home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Chip 2011 November
/
CHIP_2011_11.iso
/
Programy
/
Narzedzia
/
Calibre
/
calibre-0.8.18.msi
/
file_280
/
wash_times.recipe
< prev
next >
Wrap
Text File
|
2011-09-09
|
2KB
|
50 lines
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
import re
from calibre.web.feeds.news import BasicNewsRecipe
class WashingtonTimes(BasicNewsRecipe):
title = 'Washington Times'
max_articles_per_feed = 15
language = 'en'
__author__ = 'Kos Semonski'
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
[
(r'<HEAD>.*?</HEAD>' , lambda match : '<HEAD></HEAD>'),
(r'<div id="apple-rss-sidebar-background">.*?<!-- start Entries -->', lambda match : ''),
(r'<!-- end apple-rss-content-area -->.*?</body>', lambda match : '</body>'),
(r'<script.*?>.*?</script>', lambda match : ''),
(r'<body onload=.*?>.*?<a href="http://www.upi.com">', lambda match : '<body style="font: 8pt arial;">'),
##(r'<div class=\'headerDIV\'><h2><a style="color: #990000;" href="http://www.washingtontimes.com/NewsTrack/Top_News/">Top News</a></h2></div>.*?<br clear="all">', lambda match : ''),
(r'<script src="http://www.g.*?>.*?</body>', lambda match : ''),
(r'<span style="font: 16pt arial', lambda match : '<span style="font: 12pt arial'),
]
]
def get_feeds(self):
return [ (u'Headlines', u'http://www.washingtontimes.com/rss/headlines/news/headlines/'),
(u'Newsmakers', u'http://www.washingtontimes.com/rss/headlines/news/newsmakers/'),
(u'National', u'http://www.washingtontimes.com/rss/headlines/news/national/'),
(u'World', u'http://www.washingtontimes.com/rss/headlines/news/world/'),
(u'Editor Favs', u'http://www.washingtontimes.com/rss/headlines/news/editor-favorites/'),
(u'Editorials', u'http://www.washingtontimes.com/rss/headlines/opinion/editorials/'),
(u'Cartoons', u'http://www.washingtontimes.com/rss/headlines/opinion/cartoons/'),
(u'Business', u'http://www.washingtontimes.com/rss/headlines/news/business/'),
(u'Technology', u'http://www.washingtontimes.com/rss/headlines/news/technology/'),
(u'Security', u'http://www.washingtontimes.com/rss/headlines/news/security/'),
(u'Politics', u'http://www.washingtontimes.com/rss/headlines/news/politics/'),
(u'Congress', u'http://www.washingtontimes.com/rss/headlines/news/congress/'),
]
def print_version(self, url):
return url + '/print/'