home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Chip 2011 November
/
CHIP_2011_11.iso
/
Programy
/
Narzedzia
/
Calibre
/
calibre-0.8.18.msi
/
file_280
/
wired_daily.recipe
< prev
next >
Wrap
Text File
|
2011-09-09
|
2KB
|
60 lines
#!/usr/bin/env python
__license__ = 'GPL v3'
__docformat__ = 'restructuredtext en'
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.chardet import xml_to_unicode
class Wired_Daily(BasicNewsRecipe):
title = 'Wired Daily Edition'
__author__ = 'Kovid Goyal'
description = 'Technology news'
timefmt = ' [%Y%b%d %H%M]'
language = 'en'
no_stylesheets = True
preprocess_regexps = [(re.compile(r'<head.*</head>', re.DOTALL), lambda m:
'<head></head>')]
remove_tags_before = dict(name='div', id='content')
remove_tags = [dict(id=['header', 'commenting_module', 'post_nav',
'social_tools', 'sidebar', 'footer', 'social_wishlist', 'pgwidget',
'outerWrapper', 'inf_widget']),
{'class':['entryActions', 'advertisement', 'entryTags']},
dict(name=['noscript', 'script']),
dict(name='h4', attrs={'class':re.compile(r'rat\d+')}),
{'class':lambda x: x and x.startswith('contentjump')},
dict(name='li', attrs={'class':['entryCategories', 'entryEdit']})]
feeds = [
('Top News', 'http://feeds.wired.com/wired/index'),
('Product Reviews',
'http://www.wired.com/reviews/feeds/latestProductsRss'),
('Autopia', 'http://www.wired.com/autopia/feed/'),
('Danger Room', 'http://www.wired.com/dangerroom/feed/'),
('Epicenter', 'http://www.wired.com/epicenter/feed/'),
('Gadget Lab', 'http://www.wired.com/gadgetlab/feed/'),
('Geek Dad', 'http://www.wired.com/geekdad/feed/'),
('Playbook', 'http://www.wired.com/playbook/feed/'),
('Rawfile', 'http://www.wired.com/rawfile/feed/'),
('This Day in Tech', 'http://www.wired.com/thisdayintech/feed/'),
('Threat Level', 'http://www.wired.com/threatlevel/feed/'),
('Underwire', 'http://www.wired.com/underwire/feed/'),
('Web Monkey', 'http://www.webmonkey.com/feed/'),
('Science', 'http://www.wired.com/wiredscience/feed/'),
]
def populate_article_metadata(self, article, soup, first):
if article.text_summary:
article.text_summary = xml_to_unicode(article.text_summary,
resolve_entities=True)[0]
def print_version(self, url):
return url + '/all/1'