diff --git a/Changelog.yaml b/Changelog.yaml index bfa5a443da..478e6a311b 100644 --- a/Changelog.yaml +++ b/Changelog.yaml @@ -19,6 +19,60 @@ # new recipes: # - title: +- version: 0.8.27 + date: 2011-11-18 + + new features: + - title: "Drivers for the Kindle Fire and the Nook Tablet" + tickets: [890918] + + - title: "Conversion: Add an option under Look & Feel to remove specified style information (CSS) from the document during conversion." + tickets: [871384] + + - title: "Add an option in the bulk metadata edit dialog to restore the pre-conversion files for many books with a single click." + tickets: [886116] + + - title: "Jobs list: Add the ability to search for and to hide jobs, useful if you have run a lot of jobs and the list is getting crowded." + tickets: [883734] + + - title: "Book jacket generation: Add ability to customize the book jacket template and add custom columns into the jacket." + tickets: [889912] + + - title: "MOBI Input: Performance improvement when viewing/converting a file with a lot of links" + + bug fixes: + - title: "Fix regression in 0.8.26 that broke disabling the update of particular fields during a bulk metadata download." + tickets: [889696] + + - title: "Get Books: Fix DRM status for legimi" + + - title: "When parsing for lxml via BeatifulSoup, use the calibre modified copy of BeautifulSoup (more robust)." + tickets: [889890] + + - title: "HTML Input: Handle double encoded URLs in img tags" + tickets: [889323] + + improved recipes: + - Various Polish recipes + - Academia Catavencu + - El Periodico de Aragon + - Weblogs SL + - Folha de Sao Paolo (subscription) + + new recipes: + - title: News on Japan + author: Krittika Goyal + + - title: Formula AS + author: Silviu Cotoara + + - title: Various Turkish news sources + author: Osman Kaysan + + - title: Infra.pl and Spider's Web + author: fenuks + + - version: 0.8.26 date: 2011-11-12 diff --git a/recipes/gosc_niedzielny.recipe b/recipes/gosc_niedzielny.recipe index 1538e7fc2c..6a99411244 100644 --- a/recipes/gosc_niedzielny.recipe +++ b/recipes/gosc_niedzielny.recipe @@ -12,7 +12,6 @@ class GN(BasicNewsRecipe): EDITION = 0 __author__ = 'Piotr Kontek' - title = u'Gość niedzielny' description = 'Weekly magazine' encoding = 'utf-8' no_stylesheets = True @@ -20,6 +19,8 @@ class GN(BasicNewsRecipe): remove_javascript = True temp_files = [] simultaneous_downloads = 1 + masthead_url = 'http://gosc.pl/files/11/03/12/949089_top.gif' + title = u'Gość niedzielny' articles_are_obfuscated = True @@ -64,7 +65,6 @@ class GN(BasicNewsRecipe): if img != None: a = img.parent self.EDITION = a['href'] - self.title = img['alt'] self.cover_url = 'http://www.gosc.pl' + img['src'] if not first: break diff --git a/recipes/heise_online.recipe b/recipes/heise_online.recipe index 338b54782c..4d82570698 100644 --- a/recipes/heise_online.recipe +++ b/recipes/heise_online.recipe @@ -1,11 +1,11 @@ from calibre.web.feeds.news import BasicNewsRecipe -import re - class AdvancedUserRecipe(BasicNewsRecipe): - title = 'heise online' + title = 'Heise-online' description = 'News vom Heise-Verlag' __author__ = 'schuster' + masthead_url = 'http://www.heise.de/icons/ho/heise_online_logo.gif' + publisher = 'Heise Zeitschriften Verlag GmbH & Co. KG' use_embedded_content = False language = 'de' oldest_article = 2 @@ -14,11 +14,10 @@ class AdvancedUserRecipe(BasicNewsRecipe): remove_empty_feeds = True timeout = 5 no_stylesheets = True - encoding = 'utf-8' remove_tags_after = dict(name ='p', attrs={'class':'editor'}) - remove_tags = [{'class':'navi_top_container'}, + remove_tags = [dict(id='navi_top_container'), dict(id='navi_bottom'), dict(id='mitte_rechts'), dict(id='navigation'), @@ -29,27 +28,31 @@ class AdvancedUserRecipe(BasicNewsRecipe): dict(id='seiten_navi'), dict(id='adbottom'), dict(id='sitemap'), - dict(name='a', href=re.compile(r'^/([a-zA-Z]+/)?')), - ] + dict(name='div', attrs={'id':'sitemap'}), + dict(name='ul', attrs={'class':'erste_zeile'}), + dict(name='ul', attrs={'class':'zweite_zeile'}), + dict(name='div', attrs={'class':'navi_top_container'})] feeds = [ ('Newsticker', 'http://www.heise.de/newsticker/heise.rdf'), - ('iX', 'http://www.heise.de/ix/news/news.rdf'), - ('Technology Review', 'http://www.heise.de/tr/news-atom.xml'), - ('mobil', 'http://www.heise.de/mobil/newsticker/heise-atom.xml'), - ('Security', 'http://www.heise.de/security/news/news-atom.xml'), - ('Netze', 'http://www.heise.de/netze/rss/netze-atom.xml'), - ('Open Source', 'http://www.heise.de/open/news/news-atom.xml'), - ('Resale ', 'http://www.heise.de/resale/rss/resale.rdf'), + ('Auto', 'http://www.heise.de/autos/rss/news.rdf'), ('Foto ', 'http://www.heise.de/foto/rss/news-atom.xml'), - ('Autos', 'http://www.heise.de/autos/rss/news.rdf'), - ('Mac & i', 'http://www.heise.de/mac-and-i/news.rdf'), + ('Mac&i', 'http://www.heise.de/mac-and-i/news.rdf'), + ('Mobile ', 'http://www.heise.de/mobil/newsticker/heise-atom.xml'), + ('Netz ', 'http://www.heise.de/netze/rss/netze-atom.xml'), + ('Open ', 'http://www.heise.de/open/news/news-atom.xml'), + ('Resale ', 'http://www.heise.de/resale/rss/resale.rdf'), + ('Security ', 'http://www.heise.de/security/news/news-atom.xml'), + ('C`t', 'http://www.heise.de/ct/rss/artikel-atom.xml'), + ('iX', 'http://www.heise.de/ix/news/news.rdf'), + ('Mach-flott', 'http://www.heise.de/mach-flott/rss/mach-flott-atom.xml'), ('Blog: Babel-Bulletin', 'http://www.heise.de/developer/rss/babel-bulletin/blog.rdf'), ('Blog: Der Dotnet-Doktor', 'http://www.heise.de/developer/rss/dotnet-doktor/blog.rdf'), ('Blog: Bernds Management-Welt', 'http://www.heise.de/developer/rss/bernds-management-welt/blog.rdf'), - ('Blog: The World of IT', 'http://www.heise.de/developer/rss/world-of-it/blog.rdf'), - ('Blog: Kais bewegtes Web', 'http://www.heise.de/developer/rss/kais-bewegtes-web/blog.rdf') - ] + ('Blog: IT conversation', 'http://www.heise.de/developer/rss/world-of-it/blog.rdf'), + ('Blog: Kais bewegtes Web', 'http://www.heise.de/developer/rss/kais-bewegtes-web/blog.rdf')] def print_version(self, url): return url + '?view=print' + + diff --git a/recipes/histmag.recipe b/recipes/histmag.recipe index 846bab2f66..0009580e49 100644 --- a/recipes/histmag.recipe +++ b/recipes/histmag.recipe @@ -4,7 +4,6 @@ __license__ = 'GPL v3' __copyright__ = '2010, matek09, matek09@gmail.com' from calibre.web.feeds.news import BasicNewsRecipe -import re class Histmag(BasicNewsRecipe): title = u'Histmag' diff --git a/recipes/japan_news.recipe b/recipes/japan_news.recipe index 3c5e459f99..12db4c9673 100644 --- a/recipes/japan_news.recipe +++ b/recipes/japan_news.recipe @@ -1,5 +1,4 @@ from calibre.web.feeds.news import BasicNewsRecipe -from calibre.ebooks.BeautifulSoup import BeautifulSoup class NewsOnJapan(BasicNewsRecipe): title = u'News On Japan' @@ -14,6 +13,6 @@ class NewsOnJapan(BasicNewsRecipe): feeds = [ -('News', +('News', 'http://newsonjapan.com/rss/top.xml'), -] \ No newline at end of file +] diff --git a/recipes/tagesspiegel.recipe b/recipes/tagesspiegel.recipe index b355a72ebd..b71a34aa85 100644 --- a/recipes/tagesspiegel.recipe +++ b/recipes/tagesspiegel.recipe @@ -37,11 +37,13 @@ class TagesspiegelRSS(BasicNewsRecipe): keep_only_tags = dict(name='div', attrs={'class':["hcf-article"]}) remove_tags = [ dict(name='link'), dict(name='iframe'),dict(name='style'),dict(name='meta'),dict(name='button'), - dict(name='div', attrs={'class':["hcf-jump-to-comments","hcf-clear","hcf-magnify hcf-media-control"] }), + dict(name='div', attrs={'class':["hcf-jump-to-comments","hcf-clear","hcf-magnify hcf-media-control", + "hcf-socials-widgets hcf-socials-top","hcf-socials-widgets hcf-socials-bottom"] }), dict(name='span', attrs={'class':["hcf-mainsearch",] }), dict(name='ul', attrs={'class':["hcf-tools"]}), dict(name='ul', attrs={'class': re.compile('hcf-services')}) ] + def parse_index(self): soup = self.index_to_soup('http://www.tagesspiegel.de/zeitung/') diff --git a/recipes/the_week_magazine_free.recipe b/recipes/the_week_magazine_free.recipe index 6e033eaf82..89d9b128b2 100644 --- a/recipes/the_week_magazine_free.recipe +++ b/recipes/the_week_magazine_free.recipe @@ -5,7 +5,6 @@ www.theweek.com ''' from calibre.web.feeds.news import BasicNewsRecipe -import re class TheWeek(BasicNewsRecipe): title = 'The Week Magazine' @@ -21,23 +20,7 @@ class TheWeek(BasicNewsRecipe): encoding = 'utf-8' use_embedded_content = False language = 'en' - preprocess_regexps = [(re.compile(r'