Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-31 14:33:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

KG updates pre-6.36

Browse Source
This commit is contained in:
GRiker 2010-01-25 09:13:56 -07:00
commit 345e752714
4 changed files with 77 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
resources/images/news/nursingtimes.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 788 B

7
resources/recipes/kidney.recipe
View File

@ -58,7 +58,7 @@ class JASN(BasicNewsRecipe):
# To parse artice toc
def parse_index(self):
parse_soup = self.jasn_get_index()
div = parse_soup.find(id='tocBody')
current_section = None
@ -91,7 +91,7 @@ class JASN(BasicNewsRecipe):
feeds.append((current_section, current_articles))
return feeds
def preprocess_html(self, soup):
@ -112,4 +112,5 @@ class JASN(BasicNewsRecipe):
return soup

67
resources/recipes/nursingtimes.recipe Normal file
View File

@ -0,0 +1,67 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.nursingtimes.net
'''
import urllib
from calibre.web.feeds.recipes import BasicNewsRecipe
class NursingTimes(BasicNewsRecipe):
title = 'Nursing Times'
__author__ = 'Darko Miletic'
description = 'Nursing practice, NHS and health care news'
oldest_article = 8
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
publisher = 'emap'
category = 'news, health, nursing, UK'
language = 'en-UK'
needs_subscription = True
LOGIN = 'http://www.nursingtimes.net/sign-in'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
def get_browser(self):
br = BasicNewsRecipe.get_browser()
br.open(self.LOGIN)
if self.username is not None and self.password is not None:
data = urllib.urlencode({ 'campaigncode' :'0'
,'referrer' :''
,'security_text':''
,'SIemail' :self.username
,'passWord' :self.password
,'LoginButton.x':'27'
,'LoginButton.y':'13'
})
br.open(self.LOGIN,data)
return br
keep_only_tags = [dict(name='div', attrs={'class':'storytext'})]
remove_tags = [
dict(name=['object','link','script','iframe'])
,dict(name='div',attrs={'id':'comments_form'})
]
remove_tags_after = dict(name='div',attrs={'id':'comments_form'})
feeds = [
(u'Breaking News', u'http://www.nursingtimes.net/XmlServers/navsectionRSS.aspx?navsectioncode=1')
,(u'Practice', u'http://www.nursingtimes.net/XmlServers/navsectionRSS.aspx?navsectioncode=512')
,(u'Behind the headlines', u'http://www.nursingtimes.net/XmlServers/navsectionRSS.aspx?navsectioncode=468')
,(u'Analysis', u'http://www.nursingtimes.net/XmlServers/navsectionRSS.aspx?navsectioncode=62')
,(u'Acute care news', u'http://www.nursingtimes.net/XmlServers/navsectionRSS.aspx?navsectioncode=5')
,(u'Primary vare news', u'http://www.nursingtimes.net/XmlServers/navsectionRSS.aspx?navsectioncode=231')
,(u'Mental Health news', u'http://www.nursingtimes.net/XmlServers/navsectionRSS.aspx?navsectioncode=27')
,(u'Management news', u'http://www.nursingtimes.net/XmlServers/navsectionRSS.aspx?navsectioncode=32')
,(u"Older people's nursing news", u'http://www.nursingtimes.net/XmlServers/navsectionRSS.aspx?navsectioncode=181')
,(u'Respiratory news', u'http://www.nursingtimes.net/XmlServers/navsectionRSS.aspx?navsectioncode=177')
,(u'Wound care news', u'http://www.nursingtimes.net/XmlServers/navsectionRSS.aspx?navsectioncode=182')
]

18
src/calibre/library/catalog.py
View File

@ -3,15 +3,11 @@ import os, re, shutil, htmlentitydefs
from collections import namedtuple
from xml.sax.saxutils import escape
from PyQt4.Qt import *
from calibre import filesystem_encoding
from calibre.customize import CatalogPlugin
from calibre.customize.conversion import OptionRecommendation, DummyReporter
from calibre.ebooks.BeautifulSoup import BeautifulSoup, BeautifulStoneSoup, Tag, NavigableString
from calibre.ptempfile import PersistentTemporaryDirectory
from calibre.customize.conversion import OptionRecommendation, DummyReporter
from calibre import filesystem_encoding, prints
from calibre.utils.logging import Log
FIELDS = ['all', 'author_sort', 'authors', 'comments',
@ -512,7 +508,7 @@ class EPUB_MOBI(CatalogPlugin):
self.__verbose = opts.verbose
self.opts.log.info("CatalogBuilder(): Generating %s %s"% \
(self.opts.fmt,
(self.opts.fmt,
"for %s" % self.opts.output_profile if self.opts.output_profile \
else ''))
# Accessors
@ -912,7 +908,7 @@ class EPUB_MOBI(CatalogPlugin):
if author[0] == current_author[0]:
self.opts.log.warn("Warning: multiple entries for Author '%s' with differing Author Sort metadata:" % author[0])
self.opts.log.warn(" '%s' != '%s'" % (author[1], current_author[1]))
# New author, save the previous author/sort/count
unique_authors.append((current_author[0], current_author[1].title(),
books_by_current_author))
@ -933,8 +929,8 @@ class EPUB_MOBI(CatalogPlugin):
if False and self.verbose:
self.opts.log.info("\nfetchBooksByauthor(): %d unique authors" % len(unique_authors))
for author in unique_authors:
self.opts.log.info((u" %-50s %-25s %2d" % (author[0][0:45], author[1][0:20],
author[2])).encode('utf-8'))
self.opts.log.info((u" %-50s %-25s %2d" % (author[0][0:45], author[1][0:20],
author[2])).encode('utf-8'))
self.authors = unique_authors
def generateHTMLDescriptions(self):
@ -977,7 +973,7 @@ class EPUB_MOBI(CatalogPlugin):
authorTag.insert(1, aTag)
'''
# Insert the unlinked genres.
# Insert the unlinked genres.
if 'tags' in title:
tagsTag = body.find(attrs={'class':'tags'})
emTag = Tag(soup,"em")
@ -1404,7 +1400,7 @@ class EPUB_MOBI(CatalogPlugin):
self.generateThumbnail(title, image_dir, thumb_file)
else:
# Use default cover
if self.verbose:
if self.verbose:
self.opts.log.warn(" using default cover for '%s'" % \
(title['title']))
# Check to make sure default is current
@ -2282,8 +2278,6 @@ class EPUB_MOBI(CatalogPlugin):
# The 21-Day Consciousness Cleanse
title_words = title.split(' ')
if title_words[0].lower() in ['the','a','an']:
stop_word = title_words.pop(0)
# Scan for numbers in each word clump
translated = []