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

Sync to trunk.

Browse Source
This commit is contained in:
John Schember 2011-05-15 17:55:02 -04:00
commit d69621b71d
16 changed files with 390 additions and 164 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
recipes/bild_de.recipe Normal file
View File

@ -0,0 +1,46 @@
# -*- coding: utf-8 -*-
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'Bild.de'
__author__ = 'schuster'
oldest_article = 1
max_articles_per_feed = 50
no_stylesheets = True
use_embedded_content = False
language = 'de'
remove_javascript = True
# get cover from myspace
cover_url = 'http://a3.l3-images.myspacecdn.com/images02/56/0232f842170b4d349779f8379c27e073/l.jpg'
# set what to fetch on the site
remove_tags_before = dict(name = 'h2', attrs={'id':'cover'})
remove_tags_after = dict(name ='div', attrs={'class':'back'})
# thanx to kiklop74 for code (see sticky thread -> Recipes - Re-usable code)
# this one removes a lot of direct-link's
def preprocess_html(self, soup):
for alink in soup.findAll('a'):
if alink.string is not None:
tstr = alink.string
alink.replaceWith(tstr)
return soup
# remove the ad's
filter_regexps = [r'.\.smartadserver\.com']
def skip_ad_pages(self, soup):
return None
#get the real url behind .feedsportal.com and fetch the artikels
def get_article_url(self, article):
return article.get('id', article.get('guid', None))
#list of the rss source from www.bild.de
feeds = [(u'Überblick', u'http://rss.bild.de/bild.xml'),
(u'News', u'http://rss.bild.de/bild-news.xml'),
(u'Politik', u'http://rss.bild.de/bild-politik.xml'),
(u'Unterhaltung', u'http://rss.bild.de/bild-unterhaltung.xml'),
(u'Sport', u'http://rss.bild.de/bild-sport.xml'),
(u'Lifestyle', u'http://rss.bild.de/bild-lifestyle.xml'),
(u'Ratgeber', u'http://rss.bild.de/bild-ratgeber.xml')
]

2
recipes/dn_se.recipe
View File

@ -37,7 +37,7 @@ class DN_se(BasicNewsRecipe):
,(u'Kultur' , u'http://www.dn.se/kultur-rss' )
]
keep_only_tags = [dict(name='div', attrs={'id':'article'})]
keep_only_tags = [dict(name='div', attrs={'id':'article-content'})]
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div',attrs={'id':'byline'})
remove_tags = [

74
recipes/express_de.recipe Normal file
View File

@ -0,0 +1,74 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'Express.de'
__author__ = 'schuster'
oldest_article = 2
max_articles_per_feed = 50
no_stylesheets = True
use_embedded_content = False
language = 'de'
extra_css = '''
h2{font-family:Arial,Helvetica,sans-serif; font-size: x-small;}
h1{ font-family:Arial,Helvetica,sans-serif; font-size:x-large; font-weight:bold;}
'''
remove_javascript = True
remove_tags_befor = [dict(name='div', attrs={'class':'Datum'})]
remove_tags_after = [dict(name='div', attrs={'class':'MoreNews'})]
remove_tags = [dict(id='kalaydo'),
dict(id='Header'),
dict(id='Searchline'),
dict(id='MainNav'),
dict(id='Logo'),
dict(id='MainLinkSpacer'),
dict(id='MainLinks'),
dict(title='Diese Seite Bookmarken'),
dict(name='span'),
dict(name='div', attrs={'class':'spacer_leftneu'}),
dict(name='div', attrs={'class':'button kalaydologo'}),
dict(name='div', attrs={'class':'button stellenneu'}),
dict(name='div', attrs={'class':'button autoneu'}),
dict(name='div', attrs={'class':'button immobilienneu'}),
dict(name='div', attrs={'class':'button kleinanzeigen'}),
dict(name='div', attrs={'class':'button tiereneu'}),
dict(name='div', attrs={'class':'button ferienwohnungen'}),
dict(name='div', attrs={'class':'button inserierenneu'}),
dict(name='div', attrs={'class':'spacer_rightneu'}),
dict(name='div', attrs={'class':'spacer_rightcorner'}),
dict(name='div', attrs={'class':'HeaderMetaNav'}),
dict(name='div', attrs={'class':'HeaderSearchOption'}),
dict(name='div', attrs={'class':'HeaderSearch'}),
dict(name='div', attrs={'class':'sbutton'}),
dict(name='div', attrs={'class':'active'}),
]
def preprocess_html(self, soup):
for alink in soup.findAll('a'):
if alink.string is not None:
tstr = alink.string
alink.replaceWith(tstr)
return soup
feeds = [(u'Top-Themen', u'http://www.express.de/home/-/2126/2126/-/view/asFeed/-/index.xml'),
(u'Regional - Köln', u'http://www.express.de/regional/koeln/-/2856/2856/-/view/asFeed/-/index.xml'),
(u'Regional - Bonn', u'http://www.express.de/regional/bonn/-/2860/2860/-/view/asFeed/-/index.xml'),
(u'Regional - Düsseldorf', u'http://www.express.de/regional/duesseldorf/-/2858/2858/-/view/asFeed/-/index.xml'),
(u'Regional - Region', u'http://www.express.de/regional/-/2178/2178/-/view/asFeed/-/index.xml'),
(u'Sport-News', u'http://www.express.de/sport/-/2176/2176/-/view/asFeed/-/index.xml'),
(u'Fussball-News', u'http://www.express.de/sport/fussball/-/3186/3186/-/view/asFeed/-/index.xml'),
(u'1.FC Köln News', u'http://www.express.de/sport/fussball/fc-koeln/-/3192/3192/-/view/asFeed/-/index.xml'),
(u'Alemannia Aachen News', u'http://www.express.de/sport/fussball/alemannia/-/3290/3290/-/view/asFeed/-/index.xml'),
(u'Borussia M~Gladbach', u'http://www.express.de/sport/fussball/gladbach/-/3286/3286/-/view/asFeed/-/index.xml'),
(u'Fortuna D~Dorf', u'http://www.express.de/sport/fussball/fortuna/-/3292/3292/-/view/asFeed/-/index.xml'),
(u'Basketball News', u'http://www.express.de/sport/basketball/-/3190/3190/-/view/asFeed/-/index.xml'),
(u'Big Brother', u'http://www.express.de/news/promi-show/big-brother/-/2402/2402/-/view/asFeed/-/index.xml'),
]

73
recipes/faznet.recipe
View File

@ -1,51 +1,38 @@
__license__ = 'GPL v3'
__copyright__ = '2008-2009, Kovid Goyal <kovid at kovidgoyal.net>, Darko Miletic <darko at gmail.com>'
'''
Profile to download FAZ.net
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
from calibre.web.feeds.news import BasicNewsRecipe
class FazNet(BasicNewsRecipe):
title = 'FAZ NET'
__author__ = 'Kovid Goyal, Darko Miletic'
title = u'Faz.net'
__author__ = 'schuster'
remove_tags = [dict(attrs={'class':['right', 'ArrowLinkRight', 'ModulVerlagsInfo', 'left', 'Head']}),
dict(id=['BreadCrumbs', 'tstag', 'FazFooterPrint']),
dict(name=['script', 'noscript', 'style'])]
oldest_article = 2
description = 'Frankfurter Allgemeine Zeitung'
publisher = 'FAZ Electronic Media GmbH'
category = 'news, politics, Germany'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'de'
max_articles_per_feed = 30
no_stylesheets = True
encoding = 'utf-8'
remove_javascript = True
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'class':'Article'})]
remove_tags = [
dict(name=['object','link','embed','base'])
,dict(name='div', attrs={'class':['LinkBoxModulSmall','ModulVerlagsInfo']})
]
feeds = [ ('FAZ.NET', 'http://www.faz.net/s/Rub/Tpl~Epartner~SRss_.xml') ]
cover_url = 'http://www.faz.net/f30/Images/Logos/logo.gif'
def print_version(self, url):
article, sep, rest = url.partition('?')
return article.replace('.html', '~Afor~Eprint.html')
return url.replace('.html', '~Afor~Eprint.html')
feeds = [(u'Politik', u'http://www.faz.net/s/RubA24ECD630CAE40E483841DB7D16F4211/Tpl~Epartner~SRss_.xml'),
(u'Wirtschaft', u'http://www.faz.net/s/RubC9401175958F4DE28E143E68888825F6/Tpl~Epartner~SRss_.xml'),
(u'Feuilleton', u'http://www.faz.net/s/RubCC21B04EE95145B3AC877C874FB1B611/Tpl~Epartner~SRss_.xml'),
(u'Sport', u'http://www.faz.net/s/Rub9F27A221597D4C39A82856B0FE79F051/Tpl~Epartner~SRss_.xml'),
(u'Gesellschaft', u'http://www.faz.net/s/Rub02DBAA63F9EB43CEB421272A670A685C/Tpl~Epartner~SRss_.xml'),
(u'Finanzen', u'http://www.faz.net/s/Rub4B891837ECD14082816D9E088A2D7CB4/Tpl~Epartner~SRss_.xml'),
(u'Wissen', u'http://www.faz.net/s/Rub7F4BEE0E0C39429A8565089709B70C44/Tpl~Epartner~SRss_.xml'),
(u'Reise', u'http://www.faz.net/s/RubE2FB5CA667054BDEA70FB3BC45F8D91C/Tpl~Epartner~SRss_.xml'),
(u'Technik & Motor', u'http://www.faz.net/s/Rub01E4D53776494844A85FDF23F5707AD8/Tpl~Epartner~SRss_.xml'),
(u'Beruf & Chance', u'http://www.faz.net/s/RubB1E10A8367E8446897468EDAA6EA0504/Tpl~Epartner~SRss_.xml'),
(u'Kunstmarkt', u'http://www.faz.net/s/RubBC09F7BF72A2405A96718ECBFB68FBFE/Tpl~Epartner~SRss_.xml'),
(u'Immobilien ', u'http://www.faz.net/s/RubFED172A9E10F46B3A5F01B02098C0C8D/Tpl~Epartner~SRss_.xml'),
(u'Rhein-Main Zeitung', u'http://www.faz.net/s/RubABE881A6669742C2A5EBCB5D50D7EBEE/Tpl~Epartner~SRss_.xml'),
(u'Atomdebatte ', u'http://www.faz.net/s/Rub469C43057F8C437CACC2DE9ED41B7950/Tpl~Epartner~SRss_.xml')
]
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>'
soup.head.insert(0,mtag)
del soup.body['onload']
for item in soup.findAll(style=True):
del item['style']
return soup

111
recipes/golem_de.recipe
View File

@ -1,50 +1,60 @@
#!/usr/bin/env python
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
from calibre.web.feeds.news import BasicNewsRecipe
class golem_ger(BasicNewsRecipe):
title = u'Golem.de'
language = 'de'
__author__ = 'Kovid Goyal'
__author__ = 'schuster'
oldest_article = 7
max_articles_per_feed = 100
language = 'de'
lang = 'de-DE'
max_articles_per_feed = 10
no_stylesheets = True
encoding = 'iso-8859-1'
recursions = 1
match_regexps = [r'http://www.golem.de/.*.html']
use_embedded_content = False
language = 'de'
cover_url = 'http://www.e-energy.de/images/logo_golem.jpg'
masthead_url = 'http://www.golem.de/staticrl/images/logo.png'
extra_css = '''
h2{font-family:Arial,Helvetica,sans-serif; font-size: x-small;}
h1{ font-family:Arial,Helvetica,sans-serif; font-size:x-large; font-weight:bold;}
keep_only_tags = [
dict(name='h1', attrs={'class':'artikelhead'}),
dict(name='p', attrs={'class':'teaser'}),
dict(name='div', attrs={'class':'artikeltext'}),
dict(name='h2', attrs={'id':'artikelhead'}),
]
'''
remove_javascript = True
remove_tags_befor = [dict(name='header', attrs={'class':'cluster-header'})]
remove_tags_after = [dict(name='p', attrs={'class':'meta'})]
remove_tags = [dict(rel='nofollow'),
dict(name='header', attrs={'id':'header'}),
dict(name='div', attrs={'class':'dh1'}),
dict(name='label', attrs={'class':'implied'}),
dict(name='section', attrs={'id':'comments'}),
dict(name='li', attrs={'class':'gg_prebackcounterItem'}),
dict(name='li', attrs={'class':'gg_prebackcounterItem gg_embeddedIndexCounter'}),
dict(name='img', attrs={'class':'gg_embeddedIconRight gg_embeddedIconFS gg_cursorpointer'}),
dict(name='div', attrs={'target':'_blank'})
]
def get_browser(self, *args, **kwargs):
from calibre import browser
kwargs['user_agent'] = 'mozilla'
return browser(*args, **kwargs)
def get_article_url(self, article):
return article.get('id', article.get('guid', None))
remove_tags = [
dict(name='div', attrs={'id':['similarContent','topContentWrapper','storycarousel','aboveFootPromo','comments','toolbar','breadcrumbs','commentlink','sidebar','rightColumn']}),
dict(name='div', attrs={'class':['gg_embeddedSubText','gg_embeddedIndex gg_solid','gg_toOldGallery','golemGallery']}),
dict(name='img', attrs={'class':['gg_embedded','gg_embeddedIconRight gg_embeddedIconFS gg_cursorpointer']}),
dict(name='td', attrs={'class':['xsmall']}),
]
def preprocess_html(self, soup):
for alink in soup.findAll('a'):
if alink.string is not None:
tstr = alink.string
alink.replaceWith(tstr)
return soup
# remove_tags_after = [
# dict(name='div', attrs={'id':['contentad2']})
# ]
feeds = [
(u'Golem.de', u'http://rss.golem.de/rss.php?feed=ATOM1.0'),
(u'Audio/Video', u'http://rss.golem.de/rss.php?tp=av&feed=RSS2.0'),
feeds = [(u'Audio/Video', u'http://rss.golem.de/rss.php?tp=av&feed=RSS2.0'),
(u'Foto', u'http://rss.golem.de/rss.php?tp=foto&feed=RSS2.0'),
(u'Games', u'http://rss.golem.de/rss.php?tp=games&feed=RSS2.0'),
(u'Internet', u'http://rss.golem.de/rss.php?tp=inet&feed=RSS1.0'),
(u'Mobil', u'http://rss.golem.de/rss.php?tp=mc&feed=ATOM1.0'),
(u'Internet', u'http://rss.golem.de/rss.php?tp=inet&feed=RSS1.0'),
(u'Politik/Recht', u'http://rss.golem.de/rss.php?tp=pol&feed=ATOM1.0'),
(u'Handy', u'http://rss.golem.de/rss.php?tp=handy&feed=RSS2.0'),
(u'Internet', u'http://rss.golem.de/rss.php?tp=inet&feed=RSS2.0'),
(u'Mobile', u'http://rss.golem.de/rss.php?tp=mc&feed=RSS2.0'),
(u'OSS', u'http://rss.golem.de/rss.php?tp=oss&feed=RSS2.0'),
(u'Politik/Recht', u'http://rss.golem.de/rss.php?tp=pol&feed=RSS2.0'),
(u'Security', u'http://rss.golem.de/rss.php?tp=sec&feed=RSS2.0'),
(u'Desktop-Applikationen', u'http://rss.golem.de/rss.php?tp=apps&feed=RSS2.0'),
(u'Software-Entwicklung', u'http://rss.golem.de/rss.php?tp=dev&feed=RSS2.0'),
(u'Wirtschaft', u'http://rss.golem.de/rss.php?tp=wirtschaft&feed=RSS2.0'),
@ -53,31 +63,8 @@ class golem_ger(BasicNewsRecipe):
(u'Networld', u'http://rss.golem.de/rss.php?r=nw&feed=RSS2.0'),
(u'Entertainment', u'http://rss.golem.de/rss.php?r=et&feed=RSS2.0'),
(u'TK', u'http://rss.golem.de/rss.php?r=tk&feed=RSS2.0'),
(u'E-Commerce', u'http://rss.golem.de/rss.php?r=ec&feed=RSS2.0'),
(u'Unternehmen/Maerkte', u'http://rss.golem.de/rss.php?r=wi&feed=RSS2.0')
]
(u'Wirtschaft', u'http://rss.golem.de/rss.php?r=wi&feed=RSS2.0'),
(u'E-Commerce', u'http://rss.golem.de/rss.php?r=ec&feed=RSS2.0')
]
feeds = [
(u'Golem.de', u'http://rss.golem.de/rss.php?feed=ATOM1.0'),
(u'Mobil', u'http://rss.golem.de/rss.php?tp=mc&feed=feed=RSS2.0'),
(u'OSS', u'http://rss.golem.de/rss.php?tp=oss&feed=RSS2.0'),
(u'Politik/Recht', u'http://rss.golem.de/rss.php?tp=pol&feed=RSS2.0'),
(u'Desktop-Applikationen', u'http://rss.golem.de/rss.php?tp=apps&feed=RSS2.0'),
(u'Software-Entwicklung', u'http://rss.golem.de/rss.php?tp=dev&feed=RSS2.0'),
]
extra_css = '''
h1 {color:#0066CC;font-family:Arial,Helvetica,sans-serif; font-size:30px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:20px;margin-bottom:2 em;}
h2 {color:#4D4D4D;font-family:Arial,Helvetica,sans-serif; font-size:22px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:16px; }
h3 {color:#4D4D4D;font-family:Arial,Helvetica,sans-serif; font-size:x-small; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:normal; line-height:5px;}
h4 {color:#333333; font-family:Arial,Helvetica,sans-serif;font-size:13px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:13px; }
h5 {color:#333333; font-family:Arial,Helvetica,sans-serif; font-size:11px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:11px; text-transform:uppercase;}
.teaser {font-style:italic;font-size:12pt;margin-bottom:15pt;}
.xsmall{font-style:italic;font-size:x-small;}
.td{font-style:italic;font-size:x-small;}
img {align:left;}
'''

22
recipes/max_planck.recipe Normal file
View File

@ -0,0 +1,22 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'Max-Planck-Inst.'
__author__ = 'schuster'
remove_tags = [dict(attrs={'class':['clearfix', 'lens', 'col2_box_list', 'col2_box_teaser group_ext no_print', 'dotted_line', 'col2_box_teaser', 'box_image small', 'bold', 'col2_box_teaser no_print', 'print_kontakt']}),
dict(id=['ie_clearing', 'col2', 'col2_content']),
dict(name=['script', 'noscript', 'style'])]
oldest_article = 30
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'de'
remove_javascript = True
def print_version(self, url):
split_url = url.split("/")
print_url = 'http://www.mpg.de/print/' + split_url[3]
return print_url
feeds = [(u'Forschung', u'http://www.mpg.de/de/forschung.rss')]

29
recipes/ngz.recipe Normal file
View File

@ -0,0 +1,29 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'NGZ-online'
__author__ = 'schuster'
remove_tags_before = dict(id='bu')
remove_tags_after = dict(id='noblock')
remove_tags = [dict(attrs={'class':['articleTools', 'post-tools', 'side_tool', 'nextArticleLink clearfix', 'liketext']}),
dict(id=['footer', 'toolsRight', 'articleInline', 'navigation', 'archive', 'side_search', 'blog_sidebar', 'side_tool', 'side_index', 'Verlinken', 'vorheriger', 'LESERKOMMENTARE', 'bei facebook', 'bei twitter', 'Schreiben Sie jetzt Ihre Meinung:', 'Thema', 'Ihr Beitrag', 'Ihr Name', 'Ich möchte über weitere Lesermeinungen zu diesem Artikel per E-Mail informiert werden.', 'banneroben', 'bannerrechts', 'inserieren', 'stellen', 'auto', 'immobilien', 'kleinanzeige', 'tiere', 'ferienwohnung', 'NGZ Card', 'Mediengruppe RP', 'Werben', 'Newsletter', 'Wetter', 'RSS', 'Abo', 'Anzeigen', 'Redaktion', 'Schulprojekte', 'Gast', 'Mein NGZ', 'Nachrichten', 'Sport', 'Wirtschaft', 'Stadt-Infos', 'Bilderserien', 'Bookmarken', 'del.icio.us', 'Mister Wong', 'YiGG', 'Webnews', 'Shortnews', 'Twitter', 'Newsider', 'Facebook', 'StudiVZ/MeinVZ', 'Versenden', 'Drucken']),
dict(name=['script', 'noscript', 'style'])]
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'de'
remove_javascript = True
cover_url = 'http://www.rhein-kreis-neuss-macht-sport.de/sport/includes/bilder/ngz_logo.jpg'
def print_version(self, url):
return url + '?ot=de.circit.rpo.PopupPageLayout.ot'
feeds = [
(u'Grevenbroich', u'http://www.ngz-online.de/app/feed/rss/grevenbroich'),
(u'Kreis Neuss', u'http://www.ngz-online.de/app/feed/rss/rheinkreisneuss'),
(u'Dormagen', u'http://www.ngz-online.de/app/feed/rss/dormagen'),
(u'J\xfcchen', u'http://www.ngz-online.de/app/feed/rss/juechen'),
(u'Rommerskirchen', u'http://www.ngz-online.de/app/feed/rss/rommerskirchen')
]

22
recipes/pro_physik.recipe Normal file
View File

@ -0,0 +1,22 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'Pro Physik'
__author__ = 'schuster'
oldest_article = 4
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'de'
remove_javascript = True
cover_url = 'http://www.pro-physik.de/Phy/images/site/prophysik_logo1.jpg'
def print_version(self, url):
return url.replace('leadArticle.do', 'print.do')
feeds = [(u'Hightech', u'http://www.pro-physik.de/Phy/hightechfeed.xml'),
(u'Forschung', u'http://www.pro-physik.de/Phy/forschungfeed.xml'),
(u'Magazin', u'http://www.pro-physik.de/Phy/magazinfeed.xml')]

28
recipes/spektrum.recipe Normal file
View File

@ -0,0 +1,28 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'Spektrum (der Wissenschaft)'
__author__ = 'schuster'
oldest_article = 7
max_articles_per_feed = 100
language = 'de'
cover_url = 'http://upload.wikimedia.org/wikipedia/de/3/3b/Spektrum_der_Wissenschaft_Logo.svg'
remove_tags = [dict(attrs={'class':['hauptnaviPkt gainlayout', 'hauptnaviButton', 'suchButton', 'suchbegriffKasten', 'loginButton', 'subnavigation', 'artikelInfoLeiste gainlayout', 'artikelTools', 'nurLetzteSeite', 'link', 'boxUnterArtikel', 'leserbriefeBlock', 'boxTitel', 'boxInhalt', 'sehrklein', 'boxabstand', 'werbeboxinhalt', 'rbabstand', 'bildlinks', 'rechtebox', 'denkmalbox', 'denkmalfrage']}),
dict(id=['pflip', 'verlagsleiste', 'bereich', 'bannerVertikal', 'headerLogoLink', 'kopf', 'topNavi', 'headerSchnellsuche', 'headerSchnellsucheWarten', 'navigation', 'navigationL', 'navigationR', 'inhalt', 'rechtespalte', 'sdwboxenshop', 'shopboxen', 'fuss']),
dict(name=['naservice'])]
def print_version(self,url):
newurl = url.replace('artikel/', 'sixcms/detail.php?id=')
return newurl + '&_druckversion=1'
feeds = [(u'Spektrum der Wissenschaft', u'http://www.spektrum.de/artikel/982623'),
(u'SpektrumDirekt', u'http://www.spektrumdirekt.de/artikel/996406'),
(u'Sterne und Weltraum', u'http://www.astronomie-heute.de/artikel/865248'),
(u'Gehirn & Geist', u'http://www.gehirn-und-geist.de/artikel/982626'),
(u'epoc', u'http://www.epoc.de/artikel/982625')
]
filter_regexps = [r'ads\.doubleclick\.net']

24
recipes/technology_review_de.recipe Normal file
View File

@ -0,0 +1,24 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'Technology Review'
__author__ = 'schuster'
remove_tags_before = dict(id='keywords')
remove_tags_after = dict(id='kommentar')
remove_tags = [dict(attrs={'class':['navi_oben_pvg', 'navi_oben_tarifr', 'navi_oben_itm', 'navi_oben_eve', 'navi_oben_whi', 'navi_oben_abo', 'navi_oben_shop', 'navi_top_logo', 'navi_top_abschnitt', 'first']}),
dict(id=['footer', 'toolsRight', 'articleInline', 'navigation', 'archive', 'side_search', 'blog_sidebar', 'side_tool', 'side_index']),
dict(name=['script', 'noscript', 'style'])]
oldest_article = 4
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'de'
remove_javascript = True
def print_version(self, url):
return url + '?view=print'
feeds = [
(u'Technik News', u'http://www.heise.de/tr/news-atom.xml') ]

1
setup/installer/windows/__init__.py
View File

@ -32,7 +32,6 @@ class Win32(VMInstaller):
FREEZE_TEMPLATE = 'python -OO setup.py {freeze_command} --no-ice'
INSTALLER_EXT = 'msi'
SHUTDOWN_CMD = ['shutdown.exe', '-s', '-f', '-t', '0']
BUILD_BUILD = ['python setup.py kakasi',] + VMInstaller.BUILD_BUILD
def download_installer(self):
installer = self.installer()

29
setup/resources.py
View File

@ -6,10 +6,10 @@ __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
import os, cPickle, re, anydbm, shutil, marshal, zipfile, glob
import os, cPickle, re, shutil, marshal, zipfile, glob
from zlib import compress
from setup import Command, basenames, __appname__, iswindows
from setup import Command, basenames, __appname__
def get_opts_from_parser(parser):
def do_opt(opt):
@ -34,12 +34,12 @@ class Kakasi(Command):
self.records = {}
src = self.j(self.KAKASI_PATH, 'kakasidict.utf8')
dest = self.j(self.RESOURCES, 'localization',
'pykakasi','kanwadict2.db')
'pykakasi','kanwadict2.pickle')
base = os.path.dirname(dest)
if not os.path.exists(base):
os.makedirs(base)
if self.newer(dest, src) or iswindows:
if self.newer(dest, src):
self.info('\tGenerating Kanwadict')
for line in open(src, "r"):
@ -50,7 +50,7 @@ class Kakasi(Command):
dest = self.j(self.RESOURCES, 'localization',
'pykakasi','itaijidict2.pickle')
if self.newer(dest, src) or iswindows:
if self.newer(dest, src):
self.info('\tGenerating Itaijidict')
self.mkitaiji(src, dest)
@ -58,7 +58,7 @@ class Kakasi(Command):
dest = self.j(self.RESOURCES, 'localization',
'pykakasi','kanadict2.pickle')
if self.newer(dest, src) or iswindows:
if self.newer(dest, src):
self.info('\tGenerating kanadict')
self.mkkanadict(src, dest)
@ -75,7 +75,7 @@ class Kakasi(Command):
continue
pair = re.sub(r'\\u([0-9a-fA-F]{4})', lambda x:unichr(int(x.group(1),16)), line)
dic[pair[0]] = pair[1]
cPickle.dump(dic, open(dst, 'w'), protocol=-1) #pickle
cPickle.dump(dic, open(dst, 'wb'), protocol=-1) #pickle
def mkkanadict(self, src, dst):
dic = {}
@ -87,7 +87,7 @@ class Kakasi(Command):
continue
(alpha, kana) = line.split(' ')
dic[kana] = alpha
cPickle.dump(dic, open(dst, 'w'), protocol=-1) #pickle
cPickle.dump(dic, open(dst, 'wb'), protocol=-1) #pickle
def parsekdict(self, line):
line = line.decode("utf-8").strip()
@ -115,16 +115,11 @@ class Kakasi(Command):
self.records[key][kanji]=[(yomi, tail)]
def kanwaout(self, out):
try:
# Needed as otherwise anydbm tries to create a gdbm db when the db
# created on Unix is found
os.remove(out)
except:
pass
dic = anydbm.open(out, 'n')
for (k, v) in self.records.iteritems():
with open(out, 'wb') as f:
dic = {}
for k, v in self.records.iteritems():
dic[k] = compress(marshal.dumps(v))
dic.close()
cPickle.dump(dic, f, -1)
def clean(self):
kakasi = self.j(self.RESOURCES, 'localization', 'pykakasi')

8
src/calibre/ebooks/mobi/reader.py
View File

@ -690,6 +690,14 @@ class MobiReader(object):
lm = unit_convert('2em', 12, 500, 166)
lm = self.left_margins.get(tag, lm)
ti = self.text_indents.get(tag, ti)
try:
lm = float(lm)
except:
lm = 0.0
try:
ti = float(ti)
except:
ti = 0.0
return lm + ti
parent = tag

20
src/calibre/ebooks/unihandecode/pykakasi/jisyo.py
View File

@ -2,12 +2,8 @@
# jisyo.py
#
# Copyright 2011 Hiroshi Miura <miurahr@linux.com>
from cPickle import load
import anydbm,marshal
import cPickle, marshal
from zlib import decompress
import os
import calibre.utils.resources as resources
class jisyo (object):
kanwadict = None
@ -25,16 +21,14 @@ class jisyo (object):
def __init__(self):
if self.kanwadict is None:
dictpath = resources.get_path(os.path.join('localization','pykakasi','kanwadict2.db'))
self.kanwadict = anydbm.open(dictpath,'r')
self.kanwadict = cPickle.loads(
P('localization/pykakasi/kanwadict2.pickle', data=True))
if self.itaijidict is None:
itaijipath = resources.get_path(os.path.join('localization','pykakasi','itaijidict2.pickle'))
itaiji_pkl = open(itaijipath, 'rb')
self.itaijidict = load(itaiji_pkl)
self.itaijidict = cPickle.loads(
P('localization/pykakasi/itaijidict2.pickle', data=True))
if self.kanadict is None:
kanadictpath = resources.get_path(os.path.join('localization','pykakasi','kanadict2.pickle'))
kanadict_pkl = open(kanadictpath, 'rb')
self.kanadict = load(kanadict_pkl)
self.kanadict = cPickle.loads(
P('localization/pykakasi/kanadict2.pickle', data=True))
def load_jisyo(self, char):
try:#python2

5
src/calibre/gui2/actions/preferences.py
View File

@ -19,8 +19,9 @@ class PreferencesAction(InterfaceAction):
def genesis(self):
pm = QMenu()
acname = _('Change calibre behavior') if isosx else _('Preferences')
pm.addAction(QIcon(I('config.png')), acname, self.do_config)
pm.addAction(QIcon(I('config.png')), _('Preferences'), self.do_config)
if isosx:
pm.addAction(QIcon(I('config.png')), _('Change calibre behavior'), self.do_config)
pm.addAction(QIcon(I('wizard.png')), _('Run welcome wizard'),
self.gui.run_wizard)
if not DEBUG:

14
src/calibre/utils/titlecase.py
View File

@ -10,7 +10,6 @@ License: http://www.opensource.org/licenses/mit-license.php
import re
from calibre.utils.icu import capitalize
from calibre.utils.config import prefs
__all__ = ['titlecase']
__version__ = '0.5'
@ -31,6 +30,17 @@ ALL_CAPS = re.compile(r'^[A-Z\s%s]+$' % PUNCT)
UC_INITIALS = re.compile(r"^(?:[A-Z]{1}\.{1}|[A-Z]{1}\.{1}[A-Z]{1})+$")
MAC_MC = re.compile(r"^([Mm]a?c)(.+)")
_lang = None
def lang():
global _lang
if _lang is None:
from calibre.utils.localization import get_lang
_lang = get_lang().lower()
return _lang
def titlecase(text):
"""
@ -68,7 +78,7 @@ def titlecase(text):
line.append(icu_lower(word))
continue
if prefs['language'].lower().startswith('en'):
if lang().startswith('en'):
match = MAC_MC.match(word)
if match and not match.group(2)[:3] in ('hin', 'ht'):
line.append("%s%s" % (capitalize(match.group(1)),