calibre/recipes/dominion.recipe

51 lines
1.6 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class stuffconz(BasicNewsRecipe):
title = u'stuff.co.nz'
language = 'en_NZ'
__author__ = 'Krittika Goyal'
oldest_article = 1 #days
max_articles_per_feed = 25
#encoding = 'latin1'
remove_stylesheets = True
#remove_tags_before = dict(name='h1', attrs={'class':'heading'})
remove_tags_after = dict(name='div', attrs={'id':'related_box'})
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':['story_feature_title']}),
dict(name='div', attrs={'id':['toolbox', 'related_box', 'adSTORYBODY']}),
dict(name='span', attrs={'class':['related_link', 'slideshowcontrols']}),
#dict(name='ul', attrs={'class':'articleTools'}),
]
feeds = [
('Dominion Post',
'http://www.stuff.co.nz/rss/dominion-post'),
('National',
'http://www.stuff.co.nz/rss/national'),
('World',
'http://www.stuff.co.nz/rss/world'),
('Business',
'http://www.stuff.co.nz/rss/business'),
('Technology',
'http://www.stuff.co.nz/rss/technology'),
('Sport',
'http://www.stuff.co.nz/rss/sport'),
('Entertainment',
'http://www.stuff.co.nz/rss/entertainment'),
('Life and Style',
'http://www.stuff.co.nz/rss/life-style'),
]
def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'id':'left_col'})
#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