calibre/recipes/pajama.recipe

49 lines
1.6 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class PajamasMedia(BasicNewsRecipe):
title = u'Pajamas Media'
description = u'Provides exclusive news and opinion for forty countries.'
language = 'en'
__author__ = 'Krittika Goyal'
oldest_article = 1 #days
max_articles_per_feed = 25
recursions = 1
match_regexps = [r'http://pajamasmedia.com/blog/.*/2/$']
#encoding = 'latin1'
remove_stylesheets = True
#remove_tags_before = dict(name='h1', attrs={'class':'heading'})
remove_tags_after = dict(name='div', attrs={'class':'paged-nav'})
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':['pages']}),
#dict(name='div', attrs={'id':['bookmark']}),
#dict(name='span', attrs={'class':['related_link', 'slideshowcontrols']}),
#dict(name='ul', attrs={'class':'articleTools'}),
]
feeds = [
('pajamas Media',
'http://feeds.feedburner.com/PajamasMedia'),
]
def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'id':'innerpage-content'})
#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
def postprocess_html(self, soup, first):
if not first:
h = soup.find(attrs={'class':'innerpage-header'})
if h: h.extract()
auth = soup.find(attrs={'class':'author'})
if auth: auth.extract()
return soup