Update bild.de

This commit is contained in:
Kovid Goyal 2016-05-22 16:04:06 +05:30
parent d8f2808c6f
commit 1b7c86dbaf

View File

@ -1,74 +1,85 @@
# -*- coding: utf-8 -*- #!/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 from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe): class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = 'Bild.de'
title = u'Bild.de'
__author__ = 'schuster' __author__ = 'schuster'
oldest_article = 1 description = 'RSS-Feeds von Bild.de'
max_articles_per_feed = 100 language = 'de'
no_stylesheets = True
use_embedded_content = False oldest_article = 1
language = 'de' max_articles_per_feed = 100
remove_javascript = True no_stylesheets = True
remove_javascript = True
use_embedded_content = False
remove_empty_feeds = 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' masthead_url = 'http://a3.l3-images.myspacecdn.com/images02/56/0232f842170b4d349779f8379c27e073/l.jpg'
# set what to fetch on the site # By default, no local news feeds will be fetched. To change this,
remove_tags_before = dict(name = 'h2', attrs={'id':'cover'}) # just uncomment the lines for the regions you are interested in.
remove_tags_after = dict(name ='div', attrs={'class':'back'}) 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 things on the site that we don't want remove_tags = [
remove_tags = [dict(name='div', attrs={'class':'credit'}), dict(name=['aside', 'iframe']),
dict(name='div', attrs={'class':'index'}), dict(attrs={'class':['socialbar', 'social-sharing flank', 'vel', 'back']}),
dict(name='div', attrs={'id':'zstart31'}), dict(name='img', attrs={'alt':'logo'}),
dict(name='div', attrs={'class':'hentry'}), dict(name='div', attrs={'class':re.compile('infoEl')}),
dict(name='div', attrs={'class':'back'}), dict(name='span', attrs={'class':re.compile('loupe')})
dict(name='div', attrs={'class':'pagination'}), ]
dict(name='div', attrs={'class':'header'}),
dict(name='div', attrs={'class':'element floatL'}), remove_tags_after = [
dict(name='div', attrs={'class':'stWrap'}) dict(name='div', attrs={'itemprop':re.compile('articleBody')})
] ]
# 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): def preprocess_html(self, soup):
for alink in soup.findAll('a'): # skip articles without relevant content
if alink.string is not None: if not soup.find('article'):
tstr = alink.string self.abort_article()
alink.replaceWith(tstr) # 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 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')
]