Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

RTF Output: Fix invalid RTF being produced when the text contains a double backslash. Fixes #1268118 [epub converted produces invalid .rtf file](https://bugs.launchpad.net/calibre/+bug/1268118)

Browse Source 
Also updates to various Get Books plugins

Merge branch 'master' of https://github.com/user-none/calibre
This commit is contained in:
Kovid Goyal 2014-02-24 08:24:04 +05:30
commit e5b381f460
12 changed files with 47 additions and 152 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/calibre/customize/builtins.py
View File

@ -1439,15 +1439,6 @@ class StoreEbooksGratuitsStore(StoreBase):
# formats = ['EPUB', 'PDF']
# affiliate = True
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.' # noqa
actual_plugin = 'calibre.gui2.store.stores.eharlequin_plugin:EHarlequinStore'
headquarters = 'CA'
formats = ['EPUB', 'PDF']
affiliate = True
class StoreEKnigiStore(StoreBase):
name = u'еКниги'
author = 'Alex Stanev'
@ -1734,7 +1725,6 @@ plugins += [
StoreEbookpointStore,
StoreEbookscomStore,
StoreEbooksGratuitsStore,
StoreEHarlequinStore,
StoreEKnigiStore,
StoreEmpikStore,
StoreFeedbooksStore,

1
src/calibre/ebooks/rtf/rtfml.py
View File

@ -71,6 +71,7 @@ def txt2rtf(text):
# Escape { and } in the text.
text = text.replace('{', r'\'7b')
text = text.replace('}', r'\'7d')
text = text.replace('\\', r'\'5c')
if not isinstance(text, unicode):
return text

4
src/calibre/gui2/store/stores/amazon_ca_plugin.py
View File

@ -55,7 +55,7 @@ class AmazonCAKindleStore(StorePlugin):
'.//ul[contains(@class, "rsltGridList")]'
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
cover_xpath = './/img[contains(@class, "productImage")]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = (
@ -80,7 +80,7 @@ class AmazonCAKindleStore(StorePlugin):
'.//ul[contains(@class, "rsltL")]'
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
cover_xpath = './/img[contains(@class, "productImage")]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = (

2
src/calibre/gui2/store/stores/amazon_de_plugin.py
View File

@ -94,7 +94,7 @@ class AmazonDEKindleStore(StorePlugin):
'.//ul[contains(@class, "rsltL")]'
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
cover_xpath = './/img[contains(@class, "productImage")]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = (

2
src/calibre/gui2/store/stores/amazon_es_plugin.py
View File

@ -93,7 +93,7 @@ class AmazonESKindleStore(StorePlugin):
'.//ul[contains(@class, "rsltL")]'
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
cover_xpath = './/img[contains(@class, "productImage")]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = (

2
src/calibre/gui2/store/stores/amazon_fr_plugin.py
View File

@ -90,7 +90,7 @@ class AmazonFRKindleStore(StorePlugin):
'.//ul[contains(@class, "rsltL")]'
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
cover_xpath = './/img[contains(@class, "productImage")]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = (

2
src/calibre/gui2/store/stores/amazon_it_plugin.py
View File

@ -93,7 +93,7 @@ class AmazonITKindleStore(StorePlugin):
'.//ul[contains(@class, "rsltL")]'
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
cover_xpath = './/img[contains(@class, "productImage")]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = (

6
src/calibre/gui2/store/stores/amazon_plugin.py
View File

@ -1,7 +1,7 @@
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division, absolute_import, print_function)
store_version = 4 # Needed for dynamic plugin loading
store_version = 5 # Needed for dynamic plugin loading
__license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
@ -134,7 +134,7 @@ class AmazonKindleStore(StorePlugin):
'.//ul[contains(@class, "rsltGridList")]'
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
cover_xpath = './/img[contains(@class, "productImage")]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = (
@ -159,7 +159,7 @@ class AmazonKindleStore(StorePlugin):
'.//ul[contains(@class, "rsltL")]'
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
cover_xpath = './/img[contains(@class, "productImage")]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = (

2
src/calibre/gui2/store/stores/amazon_uk_plugin.py
View File

@ -97,7 +97,7 @@ class AmazonUKKindleStore(StorePlugin):
'.//ul[contains(@class, "rsltL")]'
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
cover_xpath = './/img[contains(@class, "productImage")]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = (

91
src/calibre/gui2/store/stores/eharlequin_plugin.py
View File

@ -1,91 +0,0 @@
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division, absolute_import, print_function)
store_version = 1 # Needed for dynamic plugin loading
__license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
import re
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.search_result import SearchResult
from calibre.gui2.store.web_store_dialog import WebStoreDialog
class EHarlequinStore(BasicStoreConfig, StorePlugin):
def open(self, parent=None, detail_item=None, external=False):
url = 'http://www.harlequin.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_()
def search(self, query, max_results=10, timeout=60):
url = 'http://ebooks.eharlequin.com/BANGSearch.dll?Type=FullText&FullTextField=All&FullTextCriteria=' + 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('//table[not(.//@class="sidelink")]/tr[.//ul[@id="details"]]'):
if counter <= 0:
break
id = ''.join(data.xpath('.//ul[@id="details"]/li[@id="title-results"]/a/@href'))
if not id:
continue
title = ''.join(data.xpath('.//ul[@id="details"]/li[@id="title-results"]/a/text()'))
author = ''.join(data.xpath('.//ul[@id="details"]/li[@id="author"][1]//a/text()'))
price = ''.join(data.xpath('.//div[@class="ourprice"]/font/text()'))
cover_url = ''.join(data.xpath('.//a[@href="%s"]/img/@src' % id))
counter -= 1
s = SearchResult()
s.cover_url = cover_url
s.title = title.strip()
s.author = author.strip()
s.price = price.strip()
s.detail_item = 'http://ebooks.eharlequin.com/' + id.strip()
s.formats = 'EPUB'
yield s
def get_details(self, search_result, timeout):
url = 'http://ebooks.eharlequin.com/en/ContentDetails.htm?ID='
mo = re.search(r'\?ID=(?P<id>.+)', search_result.detail_item)
if mo:
id = mo.group('id')
if not id:
return
br = browser()
with closing(br.open(url + id, timeout=timeout)) as nf:
idata = html.fromstring(nf.read())
drm = SearchResult.DRM_UNKNOWN
if idata.xpath('boolean(//div[@class="drm_head"])'):
if idata.xpath('boolean(//td[contains(., "Copy") and contains(., "not")])'):
drm = SearchResult.DRM_LOCKED
else:
drm = SearchResult.DRM_UNLOCKED
search_result.drm = drm
return True

37
src/calibre/gui2/store/stores/kobo_plugin.py
View File

@ -1,7 +1,7 @@
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division, absolute_import, print_function)
store_version = 2 # Needed for dynamic plugin loading
store_version = 3 # Needed for dynamic plugin loading
__license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
@ -9,7 +9,6 @@ __docformat__ = 'restructuredtext en'
import random
import urllib
import urllib2
from contextlib import closing
from lxml import html
@ -49,44 +48,44 @@ class KoboStore(BasicStoreConfig, StorePlugin):
d.exec_()
def search(self, query, max_results=10, timeout=60):
url = 'http://www.kobobooks.com/search/search.html?q=' + urllib2.quote(query)
url = 'http://www.kobobooks.com/search/search.html?q=' + urllib.quote_plus(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="SCShortCoverList"]/li'):
for data in doc.xpath('//ul[contains(@class, "flowview-items")]/li'):
if counter <= 0:
break
id = ''.join(data.xpath('.//div[@class="SearchImageContainer"]/a[1]/@href'))
id = ''.join(data.xpath('./a[contains(@class, "block-link")]/@href'))
if not id:
continue
try:
id = id.split('?', 1)[0]
except:
continue
id = id[1:]
price = ''.join(data.xpath('.//span[@class="KV2OurPrice"]/strong/text()'))
if not price:
price = '$0.00'
price = ''.join(data.xpath('.//a[contains(@class, "primary-button")]//text()'))
cover_url = ''.join(data.xpath('.//div[@class="SearchImageContainer"]//img[1]/@src'))
cover_url = ''.join(data.xpath('.//img[1]/@src'))
cover_url = 'http:%s' % cover_url
title = ''.join(data.xpath('.//div[@class="SCItemHeader"]//a[1]/text()'))
author = ', '.join(data.xpath('.//div[@class="SCItemSummary"]//span[contains(@class, "Author")]//a/text()'))
drm = data.xpath('boolean(.//span[@class="SCAvailibilityFormatsText" and not(contains(text(), "DRM-Free"))])')
title = ''.join(data.xpath('.//p[contains(@class, "flowview-item-title")]//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 = 'http://www.kobobooks.com/' + id.strip()
s.drm = SearchResult.DRM_LOCKED if drm else SearchResult.DRM_UNLOCKED
s.detail_item = 'http://store.kobobooks.com/' + id.strip()
s.formats = 'EPUB'
s.drm = SearchResult.DRM_UNKNOWN
yield s
def get_details(self, search_result, timeout):
br = browser()
with closing(br.open(search_result.detail_item, timeout=timeout)) as nf:
idata = html.fromstring(nf.read())
search_result.author = ', '.join(idata.xpath('.//h2[contains(@class, "author")]//a/text()'))
return True

40
src/calibre/gui2/store/stores/smashwords_plugin.py
View File

@ -1,7 +1,7 @@
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division, absolute_import, print_function)
store_version = 1 # Needed for dynamic plugin loading
store_version = 2 # Needed for dynamic plugin loading
__license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
@ -54,36 +54,32 @@ class SmashwordsStore(BasicStoreConfig, StorePlugin):
counter = max_results
with closing(br.open(url, timeout=timeout)) as f:
doc = html.fromstring(f.read())
for data in doc.xpath('//div[@id="pageCenterContent"]//div[@class="bookCoverImg"]'):
for data in doc.xpath('//div[@id="pageCenterContent"]//div[@class="library-book"]'):
if counter <= 0:
break
data = html.fromstring(html.tostring(data))
id = None
id_a = data.xpath('//a[@class="bookTitle"]')
id_a = ''.join(data.xpath('//a[contains(@class, "library-title")]/@href'))
if id_a:
id = id_a[0].get('href', None)
if id:
id = id.split('/')[-1]
id = id_a.split('/')[-1]
if not id:
continue
cover_url = ''
c_url = data.get('style', None)
if c_url:
mo = re.search(r'http://[^\'"]+', c_url)
if mo:
cover_url = mo.group()
cover_url = ''.join(data.xpath('//img[contains(@class, "book-list-image")]/@src'))
title = ''.join(data.xpath('//a[@class="bookTitle"]/text()'))
subnote = ''.join(data.xpath('//span[@class="subnote"]/text()'))
author = ''.join(data.xpath('//span[@class="subnote"]//a[1]//text()'))
if '$' in subnote:
price = subnote.partition('$')[2]
price = price.split(u'\xa0')[0]
price = '$' + price
else:
price = '$0.00'
title = ''.join(data.xpath('.//a[contains(@class, "library-title")]/text()'))
author = ''.join(data.xpath('.//div[@class="subnote"]//a[1]//text()'))
price = ''.join(data.xpath('.//div[@class="subnote"]//text()'))
if 'Price:' in price:
try:
price = price.partition('Price:')[2]
price = re.sub('\s', ' ', price).strip()
price = price.split(' ')[0]
price = price.strip()
except:
price = 'Unknown'
counter -= 1
@ -103,5 +99,5 @@ class SmashwordsStore(BasicStoreConfig, StorePlugin):
br = browser()
with closing(br.open(url + search_result.detail_item, timeout=timeout)) as nf:
idata = html.fromstring(nf.read())
search_result.formats = ', '.join(list(set(idata.xpath('//td//b//text()'))))
search_result.formats = ', '.join(list(set(idata.xpath('//p//abbr//text()'))))
return True