Fix San Francisco Bay Guardian

This commit is contained in:
Kovid Goyal 2012-07-23 15:09:43 +05:30
parent 73a40c78a1
commit 9015213161

View File

@ -6,20 +6,30 @@ class SanFranciscoBayGuardian(BasicNewsRecipe):
__author__ = 'Krittika Goyal'
oldest_article = 31 #days
max_articles_per_feed = 25
#encoding = 'latin1'
no_stylesheets = True
#remove_tags_before = dict(name='div', attrs={'id':'story_header'})
#remove_tags_after = dict(name='div', attrs={'id':'shirttail'})
remove_tags = [
dict(name='iframe'),
#dict(name='div', attrs={'class':'related-articles'}),
#dict(name='div', attrs={'id':['story_tools', 'toolbox', 'shirttail', 'comment_widget']}),
#dict(name='ul', attrs={'class':'article-tools'}),
#dict(name='ul', attrs={'id':'story_tabs'}),
]
feeds = [
('sfbg', 'http://www.sfbg.com/rss.xml'),
('politics', 'http://www.sfbg.com/politics/rss.xml'),
('blogs', 'http://www.sfbg.com/blog/rss.xml'),
('pixel_vision', 'http://www.sfbg.com/pixel_vision/rss.xml'),
('bruce', 'http://www.sfbg.com/bruce/rss.xml'),
]
#def preprocess_html(self, soup):
#story = soup.find(name='div', attrs={'id':'story_body'})
#td = heading.findParent(name='td')
#td.extract()
#soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
#body = soup.find(name='body')
#body.insert(0, story)
#return soup