Update PC Magazine

This commit is contained in:
Kovid Goyal 2014-06-07 13:23:16 +05:30
parent d5e2c1f4cc
commit fe0a84985a

View File

@ -29,6 +29,7 @@ class pcMag(BasicNewsRecipe):
oldest_article = 15
max_articles_per_feed = 25
use_embedded_content = False
auto_cleanup = True
recursion = 10
remove_javascript = True
@ -47,13 +48,13 @@ class pcMag(BasicNewsRecipe):
(u'Technology News from Ziff Davis', u'http://rssnewsapps.ziffdavis.com/pcmagbreakingnews.xml')
]
keep_only_tags = [dict(attrs={'class':'content-page'})]
remove_tags = [
dict(attrs={'class':['control-side','comment','highlights_content','btn-holder','subscribe-panel',
'grey-box comments-box']}),
dict(id=['inlineDigg']),
dict(text=lambda text:isinstance(text, Comment)),
dict(name='img', width='1'),
]
preprocess_regexps = [(re.compile(r"<img '[^']+?'"), lambda m : '<img ')]
#keep_only_tags = [dict(attrs={'class':'content-page'})]
#remove_tags = [
#dict(attrs={'class':['control-side','comment','highlights_content','btn-holder','subscribe-panel',
#'grey-box comments-box']}),
#dict(id=['inlineDigg']),
#dict(text=lambda text:isinstance(text, Comment)),
#dict(name='img', width='1'),
#]
#preprocess_regexps = [(re.compile(r"<img '[^']+?'"), lambda m : '<img ')]