View Single Post
Old 05-22-2016, 05:00 AM   #3
Aimylios
Member
Aimylios began at the beginning.
 
Posts: 17
Karma: 10
Join Date: Apr 2016
Device: Tolino Vision 3HD
Hi,

the addresses of the bild.de RSS feeds have been changed. Here's an updated version of the bild_de.recipe.

Code:
#!/usr/bin/env python2
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function

'''
bild.de
'''

import re
from calibre.web.feeds.recipes import BasicNewsRecipe

class AdvancedUserRecipe1303841067(BasicNewsRecipe):
    title       = 'Bild.de'
    __author__  = 'schuster'
    description = 'RSS-Feeds von Bild.de'
    language    = 'de'

    oldest_article        = 1
    max_articles_per_feed = 100
    no_stylesheets        = True
    remove_javascript     = True
    use_embedded_content  = False
    remove_empty_feeds    = True

    masthead_url = 'http://a3.l3-images.myspacecdn.com/images02/56/0232f842170b4d349779f8379c27e073/l.jpg'

    # By default, no local news feeds will be fetched. To change this,
    # just uncomment the lines for the regions you are interested in.
    feeds = [
        ('Politik', 'http://www.bild.de/rss-feeds/rss-16725492,feed=politik.bild.html'),
        ('Unterhaltung', 'http://www.bild.de/rss-feeds/rss-16725492,feed=unterhaltung.bild.html'),
        ('Sport', 'http://www.bild.de/rss-feeds/rss-16725492,feed=sport.bild.html'),
        ('Lifestyle', 'http://www.bild.de/rss-feeds/rss-16725492,feed=lifestyle.bild.html'),
        ('Ratgeber', 'http://www.bild.de/rss-feeds/rss-16725492,feed=ratgeber.bild.html'),
        ('Auto', 'http://www.bild.de/rss-feeds/rss-16725492,feed=auto.bild.html'),
        ('Digital', 'http://www.bild.de/rss-feeds/rss-16725492,feed=digital.bild.html'),
        ('Spiele', 'http://www.bild.de/rss-feeds/rss-16725492,feed=spiele.bild.html'),
        ('Leserreporter', 'http://www.bild.de/rss-feeds/rss-16725492,feed=leserreporter.bild.html'),
#        ('Berlin', 'http://www.bild.de/rss-feeds/rss-16725492,feed=Newsticker.bild.html'),
#        ('Bremen', 'http://www.bild.de/rss-feeds/rss-16725492,feed=bremen.bild.html'),
#        ('Chemnitz', 'http://www.bild.de/rssfeeds/rss3/rss3-20745882,feed=ressort-regio-chemnitz.bild.html'),
#        ('Dresden', 'http://www.bild.de/rss-feeds/rss-16725492,feed=dresden.bild.html'),
#        ('Düsseldorf', 'http://www.bild.de/rss-feeds/rss-16725492,feed=duesseldorf.bild.html'),
#        ('Frankfurt/Main', 'http://www.bild.de/rss-feeds/rss-16725492,feed=regio-frankfurt.bild.html'),
#        ('Hamburg', 'http://www.bild.de/rss-feeds/rss-16725492,feed=hamburg.bild.html'),
#        ('Hannover', 'http://www.bild.de/rss-feeds/rss-16725492,feed=regio-hannover.bild.html'),
#        ('Köln', 'http://www.bild.de/rss-feeds/rss-16725492,feed=regio-koeln.bild.html'),
#        ('Leipzig', 'http://www.bild.de/rss-feeds/rss-16725492,feed=leipzig.bild.html'),
#        ('München', 'http://www.bild.de/rss-feeds/rss-16725492,feed=muenchen.bild.html'),
#        ('Ruhrgebiet', 'http://www.bild.de/rss-feeds/rss-16725492,feed=ruhrgebiet.bild.html'),
#        ('Saarland', 'http://www.bild.de/rssfeeds/rss3/rss3-20745882,feed=regional-saarland.bild.html'),
#        ('Stuttgart', 'http://www.bild.de/rss-feeds/rss-16725492,feed=regio-stuttgart.bild.html')
    ]

    keep_only_tags = [
        dict(name='article')
    ]

    remove_tags = [
        dict(name=['aside', 'iframe']),
        dict(attrs={'class':['socialbar', 'social-sharing flank', 'vel', 'back']}),
        dict(name='img', attrs={'alt':'logo'}),
        dict(name='div', attrs={'class':re.compile('infoEl')}),
        dict(name='span', attrs={'class':re.compile('loupe')})
    ]

    remove_tags_after = [
        dict(name ='div', attrs={'itemprop':re.compile('articleBody')})
    ]

    def preprocess_html(self, soup):
        # skip articles without relevant content
        if not soup.find('article'):
            self.abort_article()
        # remove all style attributes
        for item in soup.findAll(attrs={'style':True}):
            del item['style']
        # remove <br> within headlines
        for h1 in soup.findAll('h1'):
            for br in h1.findAll('br'):
                br.replaceWith(' ')
        # remove all links
        for a in soup.findAll('a'):
            a.replaceWith(a.renderContents())
        return soup
Aimylios is offline   Reply With Quote