1
## By Lorenzo goehr, lorenzogoehr@hotmail.com for Libprs500 by Kovid Goyal
4
from calibre.ebooks.lrf.web.profiles import DefaultProfile
8
class NewYorkReviewOfBooks(DefaultProfile):
10
title = 'New York Review of Books'
12
max_articles_per_feed = 50
13
html_description = True
17
return [ ('Current Issue', 'http://feeds.feedburner.com/nybooks') ]
19
preprocess_regexps = [(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in [
20
(r'<meta http-equiv="Content-Type" content="text/html; charset=(\S+)"', lambda match : match.group().replace(match.group(1), 'UTF-8')),
21
(r'<body.*?((<div id="article_body">)|(<div id="st-page-maincontent">)|(<div id="containermain">)|(<p class="ap-story-p">)|(<!-- img_nav -->))', lambda match: '<body><div>'),
22
(r'((<!-- end article content -->)|(<div id="st-custom-afterpagecontent">)|(<p class="ap-story-p">©)|(<div class="entry-footer">)|(<div id="see_also">)|(<p>Via <a href=)|(<div id="ss_nav">)).*?</html>', lambda match : '</div></body></html>'),
23
(r'<div class="nav">.*?<h2>', lambda match: '<h2>'),
24
(r'<table.*?>.*?(<img .*?/table>)', lambda match: match.group(1),), ] ]