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 American Prospect

Browse Source
This commit is contained in:
Kovid Goyal 2011-09-27 08:20:00 -06:00
parent b501a0c564
commit c0dc8bc5e0
1 changed files with 11 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
recipes/aprospect.recipe
View File

@ -1,26 +1,18 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class AmericanProspect(BasicNewsRecipe):
title = u'American Prospect'
__author__ = u'Michael Heinz'
oldest_article = 30
language = 'en'
max_articles_per_feed = 100
recursions = 0
no_stylesheets = True
remove_javascript = True
__author__ = u'Michael Heinz, a.peter'
version = 2
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: ''),
]
oldest_article = 30
language = 'en'
max_articles_per_feed = 100
recursions = 0
no_stylesheets = True
remove_javascript = True
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')]