[schuster]

here a recipe for german newspaper (yellowpress) Bild.de

import string, re
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')
]