(a), - 'url' : 'http://www.wprost.pl' + a['href'], - 'date' : '', - 'description' : '' - } + def parse_index(self): + self.find_last_issue() + soup = self.index_to_soup('http://www.wprost.pl/tygodnik/?I=' + self.EDITION) + feeds = [] + for main_block in soup.findAll(attrs={'class':'main-block-s3 s3-head head-red3'}): + articles = list(self.find_articles(main_block)) + if len(articles) > 0: + section = self.tag_to_string(main_block) + feeds.append((section, articles)) + return feeds + def find_articles(self, main_block): + for a in main_block.findAllNext( attrs={'style':['','padding-top: 15px;']}): + if a.name in "td": + break + if self.EXCLUDE_LOCKED & self.is_blocked(a): + continue + yield { + 'title' : self.tag_to_string(a), + 'url' : 'http://www.wprost.pl' + a['href'], + 'date' : '', + 'description' : '' + } From f0b58870f68f05f614ec9ce42436d4cd00010ae0 Mon Sep 17 00:00:00 2001 From: GRiker Date: Mon, 27 Jun 2011 06:30:16 -0600 Subject: [PATCH 16/22] Revised Apple customization dialog adding option specifying corresponding iTunes setting re: storage. Added code to store local copies to 'iTunes storage' subfolder within config_dir. Improved robustness in _discover_manual_sync_mode() responding to #802325 --- src/calibre/devices/apple/driver.py | 103 ++++++++++++++++------------ 1 file changed, 60 insertions(+), 43 deletions(-) diff --git a/src/calibre/devices/apple/driver.py b/src/calibre/devices/apple/driver.py index a3b1d05950..de895c65be 100644 --- a/src/calibre/devices/apple/driver.py +++ b/src/calibre/devices/apple/driver.py @@ -5,7 +5,7 @@ __copyright__ = '2010, Gregory Riker' __docformat__ = 'restructuredtext en' -import cStringIO, ctypes, datetime, os, re, sys, tempfile, time +import cStringIO, ctypes, datetime, os, re, shutil, sys, tempfile, time from calibre.constants import __appname__, __version__, DEBUG from calibre import fit_image, confirm_config_name from calibre.constants import isosx, iswindows @@ -119,11 +119,17 @@ class DriverBase(DeviceConfig, DevicePlugin): 'iBooks Category'), _('Cache covers from iTunes/iBooks') + ':::' + - _('Enable to cache and display covers from iTunes/iBooks') + _('Enable to cache and display covers from iTunes/iBooks'), + _("'Copy files to iTunes Media folder" u"\u2026" "' is enabled in iTunes Preferences|Advanced") + + ':::' + + _("

This setting should match your iTunes Preferences|Advanced setting.

" + "

Disabling will store copies of books transferred to iTunes in your calibre configuration directory.

" + "

Enabling indicates that iTunes is configured to store copies in your iTunes Media folder.

") ] EXTRA_CUSTOMIZATION_DEFAULT = [ True, True, + False, ] @@ -193,6 +199,7 @@ class ITUNES(DriverBase): # EXTRA_CUSTOMIZATION_MESSAGE indexes USE_SERIES_AS_CATEGORY = 0 CACHE_COVERS = 1 + USE_ITUNES_STORAGE = 2 OPEN_FEEDBACK_MESSAGE = _( 'Apple device detected, launching iTunes, please wait ...') @@ -281,6 +288,7 @@ class ITUNES(DriverBase): description_prefix = "added by calibre" ejected = False iTunes= None + iTunes_local_storage = None library_orphans = None log = Log() manual_sync_mode = False @@ -825,7 +833,7 @@ class ITUNES(DriverBase): # Confirm/create thumbs archive if not os.path.exists(self.cache_dir): if DEBUG: - self.log.info(" creating thumb cache '%s'" % self.cache_dir) + self.log.info(" creating thumb cache at '%s'" % self.cache_dir) os.makedirs(self.cache_dir) if not os.path.exists(self.archive_path): @@ -837,6 +845,17 @@ class ITUNES(DriverBase): if DEBUG: self.log.info(" existing thumb cache at '%s'" % self.archive_path) + # If enabled in config options, create/confirm an iTunes storage folder + if not self.settings().extra_customization[self.USE_ITUNES_STORAGE]: + self.iTunes_local_storage = os.path.join(config_dir,'iTunes storage') + if not os.path.exists(self.iTunes_local_storage): + if DEBUG: + self.log(" creating iTunes_local_storage at '%s'" % self.iTunes_local_storage) + os.mkdir(self.iTunes_local_storage) + else: + if DEBUG: + self.log(" existing iTunes_local_storage at '%s'" % self.iTunes_local_storage) + def remove_books_from_metadata(self, paths, booklists): ''' Remove books from the metadata list. This function must not communicate @@ -1281,50 +1300,27 @@ class ITUNES(DriverBase): if DEBUG: self.log.info(" ITUNES._add_new_copy()") - def _save_last_known_iTunes_storage(lb_added): - if isosx: - fp = lb_added.location().path - index = fp.rfind('/Books') + len('/Books') - last_known_iTunes_storage = fp[:index] - elif iswindows: - fp = lb_added.Location - index = fp.rfind('\Books') + len('\Books') - last_known_iTunes_storage = fp[:index] - dynamic['last_known_iTunes_storage'] = last_known_iTunes_storage - self.log.warning(" last_known_iTunes_storage: %s" % last_known_iTunes_storage) - db_added = None lb_added = None + # If using iTunes_local_storage, copy the file, redirect iTunes to use local copy + if not self.settings().extra_customization[self.USE_ITUNES_STORAGE]: + local_copy = os.path.join(self.iTunes_local_storage, str(metadata.uuid) + os.path.splitext(fpath)[1]) + shutil.copyfile(fpath,local_copy) + fpath = local_copy + if self.manual_sync_mode: ''' - This is the unsupported direct-connect mode. - In an attempt to avoid resetting the iTunes library Media folder, don't try to - add the book to iTunes if the last_known_iTunes_storage path is inaccessible. - This means that the path has to be set at least once, probably by using - 'Connect to iTunes' and doing a transfer. + Unsupported direct-connect mode. ''' self.log.warning(" unsupported direct connect mode") db_added = self._add_device_book(fpath, metadata) - last_known_iTunes_storage = dynamic.get('last_known_iTunes_storage', None) - if last_known_iTunes_storage is not None: - if os.path.exists(last_known_iTunes_storage): - if DEBUG: - self.log.warning(" iTunes storage online, adding to library") - lb_added = self._add_library_book(fpath, metadata) - else: - if DEBUG: - self.log.warning(" iTunes storage not online, can't add to library") - - if lb_added: - _save_last_known_iTunes_storage(lb_added) + lb_added = self._add_library_book(fpath, metadata) if not lb_added and DEBUG: self.log.warn(" failed to add '%s' to iTunes, iTunes Media folder inaccessible" % metadata.title) else: lb_added = self._add_library_book(fpath, metadata) - if lb_added: - _save_last_known_iTunes_storage(lb_added) - else: + if not lb_added: raise UserFeedback("iTunes Media folder inaccessible", details="Failed to add '%s' to iTunes" % metadata.title, level=UserFeedback.WARN) @@ -1520,7 +1516,7 @@ class ITUNES(DriverBase): else: self.log.error(" book_playlist not found") - if len(dev_books): + if dev_books is not None and len(dev_books): first_book = dev_books[0] if False: self.log.info(" determing manual mode by modifying '%s' by %s" % (first_book.name(), first_book.artist())) @@ -1551,7 +1547,7 @@ class ITUNES(DriverBase): dev_books = pl.Tracks break - if dev_books.Count: + if dev_books is not None and dev_books.Count: first_book = dev_books.Item(1) #if DEBUG: #self.log.info(" determing manual mode by modifying '%s' by %s" % (first_book.Name, first_book.Artist)) @@ -2526,7 +2522,15 @@ class ITUNES(DriverBase): self.log.info(" processing %s" % fp) if fp.startswith(prefs['library_path']): self.log.info(" '%s' stored in calibre database, not removed" % cached_book['title']) + elif not self.settings().extra_customization[self.USE_ITUNES_STORAGE] and \ + fp.startswith(self.iTunes_local_storage) and \ + os.path.exists(fp): + # Delete the copy in iTunes_local_storage + os.remove(fp) + if DEBUG: + self.log(" removing from iTunes_local_storage") else: + # Delete from iTunes Media folder if os.path.exists(fp): os.remove(fp) if DEBUG: @@ -2544,12 +2548,6 @@ class ITUNES(DriverBase): os.rmdir(author_storage_path) if DEBUG: self.log.info(" removing empty author directory") - ''' - else: - if DEBUG: - self.log.info(" author_storage_path not empty:") - self.log.info(" %s" % '\n'.join(author_files)) - ''' else: self.log.info(" '%s' does not exist at storage location" % cached_book['title']) @@ -2586,7 +2584,15 @@ class ITUNES(DriverBase): self.log.info(" processing %s" % fp) if fp.startswith(prefs['library_path']): self.log.info(" '%s' stored in calibre database, not removed" % cached_book['title']) + elif not self.settings().extra_customization[self.USE_ITUNES_STORAGE] and \ + fp.startswith(self.iTunes_local_storage) and \ + os.path.exists(fp): + # Delete the copy in iTunes_local_storage + os.remove(fp) + if DEBUG: + self.log(" removing from iTunes_local_storage") else: + # Delete from iTunes Media folder if os.path.exists(fp): os.remove(fp) if DEBUG: @@ -3234,6 +3240,17 @@ class ITUNES_ASYNC(ITUNES): if DEBUG: self.log.info(" existing thumb cache at '%s'" % self.archive_path) + # If enabled in config options, create/confirm an iTunes storage folder + if not self.settings().extra_customization[self.USE_ITUNES_STORAGE]: + self.iTunes_local_storage = os.path.join(config_dir,'iTunes storage') + if not os.path.exists(self.iTunes_local_storage): + if DEBUG: + self.log(" creating iTunes_local_storage at '%s'" % self.iTunes_local_storage) + os.mkdir(self.iTunes_local_storage) + else: + if DEBUG: + self.log(" existing iTunes_local_storage at '%s'" % self.iTunes_local_storage) + def sync_booklists(self, booklists, end_session=True): ''' Update metadata on device. From 02a69476e16f0f7cc986ab327ec15beef9807a09 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 27 Jun 2011 06:41:54 -0600 Subject: [PATCH 17/22] ... --- src/calibre/gui2/tag_browser/model.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/src/calibre/gui2/tag_browser/model.py b/src/calibre/gui2/tag_browser/model.py index 0e599ed431..17a228b6a7 100644 --- a/src/calibre/gui2/tag_browser/model.py +++ b/src/calibre/gui2/tag_browser/model.py @@ -224,6 +224,7 @@ class TagsModel(QAbstractItemModel): # {{{ self.row_map = [] self.root_item = self.create_node(icon_map=self.icon_state_map) self.db = None + self._build_in_progress = False self.reread_collapse_model({}, rebuild=False) def reread_collapse_model(self, state_map, rebuild=True): @@ -257,9 +258,15 @@ class TagsModel(QAbstractItemModel): # {{{ self.endResetModel() def rebuild_node_tree(self, state_map={}): + if self._build_in_progress: + print ('Tag Browser build already in progress') + traceback.print_stack() + return + self._build_in_progress = True self.beginResetModel() self._run_rebuild(state_map=state_map) self.endResetModel() + self._build_in_progress = False def _run_rebuild(self, state_map={}): for node in self.node_map.itervalues(): From 8c7c3acf99b64fec9e4df4fbc21803ba2e8576eb Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 27 Jun 2011 07:14:50 -0600 Subject: [PATCH 18/22] ... --- src/calibre/gui2/tag_browser/model.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/src/calibre/gui2/tag_browser/model.py b/src/calibre/gui2/tag_browser/model.py index 17a228b6a7..5589a1bcb4 100644 --- a/src/calibre/gui2/tag_browser/model.py +++ b/src/calibre/gui2/tag_browser/model.py @@ -262,6 +262,8 @@ class TagsModel(QAbstractItemModel): # {{{ print ('Tag Browser build already in progress') traceback.print_stack() return + #traceback.print_stack() + #print () self._build_in_progress = True self.beginResetModel() self._run_rebuild(state_map=state_map) From 4ce3217a2ea28543963a93ad8c26073add307081 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 27 Jun 2011 07:27:46 -0600 Subject: [PATCH 19/22] ... --- src/calibre/gui2/tag_browser/ui.py | 8 ++++---- src/calibre/gui2/tag_browser/view.py | 6 ++---- 2 files changed, 6 insertions(+), 8 deletions(-) diff --git a/src/calibre/gui2/tag_browser/ui.py b/src/calibre/gui2/tag_browser/ui.py index f7f724b118..7bfed8b35f 100644 --- a/src/calibre/gui2/tag_browser/ui.py +++ b/src/calibre/gui2/tag_browser/ui.py @@ -416,10 +416,10 @@ class TagBrowserWidget(QWidget): # {{{ self.tags_view.set_new_model(filter_categories_by=txt[1:]) self.current_find_position = None return - if model.get_filter_categories_by(): - self.tags_view.set_new_model(filter_categories_by=None) + if model.filter_categories_by: + model.filter_categories_by = None + self.tags_view.recount() self.current_find_position = None - model = self.tags_view.model() if not txt: return @@ -438,7 +438,7 @@ class TagBrowserWidget(QWidget): # {{{ self.current_find_position = \ model.find_item_node(key, txt, self.current_find_position) if self.current_find_position: - model.show_item_at_path(self.current_find_position, box=True) + self.tags_view.show_item_at_path(self.current_find_position, box=True) elif self.item_search.text(): self.not_found_label.setVisible(True) if self.tags_view.verticalScrollBar().isVisible(): diff --git a/src/calibre/gui2/tag_browser/view.py b/src/calibre/gui2/tag_browser/view.py index 4ff1227a6a..8d94bb6f34 100644 --- a/src/calibre/gui2/tag_browser/view.py +++ b/src/calibre/gui2/tag_browser/view.py @@ -71,7 +71,6 @@ class TagsView(QTreeView): # {{{ search_item_renamed = pyqtSignal() drag_drop_finished = pyqtSignal(object) restriction_error = pyqtSignal() - show_at_path = pyqtSignal() def __init__(self, parent=None): QTreeView.__init__(self, parent=None) @@ -96,8 +95,6 @@ class TagsView(QTreeView): # {{{ self.user_category_icon = QIcon(I('tb_folder.png')) self.delete_icon = QIcon(I('list_remove.png')) self.rename_icon = QIcon(I('edit-undo.png')) - self.show_at_path.connect(self.show_item_at_path, - type=Qt.QueuedConnection) self._model = TagsModel(self) self._model.search_item_renamed.connect(self.search_item_renamed) @@ -176,7 +173,8 @@ class TagsView(QTreeView): # {{{ state_map = self.get_state()[1] self.db.prefs.set('user_categories', user_cats) self._model.rebuild_node_tree(state_map=state_map) - self.show_at_path.emit('@'+nkey) + p = self._model.find_category_node('@'+nkey) + self.show_item_at_path(p) @property def match_all(self): From 60c877ff206d21add42e4436feeb183eaa3af3c6 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 27 Jun 2011 07:43:02 -0600 Subject: [PATCH 20/22] ... --- src/calibre/gui2/tag_browser/ui.py | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/src/calibre/gui2/tag_browser/ui.py b/src/calibre/gui2/tag_browser/ui.py index 7bfed8b35f..0b01e20154 100644 --- a/src/calibre/gui2/tag_browser/ui.py +++ b/src/calibre/gui2/tag_browser/ui.py @@ -91,10 +91,10 @@ class TagBrowserMixin(object): # {{{ # Add the new category user_cats[new_cat] = [] db.prefs.set('user_categories', user_cats) - self.tags_view.set_new_model() + self.tags_view.recount() m = self.tags_view.model() idx = m.index_for_path(m.find_category_node('@' + new_cat)) - m.show_item_at_index(idx) + self.tags_view.show_item_at_index(idx) # Open the editor on the new item to rename it if new_category_name is None: self.tags_view.edit(idx) @@ -111,7 +111,7 @@ class TagBrowserMixin(object): # {{{ for k in d.categories: db.field_metadata.add_user_category('@' + k, k) db.data.change_search_locations(db.field_metadata.get_search_terms()) - self.tags_view.set_new_model() + self.tags_view.recount() def do_delete_user_category(self, category_name): ''' @@ -144,7 +144,7 @@ class TagBrowserMixin(object): # {{{ elif k.startswith(category_name + '.'): del user_cats[k] db.prefs.set('user_categories', user_cats) - self.tags_view.set_new_model() + self.tags_view.recount() def do_del_item_from_user_cat(self, user_cat, item_name, item_category): ''' @@ -413,7 +413,8 @@ class TagBrowserWidget(QWidget): # {{{ txt = unicode(self.item_search.currentText()).strip() if txt.startswith('*'): - self.tags_view.set_new_model(filter_categories_by=txt[1:]) + model.filter_categories_by = txt[1:] + self.tags_view.recount() self.current_find_position = None return if model.filter_categories_by: @@ -437,6 +438,7 @@ class TagBrowserWidget(QWidget): # {{{ self.current_find_position = \ model.find_item_node(key, txt, self.current_find_position) + if self.current_find_position: self.tags_view.show_item_at_path(self.current_find_position, box=True) elif self.item_search.text(): From 900718355c13f861ca05cf5e101e023c9c431333 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 27 Jun 2011 08:11:46 -0600 Subject: [PATCH 21/22] Sanity check --- src/calibre/gui2/tag_browser/view.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/calibre/gui2/tag_browser/view.py b/src/calibre/gui2/tag_browser/view.py index 8d94bb6f34..64c08ea019 100644 --- a/src/calibre/gui2/tag_browser/view.py +++ b/src/calibre/gui2/tag_browser/view.py @@ -568,7 +568,7 @@ class TagsView(QTreeView): # {{{ def show_item_at_index(self, idx, box=False, position=QTreeView.PositionAtCenter): - if idx.isValid(): + if idx.isValid() and idx.data(Qt.UserRole).toPyObject() is not self._model.root_item: self.setCurrentIndex(idx) self.scrollTo(idx, position) self.setCurrentIndex(idx) From c33d7638275aa8063bdd25df9c267021311c404d Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 27 Jun 2011 08:16:42 -0600 Subject: [PATCH 22/22] ... --- src/calibre/gui2/tag_browser/view.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/src/calibre/gui2/tag_browser/view.py b/src/calibre/gui2/tag_browser/view.py index 64c08ea019..1fad4eb9a3 100644 --- a/src/calibre/gui2/tag_browser/view.py +++ b/src/calibre/gui2/tag_browser/view.py @@ -499,6 +499,8 @@ class TagsView(QTreeView): # {{{ return src_is_tb = event.mimeData().hasFormat('application/calibre+from_tag_browser') item = index.data(Qt.UserRole).toPyObject() + if item.type == TagTreeItem.ROOT: + return flags = self._model.flags(index) if item.type == TagTreeItem.TAG and flags & Qt.ItemIsDropEnabled: self.setDropIndicatorShown(not src_is_tb)