Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

...

Browse Source
This commit is contained in:
Kovid Goyal 2012-03-28 01:16:28 +05:30
parent 5ff6fc8ffe
commit 889c3baefb
1 changed files with 84 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

95
recipes/le_monde.recipe
View File

@ -1,8 +1,9 @@
__license__ = 'GPL v3'
__copyright__ = '2011'
__copyright__ = '2012'
'''
lemonde.fr
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class LeMonde(BasicNewsRecipe):
@ -24,7 +25,7 @@ class LeMonde(BasicNewsRecipe):
.ariane{font-size:xx-small;}
.source{font-size:xx-small;}
#.href{font-size:xx-small;}
.LM_caption{color:#666666; font-size:x-small;}
#.figcaption style{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;}
@ -40,8 +41,88 @@ class LeMonde(BasicNewsRecipe):
remove_empty_feeds = True
auto_cleanup = 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'([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' &quot;'), lambda match: ' &laquo;&nbsp;'),
(re.compile(r'>&quot;'), lambda match: '>&laquo;&nbsp;'),
(re.compile(r'&quot;<'), lambda match: '&nbsp;&raquo;<'),
(re.compile(r'&quot; '), lambda match: '&nbsp;&raquo; '),
(re.compile(r'&quot;,'), lambda match: '&nbsp;&raquo;,'),
(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; width='), lambda match: '.jpg'),
(re.compile(r'\.png&nbsp;&raquo; width='), lambda match: '.png'),
(re.compile(r' &ndash; '), lambda match: '&nbsp;&ndash; '),
(re.compile(r'figcaption style="display:none"'), lambda match: 'figcaption'),
(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':['global']})
]
remove_tags = [
dict(name='div', attrs={'class':['bloc_base meme_sujet']}),
dict(name='p', attrs={'class':['lire']})
]
remove_tags_after = [dict(id='fb-like')]
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 = [
('A la une', 'http://www.lemonde.fr/rss/une.xml'),
@ -66,11 +147,3 @@ class LeMonde(BasicNewsRecipe):
cover_url = link_item.img['src']
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