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 Courrier International

Browse Source
This commit is contained in:
Kovid Goyal 2015-03-27 17:40:46 +05:30
parent fe1eb2a2a2
commit a0c0c43703
1 changed files with 24 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
recipes/courrierinternational.recipe
View File

@ -1,8 +1,8 @@
#!/usr/bin/env python2 #!/usr/bin/env python
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '''2009, Mathieu Godlewski <mathieu at godlewski.fr> __copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>\
2014, Rémi Vanicat <vanicat at debian.org>''' 2014, 2015, Rémi Vanicat <vanicat at debian.org'
''' '''
Courrier International Courrier International
''' '''
@ -25,23 +25,22 @@ class CourrierInternational(BasicNewsRecipe):
html2lrf_options = ['--base-font-size', '10'] html2lrf_options = ['--base-font-size', '10']
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'class':'dessin'}), dict(name='div', attrs={'class':'article-content'}),
dict(name='div', attrs={'class':'story-content'}),
] ]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':re.compile('story-share storylinks|pager|event-expand')}), dict(name='aside', attrs={'class':re.compile('article-sitesocial|article-ad')}),
dict(name='li', attrs={'class':'event-partage_outils'}),
dict(name='li', attrs={'class':'story-comment-link'}),
] ]
needs_subscription = "optional" needs_subscription = "optional"
login_url = 'http://www.courrierinternational.com/login' login_url = 'http://www.courrierinternational.com/login'
def get_browser(self): def get_browser(self):
def is_form_login(form):
return "id" in form.attrs and form.attrs['id'] == "user-login-form"
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
if self.username: if self.username:
br.open(self.login_url) br.open(self.login_url)
br.select_form(nr=1) br.select_form(predicate=is_form_login)
br['name'] = self.username br['name'] = self.username
br['pass'] = self.password br['pass'] = self.password
br.submit() br.submit()
@ -54,23 +53,20 @@ class CourrierInternational(BasicNewsRecipe):
feeds = [ feeds = [
# Some articles requiring subscription fails on download. # Some articles requiring subscription fails on download.
('A la Une', 'http://www.courrierinternational.com/rss/rss_a_la_une.xml'), ('Tous', 'http://www.courrierinternational.com/feed/all/rss.xml'),
('France', 'http://courrierint.com/rss/rp/14/0/rss.xml'), # ('France', 'http://courrierint.com/rss/rp/14/0/rss.xml'),
('Europe', 'http://courrierint.com/rss/rp/15/0/rss.xml'), # ('Europe', 'http://courrierint.com/rss/rp/15/0/rss.xml'),
('Amerique', 'http://courrierint.com/rss/rp/16/0/rss.xml'), # ('Amerique', 'http://courrierint.com/rss/rp/16/0/rss.xml'),
('Asie', 'http://courrierint.com/rss/rp/17/0/rss.xml'), # ('Asie', 'http://courrierint.com/rss/rp/17/0/rss.xml'),
('Afrique', 'http://courrierint.com/rss/rp/18/0/rss.xml'), # ('Afrique', 'http://courrierint.com/rss/rp/18/0/rss.xml'),
('Moyen-Orient', 'http://courrierint.com/rss/rp/19/0/rss.xml'), # ('Moyen-Orient', 'http://courrierint.com/rss/rp/19/0/rss.xml'),
('Economie', 'http://courrierint.com/rss/rp/20/0/rss.xml'), # ('Economie', 'http://courrierint.com/rss/rp/20/0/rss.xml'),
('Multimedia', 'http://courrierint.com/rss/rp/23/0/rss.xml'), # ('Multimedia', 'http://courrierint.com/rss/rp/23/0/rss.xml'),
('Sciences', 'http://courrierint.com/rss/rp/22/0/rss.xml'), # ('Sciences', 'http://courrierint.com/rss/rp/22/0/rss.xml'),
('Culture', 'http://courrierint.com/rss/rp/24/0/rss.xml'), # ('Culture', 'http://courrierint.com/rss/rp/24/0/rss.xml'),
('Insolites', 'http://courrierint.com/rss/rp/26/0/rss.xml'), # ('Insolites', 'http://courrierint.com/rss/rp/26/0/rss.xml'),
('Cartoons', 'http://cs.courrierint.com/rss/all/rss.xml'), # ('Cartoons', 'http://cs.courrierint.com/rss/all/rss.xml'),
('Environnement', 'http://vt.courrierint.com/rss/all/rss.xml'), # ('Environnement', 'http://vt.courrierint.com/rss/all/rss.xml'),
('Cinema', 'http://ca.courrierint.com/rss/all/rss.xml'), # ('Cinema', 'http://ca.courrierint.com/rss/all/rss.xml'),
('Sport', 'http://st.courrierint.com/rss/all/rss.xml'), # ('Sport', 'http://st.courrierint.com/rss/all/rss.xml'),
] ]
def print_version(self, url):
return url + '?page=all'