calibre/recipes/lalibre_be.recipe

51 lines
1.8 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008-2011, Lionel Bergeret <lbergeret at gmail.com>'
'''
lalibre.be
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class LaLibre(BasicNewsRecipe):
title = u'La Libre Belgique'
__author__ = u'Lionel Bergeret'
description = u'News from Belgium in French'
publisher = u'lalibre.be'
category = 'news, Belgium'
oldest_article = 3
language = 'fr'
masthead_url = 'http://www.lalibre.be/img/logoLaLibre.gif'
max_articles_per_feed = 20
no_stylesheets = True
use_embedded_content = False
timefmt = ' [%d %b %Y]'
remove_tags_before = dict(name = 'div', attrs = {'class': 'extraMainContent'})
remove_tags_after = dict(name = 'div', attrs = {'id': 'articleText'})
remove_tags = [dict(name = 'div', attrs = {'id': 'strongArticleLinks'})]
feeds = [
(u'L\'actu' , u'http://www.lalibre.be/rss/?section=10' )
,(u'Culture' , u'http://www.lalibre.be/rss/?section=5' )
,(u'Economie' , u'http://www.lalibre.be/rss/?section=3' )
,(u'Libre Entreprise' , u'http://www.lalibre.be/rss/?section=904' )
,(u'Sports' , u'http://www.lalibre.be/rss/?section=2' )
,(u'Societe' , u'http://www.lalibre.be/rss/?section=12' )
]
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
def get_cover_url(self):
cover_url = strftime('http://pdf-online.lalibre.be/pdfonline/image/%Y%m%d/llb_%Y%m%d_nam_libre_001.pdf.L.jpg')
return cover_url