calibre/recipes/globe_and_mail.recipe

65 lines
2.6 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Szing'
__docformat__ = 'restructuredtext en'
'''
globeandmail.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1287083651(BasicNewsRecipe):
title = u'Globe & Mail'
__author__ = 'Kovid Goyal'
oldest_article = 2
no_stylesheets = True
max_articles_per_feed = 100
encoding = 'utf8'
publisher = 'Globe & Mail'
language = 'en_CA'
extra_css = 'p.meta {font-size:75%}\n .redtext {color: red;}\n .byline {font-size: 70%}'
feeds = [
(u'Top National Stories', u'http://www.theglobeandmail.com/news/national/?service=rss'),
(u'Business', u'http://www.theglobeandmail.com/report-on-business/?service=rss'),
(u'Commentary', u'http://www.theglobeandmail.com/report-on-business/commentary/?service=rss'),
(u'Blogs', u'http://www.theglobeandmail.com/blogs/?service=rss'),
(u'Facts & Arguments', u'http://www.theglobeandmail.com/life/facts-and-arguments/?service=rss'),
(u'Technology', u'http://www.theglobeandmail.com/news/technology/?service=rss'),
(u'Investing', u'http://www.theglobeandmail.com/globe-investor/?service=rss'),
(u'Top Polical Stories', u'http://www.theglobeandmail.com/news/politics/?service=rss'),
(u'Arts', u'http://www.theglobeandmail.com/news/arts/?service=rss'),
(u'Life', u'http://www.theglobeandmail.com/life/?service=rss'),
(u'Real Estate', u'http://www.theglobeandmail.com/real-estate/?service=rss'),
(u'Sports', u'http://www.theglobeandmail.com/sports/?service=rss'),
(u'Drive', u'http://www.theglobeandmail.com/auto/?service=rss')
]
preprocess_regexps = [
(re.compile(r'<head.*?</head>', re.DOTALL), lambda m: '<head></head>'),
(re.compile(r'<script.*?</script>', re.DOTALL), lambda m: ''),
]
remove_tags_before = dict(name='h1')
remove_tags = [
dict(name='div', attrs={'id':['ShareArticles', 'topStories']}),
dict(href=lambda x: x and 'tracking=' in x),
{'class':['articleTools', 'pagination', 'Ads', 'topad',
'breadcrumbs', 'footerNav', 'footerUtil', 'downloadlinks']}]
def populate_article_metadata(self, article, soup, first):
if first and hasattr(self, 'add_toc_thumbnail'):
picdiv = soup.find('img')
if picdiv is not None:
self.add_toc_thumbnail(article,picdiv['src'])
#Use the mobile version rather than the web version
def print_version(self, url):
return url.rpartition('?')[0] + '?service=mobile'