calibre/resources/recipes/le_monde.recipe
Kovid Goyal bf661325db ...
2010-12-22 11:01:48 -07:00

97 lines
4.0 KiB
Plaintext

import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class LeMonde(BasicNewsRecipe):
title = 'Le Monde'
__author__ = 'veezh'
description = u'Actualit\xe9s'
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
#delay = 1
use_embedded_content = False
encoding = 'cp1252'
publisher = 'lemonde.fr'
language = 'fr'
conversion_options = {
'comments' : description
,'language' : language
,'publisher' : publisher
,'linearize_tables': True
}
remove_empty_feeds = True
filterDuplicates = True
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
preprocess_regexps = [
(re.compile(r' \''), lambda match: ' ‘'),
(re.compile(r'\''), lambda match: '’'),
(re.compile(r'"<'), lambda match: '&nbsp;&raquo;<'),
(re.compile(r'>"'), lambda match: '>&laquo;&nbsp;'),
(re.compile(r'&rsquo;"'), lambda match: '&rsquo;«&nbsp;'),
(re.compile(r' "'), lambda match: ' &laquo;&nbsp;'),
(re.compile(r'" '), lambda match: '&nbsp;&raquo; '),
(re.compile(r'\("'), lambda match: '(&laquo;&nbsp;'),
(re.compile(r'"\)'), lambda match: '&nbsp;&raquo;)'),
(re.compile(r'"\.'), lambda match: '&nbsp;&raquo;.'),
(re.compile(r'",'), lambda match: '&nbsp;&raquo;,'),
(re.compile(r'"\?'), lambda match: '&nbsp;&raquo;?'),
(re.compile(r'":'), lambda match: '&nbsp;&raquo;:'),
(re.compile(r'";'), lambda match: '&nbsp;&raquo;;'),
(re.compile(r'"\!'), lambda match: '&nbsp;&raquo;!'),
(re.compile(r' :'), lambda match: '&nbsp;:'),
(re.compile(r' ;'), lambda match: '&nbsp;;'),
(re.compile(r' \?'), lambda match: '&nbsp;?'),
(re.compile(r' \!'), lambda match: '&nbsp;!'),
(re.compile(r'\s»'), lambda match: '&nbsp;»'),
(re.compile(r'«\s'), lambda match: '«&nbsp;'),
(re.compile(r' %'), lambda match: '&nbsp;%'),
(re.compile(r'\.jpg&nbsp;&raquo; border='), lambda match: '.jpg'),
(re.compile(r'\.png&nbsp;&raquo; border='), lambda match: '.png'),
]
keep_only_tags = [
dict(name='div', attrs={'class':['contenu']})
]
remove_tags_after = [dict(id='appel_temoignage')]
def get_article_url(self, article):
link = article.get('link')
if 'blog' not in link:
return link
feeds = [
('A la une', 'http://www.lemonde.fr/rss/une.xml'),
('International', 'http://www.lemonde.fr/rss/tag/international.xml'),
('Europe', 'http://www.lemonde.fr/rss/tag/europe.xml'),
(u'Société', 'http://www.lemonde.fr/rss/tag/societe.xml'),
('Economie', 'http://www.lemonde.fr/rss/tag/economie.xml'),
(u'Médias', 'http://www.lemonde.fr/rss/tag/actualite-medias.xml'),
(u'Planète', 'http://www.lemonde.fr/rss/tag/planete.xml'),
('Culture', 'http://www.lemonde.fr/rss/tag/culture.xml'),
('Technologies', 'http://www.lemonde.fr/rss/tag/technologies.xml'),
('Livres', 'http://www.lemonde.fr/rss/tag/livres.xml'),
]
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup('http://www.lemonde.fr/web/monde_pdf/0,33-0,1-0,0.html')
link_item = soup.find('div',attrs={'class':'pg-gch'})
if link_item and link_item.img:
cover_url = link_item.img['src']
return cover_url