calibre/recipes/courrierinternational.recipe
Kovid Goyal 4836eb97ba ...
2014-03-25 21:34:41 +05:30

77 lines
2.9 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '''2009, Mathieu Godlewski <mathieu at godlewski.fr>
2014, Rémi Vanicat <vanicat at debian.org>'''
'''
Courrier International
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class CourrierInternational(BasicNewsRecipe):
title = 'Courrier International'
__author__ = 'Mathieu Godlewski <mathieu at godlewski.fr>'
description = 'Global news in french from international newspapers'
oldest_article = 7
language = 'fr'
max_articles_per_feed = 50
no_stylesheets = True
ignore_duplicate_articles = {'title', 'url'}
html2lrf_options = ['--base-font-size', '10']
keep_only_tags = [
dict(name='div', attrs={'class':'dessin'}),
dict(name='div', attrs={'class':'story-content'}),
]
remove_tags = [
dict(name='div', attrs={'class':re.compile('story-share storylinks|pager|event-expand')}),
dict(name='li', attrs={'class':'event-partage_outils'}),
dict(name='li', attrs={'class':'story-comment-link'}),
]
needs_subscription = "optional"
login_url = 'http://www.courrierinternational.com/login'
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username:
br.open(self.login_url)
br.select_form(nr=1)
br['name'] = self.username
br['pass'] = self.password
br.submit()
return br
def preprocess_html(self, soup):
for link in soup.findAll("a",href=re.compile('^/')):
link["href"]='http://www.courrierinternational.com' + link["href"]
return soup
feeds = [
# Some articles requiring subscription fails on download.
('A la Une', 'http://www.courrierinternational.com/rss/rss_a_la_une.xml'),
('France', 'http://courrierint.com/rss/rp/14/0/rss.xml'),
('Europe', 'http://courrierint.com/rss/rp/15/0/rss.xml'),
('Amerique', 'http://courrierint.com/rss/rp/16/0/rss.xml'),
('Asie', 'http://courrierint.com/rss/rp/17/0/rss.xml'),
('Afrique', 'http://courrierint.com/rss/rp/18/0/rss.xml'),
('Moyen-Orient', 'http://courrierint.com/rss/rp/19/0/rss.xml'),
('Economie', 'http://courrierint.com/rss/rp/20/0/rss.xml'),
('Multimedia', 'http://courrierint.com/rss/rp/23/0/rss.xml'),
('Sciences', 'http://courrierint.com/rss/rp/22/0/rss.xml'),
('Culture', 'http://courrierint.com/rss/rp/24/0/rss.xml'),
('Insolites', 'http://courrierint.com/rss/rp/26/0/rss.xml'),
('Cartoons', 'http://cs.courrierint.com/rss/all/rss.xml'),
('Environnement', 'http://vt.courrierint.com/rss/all/rss.xml'),
('Cinema', 'http://ca.courrierint.com/rss/all/rss.xml'),
('Sport', 'http://st.courrierint.com/rss/all/rss.xml'),
]
def print_version(self, url):
return url + '?page=all'