This commit is contained in:
Kovid Goyal 2014-03-19 09:40:29 +05:30
parent 0e36f48c19
commit 6e81aa8442

View File

@ -48,14 +48,14 @@ class Guardian(BasicNewsRecipe):
# article history link # article history link
dict(name='a', attrs={'class':["rollover history-link"]}), dict(name='a', attrs={'class':["rollover history-link"]}),
# "a version of this article ..." speil # "a version of this article ..." speil
dict(name='div' , attrs = { 'class' : ['section']}), dict(name='div' , attrs={'class' : ['section']}),
# "about this article" js dialog # "about this article" js dialog
dict(name='div', attrs={'class':["share-top",]}), dict(name='div', attrs={'class':["share-top",]}),
# author picture # author picture
dict(name='img', attrs={'class':["contributor-pic-small"]}), dict(name='img', attrs={'class':["contributor-pic-small"]}),
# embedded videos/captions # embedded videos/captions
dict(name='span',attrs={'class' : ['inline embed embed-media']}), dict(name='span',attrs={'class' : ['inline embed embed-media']}),
#dict(name='img'), # dict(name='img'),
] ]
use_embedded_content = False use_embedded_content = False
@ -104,7 +104,7 @@ class Guardian(BasicNewsRecipe):
# removes number next to rating stars # removes number next to rating stars
items_to_remove = [] items_to_remove = []
rating_container = soup.find('div', attrs = {'class': ['rating-container']}) rating_container = soup.find('div', attrs={'class': ['rating-container']})
if rating_container: if rating_container:
for item in rating_container: for item in rating_container:
if isinstance(item, Tag) and str(item.name) == 'span': if isinstance(item, Tag) and str(item.name) == 'span':
@ -119,7 +119,7 @@ class Guardian(BasicNewsRecipe):
# soup = self.index_to_soup("http://www.guardian.co.uk/theobserver") # soup = self.index_to_soup("http://www.guardian.co.uk/theobserver")
soup = self.index_to_soup(self.base_url) soup = self.index_to_soup(self.base_url)
# find cover pic # find cover pic
img = soup.find( 'img',attrs ={'alt':self.cover_pic}) img = soup.find('img',attrs={'alt':self.cover_pic})
if img is not None: if img is not None:
self.cover_url = img['src'] self.cover_url = img['src']
# end find cover pic # end find cover pic
@ -149,7 +149,8 @@ class Guardian(BasicNewsRecipe):
continue continue
tt = li.find('div', attrs={'class':'trailtext'}) tt = li.find('div', attrs={'class':'trailtext'})
if tt is not None: if tt is not None:
for da in tt.findAll('a'): da.extract() for da in tt.findAll('a'):
da.extract()
desc = self.tag_to_string(tt).strip() desc = self.tag_to_string(tt).strip()
yield { yield {
'title': title, 'url':url, 'description':desc, 'title': title, 'url':url, 'description':desc,
@ -161,4 +162,3 @@ class Guardian(BasicNewsRecipe):
for title, href in self.find_sections(): for title, href in self.find_sections():
feeds.append((title, list(self.find_articles(href)))) feeds.append((title, list(self.find_articles(href))))
return feeds return feeds