mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
76 lines
2.3 KiB
Python
76 lines
2.3 KiB
Python
#!/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
|
|
import re
|
|
|
|
class SanFranciscoChronicle(BasicNewsRecipe):
|
|
title = u'San Francisco Chronicle'
|
|
__author__ = u'Darko Miletic and Sujata Raman'
|
|
description = u'San Francisco news'
|
|
language = 'en'
|
|
|
|
oldest_article = 7
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
|
|
|
|
|
|
remove_tags_before = {'id':'printheader'}
|
|
|
|
remove_tags = [
|
|
dict(name='div',attrs={'id':'printheader'})
|
|
,dict(name='a', attrs={'href':re.compile('http://ads\.pheedo\.com.*')})
|
|
,dict(name='div',attrs={'id':'footer'})
|
|
]
|
|
|
|
extra_css = '''
|
|
h1{font-family :Arial,Helvetica,sans-serif; font-size:large;}
|
|
h2{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#666666;}
|
|
h3{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#000000;}
|
|
h4{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
|
|
p{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
|
|
.byline{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
|
|
.date{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
|
|
.dtlcomment{font-style:italic;}
|
|
.georgia h3{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#000000;}
|
|
'''
|
|
|
|
feeds = [
|
|
(u'Top News Stories', u'http://www.sfgate.com/rss/feeds/news.xml')
|
|
]
|
|
|
|
def print_version(self,url):
|
|
url= url +"&type=printable"
|
|
return url
|
|
|
|
def get_article_url(self, article):
|
|
print str(article['title_detail']['value'])
|
|
url = article.get('guid',None)
|
|
url = "http://www.sfgate.com/cgi-bin/article.cgi?f="+url
|
|
if "Presented By:" in str(article['title_detail']['value']):
|
|
url = ''
|
|
return url
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|