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 2013-07-25 18:42:24 +05:30
parent 6a15163b1d
commit 805421573d
1 changed files with 15 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
recipes/mediapart.recipe
View File

@ -1,10 +1,10 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010-2012, Louis Gesbert <meta at antislash dot info>; 2013, Malah <malah at neuf.fr>' __copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010-2012, Louis Gesbert <meta at antislash dot info>; 2013, Malah <malah at neuf dot fr>'
''' '''
Mediapart Mediapart
''' '''
__author__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010-2012, Louis Gesbert <meta at antislash dot info>; 2013, Malah <malah at neuf.fr>' __author__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010-2012, Louis Gesbert <meta at antislash dot info>; 2013, Malah <malah at neuf dot fr>'
import re import re
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
@ -29,19 +29,26 @@ class Mediapart(BasicNewsRecipe):
('Les articles', 'http://www.mediapart.fr/articles/feed'), ('Les articles', 'http://www.mediapart.fr/articles/feed'),
] ]
# -- print-version # -- full-page-version
conversion_options = { 'smarten_punctuation' : True } conversion_options = {'smarten_punctuation' : True}
remove_tags = [ dict(name='div', attrs={'class':'print-source_url'}) ] keep_only_tags = [
dict(name='div', attrs={'class':'col-left fractal-desktop fractal-10-desktop collapse-7-desktop fractal-tablet fractal-6-tablet collapse-4-tablet'}),
dict(name='div', attrs={'id':'pageFirstContent'})
]
remove_tags = [
dict(name='div', attrs={'id':'lire-aussi'}),
dict(name='div', attrs={'class':'col-right-content'})
]
def print_version(self, url): def print_version(self, url):
raw = self.browser.open(url).read() raw = self.browser.open(url).read()
soup = BeautifulSoup(raw.decode('utf8', 'replace')) soup = BeautifulSoup(raw.decode('utf8', 'replace'))
link = soup.find('a', {'href':re.compile('^/print/[0-9]+')}) link = soup.find('a', {'href':re.compile('^.*?onglet=full$')})
if link is None: if link is None:
return None return None
return 'http://www.mediapart.fr' + link['href'] return link['href']
# -- Handle login # -- Handle login
@ -62,3 +69,4 @@ class Mediapart(BasicNewsRecipe):
legend.insert(0, Tag(soup, 'br', [])) legend.insert(0, Tag(soup, 'br', []))
legend.name = 'small' legend.name = 'small'
return soup return soup