View Single Post
Old 06-03-2011, 07:56 AM   #2
schuster
Zealot
schuster doesn't litterschuster doesn't litter
 
Posts: 116
Karma: 100
Join Date: Jan 2011
Location: Germany / NRW /Köln
Device: prs-650 / prs-350 /kindle 3
**Update**

her a new update for bild.de:

1- fetch all regional feeds
2- cleaner layout


Code:
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 = 100
    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'
    masthead_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'})


# remove things on the site that we don't want
    remove_tags = [dict(name='div', attrs={'class':'credit'}),
        dict(name='div', attrs={'class':'index'}),
        dict(name='div', attrs={'id':'zstart31'}),
        dict(name='div', attrs={'class':'hentry'}),
        dict(name='div', attrs={'class':'back'}),
        dict(name='div', attrs={'class':'pagination'}),
        dict(name='div', attrs={'class':'header'}),
        dict(name='div', attrs={'class':'element floatL'}),
        dict(name='div', attrs={'class':'stWrap'})
]

#  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'),
                          (u'Reg. - Berlin', u'http://rss.bild.de/bild-berlin.xml'),
                          (u'Reg. - Bremen', u'http://rss.bild.de/bild-bremen.xml'),
                          (u'Reg. - Dresden', u'http://rss.bild.de/bild-dresden.xml'),
                          (u'Reg. - Düsseldorf', u'http://rss.bild.de/bild-duesseldorf.xml'),
                          (u'Reg. - Frankfurt-Main', u'http://rss.bild.de/bild-frankfurt-main.xml'),
                          (u'Reg. - Hamburg', u'http://rss.bild.de/bild-hamburg.xml'),
                          (u'Reg. - Hannover', u'http://rss.bild.de/bild-hannover.xml'),
                          (u'Reg. - Köln', u'http://rss.bild.de/bild-koeln.xml'),
                          (u'Reg. - Leipzig', u'http://rss.bild.de/bild-leipzig.xml'),
                          (u'Reg. - München', u'http://rss.bild.de/bild-muenchen.xml'),
                          (u'Reg. - Ruhrgebiet', u'http://rss.bild.de/bild-ruhrgebiet.xml'),
                          (u'Reg. - Stuttgart', u'http://rss.bild.de/bild-stuttgart.xml')
]
schuster is offline   Reply With Quote