Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-07 09:01:38 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Courrier International

Browse Source
This commit is contained in:
Kovid Goyal 2014-03-25 16:47:51 +05:30
parent 88f19064dc
commit 7a4f106f3d
1 changed files with 46 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
recipes/courrierinternational.recipe
View File

@ -19,23 +19,57 @@ class CourrierInternational(BasicNewsRecipe):
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('^/(notule|sources|comment)')):
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'),
]
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE|re.DOTALL), i[1]) for i in
[
#Handle Depeches
(r'.*<td [^>]*>([0-9][0-9]/.*</p>)</td>.*', lambda match : '<html><body><table><tr><td>'+match.group(1)+'</td></tr></table></body></html>'),
#Handle Articles
(r'.*<td [^>]*>(Courrier international.*?) <td width="10"><img src="/img/espaceur.gif"></td>.*', lambda match : '<html><body><table><tr><td>'+match.group(1)+'</body></html>'),
]
]
def print_version(self, url):
return re.sub('/[a-zA-Z]+\.asp','/imprimer.asp' ,url)
return url + '?page=all'