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

Fix #916745 (Updated recipe for Variety)

Browse Source
This commit is contained in:
Kovid Goyal 2012-01-15 18:27:43 +05:30
parent 82d1efeca1
commit 3f61cda6b9
1 changed files with 6 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
recipes/variety.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>'
'''
www.variety.com
'''
@ -14,11 +14,11 @@ class Variety(BasicNewsRecipe):
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
encoding = 'utf8'
publisher = 'Red Business Information'
category = 'Entertainment Industry News, Daily Variety, Movie Reviews, TV, Awards, Oscars, Cannes, Box Office, Hollywood'
language = 'en'
masthead_url = 'http://a330.g.akamai.net/7/330/23382/20090528190853/www.variety.com/graphics/variety/Variety_logo_green_tm.gif'
masthead_url = 'http://images1.variety.com/graphics/variety/Variety_logo_green_tm.gif'
extra_css = ' body{font-family: Georgia,"Times New Roman",Times,Courier,serif } img{margin-bottom: 1em} '
conversion_options = {
@ -30,17 +30,10 @@ class Variety(BasicNewsRecipe):
remove_tags = [dict(name=['object','link','map'])]
keep_only_tags = [dict(name='div', attrs={'id':'article'})]
keep_only_tags = [dict(name='div', attrs={'class':'art control'})]
feeds = [(u'News & Articles', u'http://feeds.feedburner.com/variety/headlines' )]
def print_version(self, url):
rpt = url.rpartition('?')[0]
artid = rpt.rpartition('/')[2]
catidr = url.rpartition('categoryid=')[2]
catid = catidr.partition('&')[0]
return 'http://www.variety.com/index.asp?layout=print_story&articleid=' + artid + '&categoryid=' + catid
def preprocess_html(self, soup):
return self.adeify_images(soup)
rpt = url.rpartition('.html')[0]
return rpt + '?printerfriendly=true'