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

Update taz.de (RSS)

Browse Source
This commit is contained in:
Kovid Goyal 2013-07-21 09:29:52 +05:30
parent 1a11c09d3c
commit e7777df9ae
1 changed files with 37 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
recipes/taz_rss.recipe
View File

@ -1,3 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2013, Alexander Schremmer <alex@alexanderweb.de>, Robert Riemann <robert@riemann.cc>' __copyright__ = '2013, Alexander Schremmer <alex@alexanderweb.de>, Robert Riemann <robert@riemann.cc>'
@ -6,10 +7,15 @@ from calibre.web.feeds.news import BasicNewsRecipe
class TazRSSRecipe(BasicNewsRecipe): class TazRSSRecipe(BasicNewsRecipe):
title = u'Taz - die Tageszeitung' title = u'Taz - die Tageszeitung'
description = u'Taz.de - die tageszeitung' description = u'Taz.de - die tageszeitung (Anpassung von Robert)'
__author__ = 'Alexander Schremmer, Robert Riemann' __author__ = 'Alexander Schremmer, Robert Riemann'
language = 'de' language = 'de'
lang = 'de-DE' lang = 'de-DE'
category = 'news, Germany'
timefmt = ' [%a, %d %b %Y]'
publication_type = 'newspaper'
remove_empty_feeds = True
use_embedded_content = False
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
publisher = 'taz Entwicklungs GmbH & Co. Medien KG' publisher = 'taz Entwicklungs GmbH & Co. Medien KG'
@ -20,24 +26,37 @@ class TazRSSRecipe(BasicNewsRecipe):
'language': lang, 'language': lang,
} }
feeds = [ feeds = [
(u'Schlagzeilen', u'http://www.taz.de/!p3270;rss/'), (u'Schlagzeilen', u'http://www.taz.de/!p3270;rss/'),
(u'Politik', u'http://www.taz.de/Politik/!p2;rss/'), (u'Politik', u'http://www.taz.de/Politik/!p2;rss/'),
(u'Zukunft', u'http://www.taz.de/Zukunft/!p4;rss/'), (u'Zukunft', u'http://www.taz.de/Zukunft/!p4;rss/'),
(u'Netz', u'http://www.taz.de/Netz/!p5;rss/'), (u'Netz', u'http://www.taz.de/Netz/!p5;rss/'),
(u'Debatte', u'http://www.taz.de/Debatte/!p9;rss/'), (u'Debatte', u'http://www.taz.de/Debatte/!p9;rss/'),
(u'Leben', u'http://www.taz.de/Leben/!p10;rss/'), (u'Leben', u'http://www.taz.de/Leben/!p10;rss/'),
(u'Sport', u'http://www.taz.de/Sport/!p12;rss/'), (u'Sport', u'http://www.taz.de/Sport/!p12;rss/'),
(u'Wahrheit', u'http://www.taz.de/Wahrheit/!p13;rss/'), (u'Wahrheit', u'http://www.taz.de/Wahrheit/!p13;rss/'),
(u'Berlin', u'http://www.taz.de/Berlin/!p14;rss/'), (u'Berlin', u'http://www.taz.de/Berlin/!p14;rss/'),
(u'Nord', u'http://www.taz.de/Nord/!p11;rss/') (u'Nord', u'http://www.taz.de/Nord/!p11;rss/')
] ]
# omit articles already linked in Schlagzeilen feed
ignore_duplicate_articles = {'title', 'url'}
# use the cover presented on the homepage
cover_url = 'http://www.taz.de/digitaz/.s1jpeg320'
keep_only_tags = [dict(name='div', attrs={'class': 'sect sect_article'})] keep_only_tags = [dict(name='div', attrs={'class': 'sect sect_article'})]
remove_tags = [ remove_tags = [
dict(name=['div'], attrs={'class': 'artikelwerbung'}), dict(name=['div'], attrs={'class': 'artikelwerbung'}),
dict(name=['ul'], attrs={'class': 'toolbar'}), dict(name=['ul'], attrs={'class': 'toolbar'}),
# remove: taz paywall # remove: taz paywall
dict(name=['div'], attrs={'id': 'tzi_paywall'}), dict(name=['div'], attrs={'id': 'tzi_paywall'}),
# remove: Artikel zum Thema (not working on Kindle) # remove: Artikel zum Thema (not working on Kindle)
dict(name=['div'], attrs={'class': re.compile(r".*\bsect_seealso\b.*")}), dict(name=['div'], attrs={'class': re.compile(r".*\bsect_seealso\b.*")}),
dict(name=['div'], attrs={'class': 'sectfoot'}) dict(name=['div'], attrs={'class': 'sectfoot'})
] ]
# with article pictures on Kindle super-slow
# def populate_article_metadata(self, article, soup, first):
# if first and hasattr(self, 'add_toc_thumbnail'):
# picdiv = soup.find('img')
# if picdiv is not None:
# self.add_toc_thumbnail(article,picdiv['src'])