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

use URL.id2url to parse url if any, and ignore unwanted urls

Browse source
This commit is contained in:
Romain Bignon 2014-05-17 13:11:26 +02:00
commit b4bdb1fc92
2 changed files with 10 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

17
modules/francetelevisions/browser.py
View file

@ -17,7 +17,6 @@
# You should have received a copy of the GNU Affero General Public License # You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>. # along with weboob. If not, see <http://www.gnu.org/licenses/>.
import requests
from weboob.tools.browser2 import PagesBrowser, URL from weboob.tools.browser2 import PagesBrowser, URL
from .pages import IndexPage, VideoPage from .pages import IndexPage, VideoPage
@ -30,23 +29,23 @@ class PluzzBrowser(PagesBrowser):
BASEURL = 'http://pluzz.francetv.fr' BASEURL = 'http://pluzz.francetv.fr'
index_page = URL('recherche\?recherche=(?P<pattern>.*)', IndexPage) index_page = URL(r'recherche\?recherche=(?P<pattern>.*)', IndexPage)
latest_page = URL('lesplusrecents', IndexPage) latest_page = URL(r'lesplusrecents', IndexPage)
video_page = URL('http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/\?idDiffusion=(?P<_id>.*)&catalogue=Pluzz', VideoPage) video_page = URL(r'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/\?idDiffusion=(?P<id>.*)&catalogue=Pluzz', VideoPage)
def search_videos(self, pattern): def search_videos(self, pattern):
return self.index_page.go(pattern=pattern).iter_videos() return self.index_page.go(pattern=pattern).iter_videos()
def get_video(self, _id, video=None): @video_page.id2url
video = self.video_page.go(_id=_id).get_video(obj=video) def get_video(self, url, video=None):
self.location(url)
video = self.page.get_video(obj=video)
for item in self.read_url(video.url): for item in self.read_url(video.url):
pass
video.url = u'%s' % item video.url = u'%s' % item
return video return video
def read_url(self, url): def read_url(self, url):
r = requests.get(url, stream=True) r = self.open(url, stream=True)
buf = r.iter_lines() buf = r.iter_lines()
r.close() r.close()
return buf return buf

2
modules/francetelevisions/pages.py
View file

@ -74,7 +74,7 @@ class VideoPage(JsonPage):
self.env['url'] = video['url'] self.env['url'] = video['url']
obj_id = Env('_id') obj_id = Env('id')
obj_title = Format(u'%s - %s', Dict('titre'), Dict('sous_titre')) obj_title = Format(u'%s - %s', Dict('titre'), Dict('sous_titre'))
obj_url = Env('url') obj_url = Env('url')
obj_date = DateTime(Dict('diffusion/date_debut')) obj_date = DateTime(Dict('diffusion/date_debut'))