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

Update The Week

Browse Source
This commit is contained in:
Kovid Goyal 2010-12-30 10:15:16 -07:00
parent 6055869130
commit 89b3f22cd4
1 changed files with 29 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
resources/recipes/the_week_magazine_free.recipe
View File

@ -1,17 +1,19 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2010, JOlo'
'''
www.theweek.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
import re
class TheWeekFree(BasicNewsRecipe):
title = 'The Week Magazine - Free content'
__author__ = 'Darko Miletic'
class TheWeek(BasicNewsRecipe):
title = 'The Week Magazine'
__author__ = 'Jim Olo'
description = "The best of the US and international media. Daily coverage of commentary and analysis of the day's events, as well as arts, entertainment, people and gossip, and political cartoons."
publisher = 'The Week Publications, Inc.'
masthead_url = 'http://test.theweek.com/images/logo_theweek.gif'
cover_url = masthead_url
category = 'news, politics, USA'
oldest_article = 7
max_articles_per_feed = 100
@ -19,31 +21,27 @@ class TheWeekFree(BasicNewsRecipe):
encoding = 'utf-8'
use_embedded_content = False
language = 'en'
preprocess_regexps = [(re.compile(r'<h3><a href=.*</body>', re.DOTALL), lambda match: '</body>')]
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class':'articleSubscribe4free'})
remove_tags = [
dict(name='div', attrs={'class':['floatLeft','imageCaption','slideshowImageAttribution','postDate','utilities','cartoonInfo','left','middle','col300','articleSubscribe4free',' articleFlyout','articleFlyout floatRight','fourFreeBar']})
,dict(name='div', attrs={'id':['cartoonThumbs','rightColumn','header','partners']})
,dict(name='ul', attrs={'class':['slideshowNav','hotTopicsList topicList']})
]
remove_attributes = ['width','height', 'style', 'font', 'color']
extra_css = '''
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
p {font-family:Arial,Helvetica,sans-serif;}
'''
filter_regexps = [r'www\.palmcoastdata\.com']
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [
dict(name=['h1','h2'])
, dict(name='div', attrs={'class':'basefont'})
, dict(name='div', attrs={'id':'slideshowLoader'})
]
remove_tags = [
dict(name='div', attrs={'id':['digg_dugg','articleRight','dateHeader']})
,dict(name=['object','embed','iframe'])
]
feeds = [
(u'News & Opinions' , u'http://www.theweek.com/section/index/news_opinion.rss')
,(u'Arts & Leisure' , u'http://www.theweek.com/section/index/arts_leisure.rss')
,(u'Business' , u'http://www.theweek.com/section/index/business.rss' )
,(u'Cartoon & Short takes' , u'http://www.theweek.com/section/index/cartoons_wit.rss')
]
feeds = [
(u'News-Opinion', u'http://theweek.com/section/index/news_opinion.rss'),
(u'Business', u'http://theweek.com/section/index/business.rss'),
(u'Arts-Life', u'http://theweek.com/section/index/arts_life.rss'),
(u'Cartoons', u'http://theweek.com/section/index/cartoon_wit/0/all-cartoons.rss')
]