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

Merge from trunk

Browse Source
This commit is contained in:
Charles Haley 2011-09-27 17:20:36 +02:00
commit d39ba839e2
82 changed files with 2508152 additions and 2508160 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
recipes/aprospect.recipe
View File

@ -1,9 +1,10 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class AmericanProspect(BasicNewsRecipe):
title = u'American Prospect'
__author__ = u'Michael Heinz'
__author__ = u'Michael Heinz, a.peter'
version = 2
oldest_article = 30
language = 'en'
max_articles_per_feed = 100
@ -11,16 +12,7 @@ class AmericanProspect(BasicNewsRecipe):
no_stylesheets = True
remove_javascript = True
preprocess_regexps = [
(re.compile(r'<body.*?<div class="pad_10L10R">', re.DOTALL|re.IGNORECASE), lambda match: '<body><div>'),
(re.compile(r'</div>.*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</div></body>'),
(re.compile('\r'),lambda match: ''),
(re.compile(r'<!-- .+? -->', re.DOTALL|re.IGNORECASE), lambda match: ''),
(re.compile(r'<link .+?>', re.DOTALL|re.IGNORECASE), lambda match: ''),
(re.compile(r'<script.*?</script>', re.DOTALL|re.IGNORECASE), lambda match: ''),
(re.compile(r'<noscript.*?</noscript>', re.DOTALL|re.IGNORECASE), lambda match: ''),
(re.compile(r'<meta .*?/>', re.DOTALL|re.IGNORECASE), lambda match: ''),
]
keep_only_tags = [dict(name='div', attrs={'class':'pad_10L10R'})]
remove_tags = [dict(name='form'), dict(name='div', attrs={'class':['bkt_caption','sharebox noprint','badgebox']})]
feeds = [(u'Articles', u'feed://www.prospect.org/articles_rss.jsp')]