calibre/recipes/aprospect.recipe

27 lines
1.1 KiB
Plaintext

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
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: ''),
]
feeds = [(u'Articles', u'feed://www.prospect.org/articles_rss.jsp')]