Quote:
Originally Posted by girlperson1
|
Code:
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
sfgate.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class sfgate(BasicNewsRecipe):
title = u'San Francisco Chronicle'
__author__ = u'Darko Miletic'
description = u'San Francisco news'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
keep_only_tags = [dict(name='td' , attrs={'class':'column1 w627'})]
remove_tags_after = dict(name='div', attrs={'id':'articlecontent' })
remove_tags = [
dict(name='div', attrs={'class':'tools tools_top'})
,dict(name='div', attrs={'id':'articlebox' })
]
feeds = [
(u'Top News Stories', u'http://www.sfgate.com/rss/feeds/news.xml')
]