Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix Le Monde

Browse Source
This commit is contained in:
Kovid Goyal 2012-03-20 18:49:00 +05:30
parent 7658a536cc
commit 9915d4b963
1 changed files with 8 additions and 71 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

79
recipes/le_monde.recipe
View File

@ -3,7 +3,6 @@ __copyright__ = '2011'
''' '''
lemonde.fr lemonde.fr
''' '''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class LeMonde(BasicNewsRecipe): class LeMonde(BasicNewsRecipe):
@ -41,77 +40,8 @@ class LeMonde(BasicNewsRecipe):
remove_empty_feeds = True remove_empty_feeds = True
filterDuplicates = True auto_cleanup = 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 self.adeify_images(soup)
preprocess_regexps = [
(re.compile(r'([0-9])%'), lambda m: m.group(1) + ' %'),
(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) + ' ' + 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) + ' ' + 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'"<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: '&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'),
(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']})
]
remove_tags = [dict(name='div', attrs={'class':['LM_atome']})]
remove_tags_after = [dict(id='appel_temoignage')]
def get_article_url(self, article):
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 = [ feeds = [
('A la une', 'http://www.lemonde.fr/rss/une.xml'), ('A la une', 'http://www.lemonde.fr/rss/une.xml'),
@ -137,3 +67,10 @@ class LeMonde(BasicNewsRecipe):
return cover_url return cover_url
def get_article_url(self, article):
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