|
This still does not start
import string, re
class AdvancedUserRecipe1229426345(BasicNewsRecipe):
title = u'La Libre Belgique'
__author__ = 'Denis McCann'
oldest_article = 1
max_articles_per_feed = 100
use_embedded_content = False
no_stylesheets = True
simultaneous_downloads = 1
remove_tags_after = [dict(id='articleText')]
preprocess_regexps = [
(re.compile(ru'\u0092'), lambda match: ru'\u0027')
]
keep_only_tags = [
dict(name='p', attrs={'id':'avantTitre'}),
dict(name='p', attrs={'id':'writer'}),
dict(name='p', attrs={'id':'publicationDate'}),
dict(name='div', attrs={'id':'articleHat'}),
dict(name='div', attrs={'id':'c'}),
dict(name='div', attrs={'id':'articleText'})
]
feeds = [
(u'A la Une', u'http://www.lalibre.be/rss/?section=10'),
(u'Belgique', u'http://www.lalibre.be/rss/?section=10&subsection=90'),
(u'Europe', u'http://www.lalibre.be/rss/?section=10&subsection=91'),
(u'Bruxelles', u'http://www.lalibre.be/rss/?section=10&subsection=1083'),
(u'Brabant', u'http://www.lalibre.be/rss/?section=10&subsection=1106'),
(u'Economie', u'http://www.lalibre.be/rss/?section=3'),
(u'Opinion', u'http://www.lalibre.be/rss/?section=11&subsection=118')
]
|