mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
San Francisco Bay Guardian by Krittika Goyal
This commit is contained in:
parent
9c371377b6
commit
bf91ca5e93
42
resources/recipes/sfbg.recipe
Normal file
42
resources/recipes/sfbg.recipe
Normal file
@ -0,0 +1,42 @@
|
|||||||
|
from calibre.web.feeds.news import BasicNewsRecipe
|
||||||
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
||||||
|
|
||||||
|
class SanFranciscoBayGuardian(BasicNewsRecipe):
|
||||||
|
title = u'San Francisco Bay Guardian'
|
||||||
|
language = 'en'
|
||||||
|
__author__ = 'Krittika Goyal'
|
||||||
|
oldest_article = 1 #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 = [
|
||||||
|
('Cover', 'http://www.newsobserver.com/100/index.rss'),
|
||||||
|
('News', 'http://www.newsobserver.com/102/index.rss'),
|
||||||
|
('Politics', 'http://www.newsobserver.com/105/index.rss'),
|
||||||
|
('Business', 'http://www.newsobserver.com/104/index.rss'),
|
||||||
|
('Sports', 'http://www.newsobserver.com/103/index.rss'),
|
||||||
|
('College Sports', 'http://www.newsobserver.com/119/index.rss'),
|
||||||
|
('Lifestyles', 'http://www.newsobserver.com/106/index.rss'),
|
||||||
|
('Editorials', 'http://www.newsobserver.com/158/index.rss')]
|
||||||
|
|
||||||
|
|
||||||
|
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
|
Loading…
x
Reference in New Issue
Block a user