View Single Post
Old 12-15-2011, 08:37 PM   #5
Divingduck
Wizard
Divingduck ought to be getting tired of karma fortunes by now.Divingduck ought to be getting tired of karma fortunes by now.Divingduck ought to be getting tired of karma fortunes by now.Divingduck ought to be getting tired of karma fortunes by now.Divingduck ought to be getting tired of karma fortunes by now.Divingduck ought to be getting tired of karma fortunes by now.Divingduck ought to be getting tired of karma fortunes by now.Divingduck ought to be getting tired of karma fortunes by now.Divingduck ought to be getting tired of karma fortunes by now.Divingduck ought to be getting tired of karma fortunes by now.Divingduck ought to be getting tired of karma fortunes by now.
 
Posts: 1,161
Karma: 1404241
Join Date: Nov 2010
Location: Germany
Device: Sony PRS-650
Update for the recipe due to broken links. This is a quick update to keep the recipe running. There will be later on a clean-up.

Spoiler:
Code:
# -*- coding: utf-8 -*-
__license__   = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'

'''
Fetch sueddeutsche.de
'''
from calibre.web.feeds.news import BasicNewsRecipe


class Sueddeutsche(BasicNewsRecipe):

    title = u'sueddeutsche.de'
    description = 'News from Germany'
    __author__ = 'Oliver Niesner and Armin Geller' #AGe 2011-12-16
    use_embedded_content   = False
    timefmt = ' [%d %b %Y]'
    oldest_article = 7 #1
    max_articles_per_feed = 50#2
    no_stylesheets = True
    language = 'de'
    auto_cleanup = True
    encoding = 'utf-8'
    remove_javascript = True
    cover_url  = 'http://polpix.sueddeutsche.com/polopoly_fs/1.1236175.1323967473!/image/image.jpg_gen/derivatives/860x860/image.jpg' # 2011-12-16 AGe
# 2011-12-16 AGe
#    remove_tags = [ dict(name='link'), dict(name='iframe'),
#                    dict(name='div', attrs={'id':["bookmarking","themenbox","artikelfoot","CAD_AD",
#                          "SKY_AD","NT1_AD","navbar1","sdesiteheader"]}),
#
#                    dict(name='div', attrs={'class':["similar-article-box","artikelliste","nteaser301bg",
#                                 "pages closed","basebox right narrow","headslot galleried"]}),
#
#                    dict(name='div', attrs={'class':["articleDistractor","listHeader","listHeader2","hr2",
#                             "item","videoBigButton","articlefooter full-column",
#                                                     "bildbanderolle full-column","footerCopy padleft5"]}),
#
#                    dict(name='p', attrs={'class':["ressortartikeln","artikelFliestext","entry-summary"]}),
#                    dict(name='div', attrs={'style':["position:relative;"]}),
#                    dict(name='span', attrs={'class':["nlinkheaderteaserschwarz","artikelLink","r10000000"]}),
#                    dict(name='table', attrs={'class':["stoerBS","kommentare","footer","pageBoxBot","pageAktiv","bgcontent"]}),
#                    dict(name='ul', attrs={'class':["breadcrumb","articles","activities","sitenav","actions"]}),
#                    dict(name='td', attrs={'class':["artikelDruckenRight"]}),
#                    dict(name='p', text = "ANZEIGE")
#                     ]
#    remove_tags_after = [dict(name='div', attrs={'class':["themenbox full-column"]})]
#
    extra_css = '''
                    h2{font-family:Arial,Helvetica,sans-serif; font-size: x-small; color: #003399;}
                    a{font-family:Arial,Helvetica,sans-serif; font-style:italic;}
                    .dachzeile p{font-family:Arial,Helvetica,sans-serif; font-size: x-small; }
                    h1{ font-family:Arial,Helvetica,sans-serif;  font-size:x-large; font-weight:bold;}
                    .artikelTeaser{font-family:Arial,Helvetica,sans-serif; font-size: x-small; font-weight:bold; }
                    body{font-family:Arial,Helvetica,sans-serif; }
                    .photo {font-family:Arial,Helvetica,sans-serif; font-size: x-small; color: #666666;}                 '''
#
    feeds = [
#              (u'Politik', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EPolitik%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Wirtschaft', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EWirtschaft%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Geld', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EGeld%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Kultur', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EKultur%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Sport', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5ESport%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Leben', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5ELeben%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Karriere', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EKarriere%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'München & Region', u'http://www.sueddeutsche.de/app/service/rss/ressort/muenchen/rss.xml'), # AGe 2011-11-13
#              (u'Bayern', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EBayern%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Medien', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EMedien%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Digital', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EDigital%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Auto', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EAuto%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Wissen', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EWissen%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Panorama', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EPanorama%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Reise', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EReise%24?output=rss'), #AGe 2011-12-16 deactivated
#              (u'Technik', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5ETechnik%24?output=rss'), # sometimes only #AGe 2011-12-16 deactivated
#              (u'Macht', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EMacht%24?output=rss'),     # sometimes only #AGe 2011-12-16 deactivated
#              (u'Job', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EJob%24?output=rss'),         # sometimes only #AGe 2011-12-16 deactivated
#              (u'Service', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EService%24?output=rss'), # sometimes only #AGe 2011-12-16 deactivated
#              (u'Verlag', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EVerlag%24?output=rss'),   # sometimes only #AGe 2011-12-16 deactivated
              (u'Politik', u'http://www.sueddeutsche.de/app/service/rss/ressort/politik/rss.xml'),
              (u'Wirtschaft', u'http://www.sueddeutsche.de/app/service/rss/ressort/wirtschaft/rss.xml'),
              (u'Geld', u'http://www.sueddeutsche.de/app/service/rss/ressort/finanzen/rss.xml'),
              (u'Kultur', u'http://www.sueddeutsche.de/app/service/rss/ressort/kultur/rss.xml'),
              (u'Sport', u'http://www.sueddeutsche.de/app/service/rss/ressort/sport/rss.xml'),
              (u'Leben', u'http://www.sueddeutsche.de/app/service/rss/ressort/leben/rss.xml'),
              (u'Karriere', u'http://www.sueddeutsche.de/app/service/rss/ressort/karriere/rss.xml'),
              (u'München & Region', u'http://www.sueddeutsche.de/app/service/rss/ressort/muenchen/rss.xml'),
              (u'Bayern', u'http://www.sueddeutsche.de/app/service/rss/ressort/bayern/rss.xml'),
              (u'Medien', u'http://www.sueddeutsche.de/app/service/rss/ressort/medien/rss.xml'),
              (u'Digital', u'http://www.sueddeutsche.de/app/service/rss/ressort/computerwissen/rss.xml'),
              (u'Auto', u'http://www.sueddeutsche.de/app/service/rss/ressort/autoreise/rss.xml'),
              (u'Wissen', u'http://www.sueddeutsche.de/app/service/rss/ressort/wissen/rss.xml'),
              (u'Panorama', u'http://www.sueddeutsche.de/app/service/rss/ressort/panorama/rss.xml'),
              (u'Reise', u'http://www.sueddeutsche.de/app/service/rss/ressort/reise/rss.xml'),
            ]

#    def print_version(self, url):             #AGe 2011-12-16 deactivated
#        main, sep, id = url.rpartition('/')   #AGe 2011-12-16 deactivated
#        return main + '/2.220/' + id          #AGe 2011-12-16 deactivated


Let me know if there are other problems coming up. Thanks.

Have fun,
DD

Last edited by Divingduck; 12-16-2011 at 03:29 AM. Reason: change: oldest_article = 7 and max_articles_per_feed = 50
Divingduck is offline   Reply With Quote