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 Daily Mail

Browse Source
This commit is contained in:
Kovid Goyal 2013-12-19 21:27:14 +05:30
parent 1c7ca5b803
commit 717e8ccdd4
1 changed files with 13 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
recipes/daily_mail.recipe
View File

@ -8,6 +8,8 @@ class TheDailyMail(BasicNewsRecipe):
author = 'RufusA and Sujata Raman'
simultaneous_downloads= 1
max_articles_per_feed = 50
use_embedded_content = False
auto_cleanup = True
extra_css = '''#js-article-text{font-family:Arial,Helvetica,sans-serif;}
h1{font-size:x-large; font-weight:bold;}
@ -18,33 +20,18 @@ class TheDailyMail(BasicNewsRecipe):
'''
remove_tags = [ dict(name='div', attrs={'class':['article-icon-links-container','print-or-mail-links cleared',
'social-links cleared','explore-links','relatedItems','intellicrumbs box','travel','moduleHalf']}),
dict(name='div', attrs={'id':['link-unit-wrapper','pushdown-ad','reader-comments','googleAds',]}),
dict(name='h3', attrs={'class':['social-links-title']}),
dict(name='span', attrs={'class':['clickToEnlargeTop']}),
]
#remove_tags_before = dict(name='div', attrs={'id':'content'})
keep_only_tags = [dict(name='div', attrs={'id':'js-article-text'})]
no_stylesheets = True
feeds = [
(u'Home', u'http://www.dailymail.co.uk/home/index.rss'),
(u'News', u'http://www.dailymail.co.uk/news/index.rss'),
(u'Sport', u'http://www.dailymail.co.uk/sport/index.rss'),
(u'TV and Showbiz', u'http://www.dailymail.co.uk/tvshowbiz/index.rss'),
(u'Femail', u'http://www.dailymail.co.uk/femail/index.rss'),
(u'Health', u'http://www.dailymail.co.uk/health/index.rss'),
(u'Science and Technology', u'http://www.dailymail.co.uk/sciencetech/index.rss'),
(u'Money', u'http://www.dailymail.co.uk/money/index.rss'),
(u'Property', u'http://www.dailymail.co.uk/property/index.rss'),
(u'Motoring', u'http://www.dailymail.co.uk/motoring/index.rss'),
(u'Travel', u'http://www.dailymail.co.uk/travel/index.rss')
(u'Home', u'http://www.dailymail.co.uk/home/index.rss'),
(u'News', u'http://www.dailymail.co.uk/news/index.rss'),
(u'Sport', u'http://www.dailymail.co.uk/sport/index.rss'),
(u'TV and Showbiz', u'http://www.dailymail.co.uk/tvshowbiz/index.rss'),
(u'Femail', u'http://www.dailymail.co.uk/femail/index.rss'),
(u'Health', u'http://www.dailymail.co.uk/health/index.rss'),
(u'Science and Technology', u'http://www.dailymail.co.uk/sciencetech/index.rss'),
(u'Money', u'http://www.dailymail.co.uk/money/index.rss'),
(u'Property', u'http://www.dailymail.co.uk/property/index.rss'),
(u'Motoring', u'http://www.dailymail.co.uk/motoring/index.rss'),
(u'Travel', u'http://www.dailymail.co.uk/travel/index.rss')
]
#def print_version(self, url):
# main = url.partition('?')[0]
# return main + '?printingPage=true'