nojhan/weboob-devel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

get the correct name of the video

Browse source 
Signed-off-by: franek <franek@chicour.net>
This commit is contained in:
franek 2013-04-01 11:52:35 +02:00 • committed by Florent
commit b6f46ab694
1 changed files with 10 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

15
modules/arretsurimages/pages.py
View file

@ -71,26 +71,31 @@ class VideoPage(BasePage):
def get_video(self, video=None): def get_video(self, video=None):
if not video: if not video:
video = ArretSurImagesVideo(self.get_id) video = ArretSurImagesVideo(self.get_id())
video.title = unicode(self.get_title()) video.title = unicode(self.get_title())
video.url = unicode(self.get_url()) video.url = unicode(self.get_url())
video.set_empty_fields(NotAvailable) video.set_empty_fields(NotAvailable)
return video return video
def get_firstUrl(self):
obj = self.parser.select(self.document.getroot(), 'a.bouton-telecharger', 1)
firstUrl = obj.attrib['href']
return firstUrl
def get_title(self): def get_title(self):
title = self.document.getroot().cssselect('div[id=titrage-contenu] h1')[0].text title = self.document.getroot().cssselect('div[id=titrage-contenu] h1')[0].text
return title; return title;
def get_id(self): def get_id(self):
m = self.URL_REGEXP.match(self['url']) m = re.match(r'http://videos.arretsurimages.net/telecharger/(.*)', self.get_firstUrl())
_id = ''
if m: if m:
return self.create_id(m.group(1)) return m.group(1)
self.logger.warning('Unable to parse ID') self.logger.warning('Unable to parse ID')
return 0 return 0
def get_url(self): def get_url(self):
obj = self.parser.select(self.document.getroot(), 'a.bouton-telecharger', 1) firstUrl = self.get_firstUrl()
firstUrl = obj.attrib['href']
doc = self.browser.get_document(self.browser.openurl(firstUrl)) doc = self.browser.get_document(self.browser.openurl(firstUrl))
links = doc.xpath('//a'); links = doc.xpath('//a');
url = None; url = None;