mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-11-25 07:45:01 -05:00
62 lines
2.5 KiB
Python
62 lines
2.5 KiB
Python
#!/usr/bin/env python
|
|
__license__ = 'GPL v3'
|
|
|
|
__copyright__ = '2010, Szing'
|
|
__docformat__ = 'restructuredtext en'
|
|
|
|
'''
|
|
globeandmail.com
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class AdvancedUserRecipe1287083651(BasicNewsRecipe):
|
|
title = u'Globe & Mail'
|
|
__license__ = 'GPL v3'
|
|
__author__ = 'Szing'
|
|
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'Auto', u'http://www.theglobeandmail.com/sports/?service=rss'),
|
|
(u'Sports', u'http://www.theglobeandmail.com/auto/?service=rss')
|
|
]
|
|
|
|
keep_only_tags = [
|
|
dict(name='h1'),
|
|
dict(name='h2', attrs={'id':'articletitle'}),
|
|
dict(name='p', attrs={'class':['leadText', 'meta', 'leadImage', 'redtext byline', 'bodyText']}),
|
|
dict(name='div', attrs={'class':['news','articlemeta','articlecopy']}),
|
|
dict(name='id', attrs={'class':'article'}),
|
|
dict(name='table', attrs={'class':'todays-market'}),
|
|
dict(name='header', attrs={'id':'leadheader'})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name='div', attrs={'id':['tabInside', 'ShareArticles', 'topStories']})
|
|
]
|
|
|
|
#this has to be here or the text in the article appears twice.
|
|
remove_tags_after = [dict(id='article')]
|
|
|
|
#Use the mobile version rather than the web version
|
|
def print_version(self, url):
|
|
return url + '&service=mobile'
|
|
|