Updated Le Monde

This commit is contained in:
Kovid Goyal 2011-02-25 06:36:30 -07:00
parent c626b60a29
commit 414db0f196

View File

@ -1,10 +1,15 @@
__license__ = 'GPL v3'
__copyright__ = '2011'
'''
lemonde.fr
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class LeMonde(BasicNewsRecipe):
title = 'Le Monde'
__author__ = 'veezh'
description = u'Actualit\xe9s'
description = 'Actualités'
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
@ -12,13 +17,27 @@ class LeMonde(BasicNewsRecipe):
use_embedded_content = False
encoding = 'cp1252'
publisher = 'lemonde.fr'
category = 'news, France, world'
language = 'fr'
#publication_type = 'newsportal'
extra_css = '''
h1{font-size:130%;}
.ariane{font-size:xx-small;}
.source{font-size:xx-small;}
#.href{font-size:xx-small;}
.LM_caption{color:#666666; font-size:x-small;}
#.main-article-info{font-family:Arial,Helvetica,sans-serif;}
#full-contents{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
#match-stats-summary{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
'''
#preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
conversion_options = {
'comments' : description
,'language' : language
,'publisher' : publisher
,'linearize_tables': True
}
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
,'linearize_tables': True
}
remove_empty_feeds = True
@ -32,15 +51,28 @@ class LeMonde(BasicNewsRecipe):
return soup
preprocess_regexps = [
(re.compile(r'([0-9])%'), lambda m: m.group(1) + '&nbsp;%'),
(re.compile(r'([0-9])([0-9])([0-9]) ([0-9])([0-9])([0-9])'), lambda m: m.group(1) + m.group(2) + m.group(3) + '&nbsp;' + m.group(4) + m.group(5) + m.group(6)),
(re.compile(r'([0-9]) ([0-9])([0-9])([0-9])'), lambda m: m.group(1) + '&nbsp;' + m.group(2) + m.group(3) + m.group(4)),
(re.compile(r'<span>'), lambda match: ' <span>'),
(re.compile(r'\("'), lambda match: '(&laquo;&nbsp;'),
(re.compile(r'"\)'), lambda match: '&nbsp;&raquo;)'),
(re.compile(r'&ldquo;'), lambda match: '(&laquo;&nbsp;'),
(re.compile(r'&rdquo;'), lambda match: '&nbsp;&raquo;)'),
(re.compile(r'>\''), lambda match: '>&lsquo;'),
(re.compile(r' \''), lambda match: ' &lsquo;'),
(re.compile(r'\''), lambda match: '&rsquo;'),
(re.compile(r'"<'), lambda match: '&nbsp;&raquo;<'),
(re.compile(r'"<em>'), lambda match: '<em>&laquo;&nbsp;'),
(re.compile(r'"<em>"</em><em>'), lambda match: '<em>&laquo;&nbsp;'),
(re.compile(r'"<a href='), lambda match: '&laquo;&nbsp;<a href='),
(re.compile(r'</em>"'), lambda match: '&nbsp;&raquo;</em>'),
(re.compile(r'</a>"'), lambda match: '&nbsp;&raquo;</a>'),
(re.compile(r'"</'), lambda match: '&nbsp;&raquo;</'),
(re.compile(r'>"'), lambda match: '>&laquo;&nbsp;'),
(re.compile(r'"<'), lambda match: '&nbsp;&raquo;<'),
(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;?'),
@ -56,8 +88,14 @@ class LeMonde(BasicNewsRecipe):
(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'),
(re.compile(r' &ndash; '), lambda match: '&nbsp;&ndash; '),
(re.compile(r' '), lambda match: '&nbsp;&ndash; '),
(re.compile(r' - '), lambda match: '&nbsp;&ndash; '),
(re.compile(r' -,'), lambda match: '&nbsp;&ndash;,'),
(re.compile(r'&raquo;:'), lambda match: '&raquo;&nbsp;:'),
]
keep_only_tags = [
dict(name='div', attrs={'class':['contenu']})
]
@ -65,11 +103,15 @@ class LeMonde(BasicNewsRecipe):
remove_tags_after = [dict(id='appel_temoignage')]
def get_article_url(self, article):
link = article.get('link')
if 'blog' not in link:
return link
url = article.get('guid', None)
if '/chat/' in url or '.blog' in url or '/video/' in url or '/sport/' in url or '/portfolio/' in url or '/visuel/' in url :
url = None
return url
# def get_article_url(self, article):
# link = article.get('link')
# if 'blog' not in link and ('chat' not in link):
# return link
feeds = [
('A la une', 'http://www.lemonde.fr/rss/une.xml'),
@ -94,3 +136,4 @@ class LeMonde(BasicNewsRecipe):
cover_url = link_item.img['src']
return cover_url