Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update mediapart.fr

Browse Source
This commit is contained in:
Kovid Goyal 2013-07-07 22:47:57 +05:30
parent e64ff83e07
commit 08834f636a
1 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
recipes/mediapart.recipe
View File

@ -1,17 +1,18 @@
__license__ = 'GPL v3'
__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010-2012, Louis Gesbert <meta at antislash dot info>'
__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010-2012, Louis Gesbert <meta at antislash dot info>; 2013, Malah <malah at neuf.fr>'
'''
Mediapart
'''
__author__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010-2012, Louis Gesbert <meta at antislash dot info>'
__author__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010-2012, Louis Gesbert <meta at antislash dot info>; 2013, Malah <malah at neuf.fr>'
import re
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
from calibre.web.feeds.news import BasicNewsRecipe
class Mediapart(BasicNewsRecipe):
title = 'Mediapart'
__author__ = 'Mathieu Godlewski, Louis Gesbert'
__author__ = 'Mathieu Godlewski, Louis Gesbert, Malah'
description = 'Global news in french from news site Mediapart'
oldest_article = 7
language = 'fr'
@ -21,6 +22,7 @@ class Mediapart(BasicNewsRecipe):
use_embedded_content = False
no_stylesheets = True
masthead_url = 'https://upload.wikimedia.org/wikipedia/fr/2/23/Mediapart.png'
cover_url = 'http://static.mediapart.fr/files/pave_mediapart.jpg'
feeds = [
@ -36,18 +38,18 @@ class Mediapart(BasicNewsRecipe):
def print_version(self, url):
raw = self.browser.open(url).read()
soup = BeautifulSoup(raw.decode('utf8', 'replace'))
link = soup.find('a', {'title':'Imprimer'})
link = soup.find('a', {'href':re.compile('^/print/[0-9]+')})
if link is None:
return None
return link['href']
return 'http://www.mediapart.fr' + link['href']
# -- Handle login
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None:
br.open('http://www.mediapart.fr/')
br.select_form(nr=0)
br.open('http://blogs.mediapart.fr/editions/guide-du-coordonnateur-d-edition')
br.select_form(nr=1)
br['name'] = self.username
br['pass'] = self.password
br.submit()