Update The Guardian

This commit is contained in:
Kovid Goyal 2014-12-06 07:57:26 +05:30
parent 54909e3a59
commit 30ebdfe1f3

View File

@ -38,11 +38,14 @@ class Guardian(BasicNewsRecipe):
ignore_sections = []
timefmt = ' [%a, %d %b %Y]'
keep_only_tags = [
dict(name='div', attrs={'id':["content","article_header","main-article-info",]}),
dict(attrs={'class':lambda x: x and set(x.split()).intersection({'content__head', 'content__main'})}),
]
remove_tags = [
dict(name='div', attrs={'class':["video-content","videos-third-column"]}),
dict(name='div', attrs={'class':[
"video-content","videos-third-column", 'meta__extras', 'submeta-container submeta-container--break-at-leftcol ']}),
dict(name='div', attrs={'id':["article-toolbox","subscribe-feeds",]}),
dict(name='div', attrs={'class':["guardian-tickets promo-component",]}),
dict(name='ul', attrs={'class':["pagination"]}),
@ -57,7 +60,6 @@ class Guardian(BasicNewsRecipe):
dict(name='img', attrs={'class':["contributor-pic-small"]}),
# embedded videos/captions
dict(name='span',attrs={'class' : ['inline embed embed-media']}),
# dict(name='img'),
]
use_embedded_content = False