| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
from __future__ import absolute_import, division, print_function, unicode_literals |
| 4 |
|
| 5 |
''' |
| 6 |
bild.de |
| 7 |
''' |
| 8 |
|
| 9 |
import re |
| 10 |
|
| 11 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 12 |
|
| 13 |
|
| 14 |
class AdvancedUserRecipe1303841067(BasicNewsRecipe): |
| 15 |
title = 'Bild.de' |
| 16 |
__author__ = 'schuster' |
| 17 |
description = 'RSS-Feeds von Bild.de' |
| 18 |
language = 'de' |
| 19 |
|
| 20 |
oldest_article = 1 |
| 21 |
max_articles_per_feed = 100 |
| 22 |
no_stylesheets = True |
| 23 |
remove_javascript = True |
| 24 |
use_embedded_content = False |
| 25 |
remove_empty_feeds = True |
| 26 |
|
| 27 |
masthead_url = 'http://a3.l3-images.myspacecdn.com/images02/56/0232f842170b4d349779f8379c27e073/l.jpg' |
| 28 |
|
| 29 |
# By default, no local news feeds will be fetched. To change this, |
| 30 |
# just uncomment the lines for the regions you are interested in. |
| 31 |
feeds = [ |
| 32 |
('Politik', 'http://www.bild.de/rss-feeds/rss-16725492,feed=politik.bild.html'), |
| 33 |
('Unterhaltung', 'http://www.bild.de/rss-feeds/rss-16725492,feed=unterhaltung.bild.html'), |
| 34 |
('Sport', 'http://www.bild.de/rss-feeds/rss-16725492,feed=sport.bild.html'), |
| 35 |
('Lifestyle', 'http://www.bild.de/rss-feeds/rss-16725492,feed=lifestyle.bild.html'), |
| 36 |
('Ratgeber', 'http://www.bild.de/rss-feeds/rss-16725492,feed=ratgeber.bild.html'), |
| 37 |
('Auto', 'http://www.bild.de/rss-feeds/rss-16725492,feed=auto.bild.html'), |
| 38 |
('Digital', 'http://www.bild.de/rss-feeds/rss-16725492,feed=digital.bild.html'), |
| 39 |
('Spiele', 'http://www.bild.de/rss-feeds/rss-16725492,feed=spiele.bild.html'), |
| 40 |
('Leserreporter', 'http://www.bild.de/rss-feeds/rss-16725492,feed=leserreporter.bild.html'), |
| 41 |
# ('Berlin', 'http://www.bild.de/rss-feeds/rss-16725492,feed=Newsticker.bild.html'), |
| 42 |
# ('Bremen', 'http://www.bild.de/rss-feeds/rss-16725492,feed=bremen.bild.html'), |
| 43 |
# ('Chemnitz', 'http://www.bild.de/rssfeeds/rss3/rss3-20745882,feed=ressort-regio-chemnitz.bild.html'), |
| 44 |
# ('Dresden', 'http://www.bild.de/rss-feeds/rss-16725492,feed=dresden.bild.html'), |
| 45 |
# ('Düsseldorf', 'http://www.bild.de/rss-feeds/rss-16725492,feed=duesseldorf.bild.html'), |
| 46 |
# ('Frankfurt/Main', 'http://www.bild.de/rss-feeds/rss-16725492,feed=regio-frankfurt.bild.html'), |
| 47 |
# ('Hamburg', 'http://www.bild.de/rss-feeds/rss-16725492,feed=hamburg.bild.html'), |
| 48 |
# ('Hannover', 'http://www.bild.de/rss-feeds/rss-16725492,feed=regio-hannover.bild.html'), |
| 49 |
# ('Köln', 'http://www.bild.de/rss-feeds/rss-16725492,feed=regio-koeln.bild.html'), |
| 50 |
# ('Leipzig', 'http://www.bild.de/rss-feeds/rss-16725492,feed=leipzig.bild.html'), |
| 51 |
# ('München', 'http://www.bild.de/rss-feeds/rss-16725492,feed=muenchen.bild.html'), |
| 52 |
# ('Ruhrgebiet', 'http://www.bild.de/rss-feeds/rss-16725492,feed=ruhrgebiet.bild.html'), |
| 53 |
# ('Saarland', 'http://www.bild.de/rssfeeds/rss3/rss3-20745882,feed=regional-saarland.bild.html'), |
| 54 |
# ('Stuttgart', 'http://www.bild.de/rss-feeds/rss-16725492,feed=regio-stuttgart.bild.html') |
| 55 |
] |
| 56 |
|
| 57 |
keep_only_tags = [dict(name='article')] |
| 58 |
|
| 59 |
remove_tags = [ |
| 60 |
dict(name=['aside', 'iframe']), |
| 61 |
dict(attrs={'class': ['socialbar', 'social-sharing flank', 'vel', 'back']}), |
| 62 |
dict(name='img', attrs={'alt': 'logo'}), |
| 63 |
dict(name='div', attrs={'class': re.compile(r'infoEl')}), |
| 64 |
dict(name='span', attrs={'class': re.compile(r'loupe')}), |
| 65 |
] |
| 66 |
|
| 67 |
remove_tags_after = [dict(name='div', attrs={'itemprop': re.compile(r'articleBody')})] |
| 68 |
|
| 69 |
def preprocess_html(self, soup): |
| 70 |
# skip articles without relevant content |
| 71 |
if not soup.find('article'): |
| 72 |
self.abort_article() |
| 73 |
# remove all style attributes |
| 74 |
for item in soup.findAll(attrs={'style': True}): |
| 75 |
del item['style'] |
| 76 |
# remove <br> within headlines |
| 77 |
for h1 in soup.findAll('h1'): |
| 78 |
for br in h1.findAll('br'): |
| 79 |
br.replaceWith(' ') |
| 80 |
# remove all links |
| 81 |
for a in soup.findAll('a'): |
| 82 |
a.replaceWith(a.renderContents().decode('utf-8')) |
| 83 |
return soup |