calibre/resources/recipes/independent.recipe
Kovid Goyal 75a138348e ...
2010-01-01 11:43:18 -07:00

56 lines
2.1 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class TheIndependent(BasicNewsRecipe):
title = u'The Independent'
language = 'en_GB'
__author__ = 'Krittika Goyal'
oldest_article = 1 #days
max_articles_per_feed = 25
encoding = 'latin1'
no_stylesheets = True
#remove_tags_before = dict(name='h1', attrs={'class':'heading'})
#remove_tags_after = dict(name='td', attrs={'class':'newptool1'})
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':'related-articles'}),
dict(name='div', attrs={'id':['qrformdiv', 'inSection', 'alpha-inner']}),
dict(name='ul', attrs={'class':'article-tools'}),
dict(name='ul', attrs={'class':'articleTools'}),
]
feeds = [
('UK',
'http://www.independent.co.uk/news/uk/rss'),
('World',
'http://www.independent.co.uk/news/world/rss'),
('Sport',
'http://www.independent.co.uk/sport/rss'),
('Arts and Entertainment',
'http://www.independent.co.uk/arts-entertainment/rss'),
('Business',
'http://www.independent.co.uk/news/business/rss'),
('Life and Style',
'http://www.independent.co.uk/life-style/gadgets-and-tech/news/rss'),
('Science',
'http://www.independent.co.uk/news/science/rss'),
('People',
'http://www.independent.co.uk/news/people/rss'),
('Media',
'http://www.independent.co.uk/news/media/rss'),
('Health and Families',
'http://www.independent.co.uk/life-style/health-and-families/rss'),
('Obituaries',
'http://www.independent.co.uk/news/obituaries/rss'),
]
def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'id':'mainColumn'})
#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