1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-25 11:41:52 +00:00

Clean up InaIE (Closes #823)

This commit is contained in:
Philipp Hagemeister 2013-05-05 20:57:19 +02:00
parent 7f5bd09baf
commit dfb9323cf9

View file

@ -4128,33 +4128,25 @@ class RedTubeIE(InfoExtractor):
class InaIE(InfoExtractor):
"""Information Extractor for Ina.fr"""
_VALID_URL = r'(?:http://)?(?:www.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
IE_NAME = u'Ina'
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('id')
self.to_screen(u'video id : %s' % video_id)
mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id
self.to_screen(u'mrss url : %s' % mrss_url)
video_extension = 'mp4'
webpage = self._download_webpage(mrss_url, video_id)
self.report_extraction(video_id)
reg1=r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)'
mobj = re.search(reg1,webpage)
mobj = re.search(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract media URL')
video_url = mobj.group(1)
reg2=r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>'
mobj = re.search(reg2,webpage)
mobj = re.search(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract title')
video_title = mobj.group(1)
self.to_screen(u'Titre de la video : %s' % video_title)
return [{
'id': video_id,
'url': video_url,
@ -4218,7 +4210,7 @@ def gen_extractors():
TumblrIE(),
BandcampIE(),
RedTubeIE(),
InaIE,
InaIE(),
GenericIE()
]