Fix #7180 (Fox news website changed)

This commit is contained in:
Kovid Goyal 2010-10-21 07:51:31 -07:00
parent 6dce871b05
commit eafc6e72c1

View File

@ -4,7 +4,6 @@ __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
foxnews.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class FoxNews(BasicNewsRecipe):
@ -21,11 +20,10 @@ class FoxNews(BasicNewsRecipe):
language = 'en'
publication_type = 'newsportal'
remove_empty_feeds = True
extra_css = ' body{font-family: Arial,sans-serif } img{margin-bottom: 0.4em} .caption{font-size: x-small} '
preprocess_regexps = [
(re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE),lambda match: '</title></head>')
]
extra_css = """
body{font-family: Arial,sans-serif }
.caption{font-size: x-small}
"""
conversion_options = {
'comment' : description
@ -34,27 +32,15 @@ class FoxNews(BasicNewsRecipe):
, 'language' : language
}
remove_attributes = ['xmlns']
keep_only_tags = [
dict(name='div', attrs={'id' :['story','browse-story-content']})
,dict(name='div', attrs={'class':['posts articles','slideshow']})
,dict(name='h4' , attrs={'class':'storyDate'})
,dict(name='h1' , attrs={'xmlns:functx':'http://www.functx.com'})
,dict(name='div', attrs={'class':'authInfo'})
,dict(name='div', attrs={'id':'articleCont'})
]
remove_attributes = ['xmlns','lang']
remove_tags = [
dict(name='div', attrs={'class':['share-links','quigo quigo2','share-text','storyControls','socShare','btm-links']})
,dict(name='div', attrs={'id' :['otherMedia','loomia_display','img-all-path','story-vcmId','story-url','pane-browse-story-comments','story_related']})
,dict(name='ul' , attrs={'class':['tools','tools alt','tools alt2','tabs']})
,dict(name='a' , attrs={'class':'join-discussion'})
,dict(name='ul' , attrs={'class':['tools','tools alt','tools alt2']})
,dict(name='p' , attrs={'class':'see_fullarchive'})
,dict(name=['object','embed','link','script'])
dict(name=['object','embed','link','script','iframe','meta','base'])
,dict(attrs={'class':['user-control','url-description','ad-context']})
]
remove_tags_before=dict(name='h1')
remove_tags_after =dict(attrs={'class':'url-description'})
feeds = [
(u'Latest Headlines', u'http://feeds.foxnews.com/foxnews/latest' )
@ -67,8 +53,5 @@ class FoxNews(BasicNewsRecipe):
,(u'Entertainment' , u'http://feeds.foxnews.com/foxnews/entertainment' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)
def print_version(self, url):
return url + 'print'