mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
36 lines
1.2 KiB
Plaintext
36 lines
1.2 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class SanFranciscoBayGuardian(BasicNewsRecipe):
|
|
title = u'San Francisco Bay Guardian'
|
|
language = 'en'
|
|
__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'),
|
|
]
|
|
|
|
|
|
#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
|