Extractor for canalc2.tv

This commit is contained in:
Pierre Rudloff 2013-08-22 13:54:23 +02:00
parent 05a2926c5c
commit cd0abcc0bb
2 changed files with 38 additions and 0 deletions

View File

@ -7,6 +7,7 @@
from .breakcom import BreakIE from .breakcom import BreakIE
from .brightcove import BrightcoveIE from .brightcove import BrightcoveIE
from .canalplus import CanalplusIE from .canalplus import CanalplusIE
from .canalc2 import Canalc2IE
from .collegehumor import CollegeHumorIE from .collegehumor import CollegeHumorIE
from .comedycentral import ComedyCentralIE from .comedycentral import ComedyCentralIE
from .condenast import CondeNastIE from .condenast import CondeNastIE

View File

@ -0,0 +1,37 @@
# coding: utf-8
"""Extractor for canalc2.tv"""
import re
import lxml.html
from .common import InfoExtractor
class Canalc2IE(InfoExtractor):
"""Extractor for canalc2.tv"""
_VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui'
_TEST = {
u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
u'file': u'12163.mp4',
u'md5': u'c00fa80517373764ff5c0b5eb5a58780',
u'info_dict': {
u'title': u'Terrasses du Numérique'
}
}
def _real_extract(self, url):
video_id = re.match(self._VALID_URL, url).group(1)
webpage = self._download_webpage(url, video_id)
file_name = re.search(r"so\.addVariable\('file','(.*?)'\);",
webpage).group(1)
video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
html = lxml.html.fromstring(webpage)
title = html.cssselect('.evenement8')[0].text_content()
return {'id': video_id,
'ext' : 'mp4',
'url' : video_url,
'title' : title
}