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 Fox News

Browse Source
This commit is contained in:
Kovid Goyal 2015-12-20 22:16:10 +05:30
parent 6a0c039d93
commit debb1a3968
1 changed files with 3 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
recipes/foxnews.recipe
View File

@ -35,13 +35,9 @@ class FoxNews(BasicNewsRecipe):
remove_attributes = ['xmlns','lang']
remove_tags=[
dict(attrs={'class':['user-control','logo','ad-300x250','url-description']})
,dict(name=['meta','base','link','iframe','object','embed'])
]
keep_only_tags=[dict(attrs={'id':'article-print'})]
remove_tags_after =dict(attrs={'class':'url-description'})
keep_only_tags = [
dict(itemprop=['headline', 'articleBody']),
]
feeds = [
(u'Latest Headlines', u'http://feeds.foxnews.com/foxnews/latest' )
@ -54,26 +50,3 @@ class FoxNews(BasicNewsRecipe):
,(u'Entertainment' , u'http://feeds.foxnews.com/foxnews/entertainment' )
]
def print_version(self, url):
return url + 'print'
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('a'):
limg = item.find('img')
if item.string is not None:
str = item.string
item.replaceWith(str)
else:
if limg:
item.name = 'div'
item.attrs = []
else:
str = self.tag_to_string(item)
item.replaceWith(str)
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
return soup