[tf1] add support for TFOU

This commit is contained in:
t0mm0 2015-01-04 00:05:31 +00:00
parent 19b05d886e
commit 382e05fa56
1 changed files with 16 additions and 5 deletions

View File

@ -8,8 +8,8 @@ from .common import InfoExtractor
class TF1IE(InfoExtractor): class TF1IE(InfoExtractor):
"""TF1 uses the wat.tv player.""" """TF1 uses the wat.tv player."""
_VALID_URL = r'http://videos\.tf1\.fr/.*-(?P<id>.*?)\.html' _VALID_URL = r'http://(?:videos\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html'
_TEST = { _TESTS = {
'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', 'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
'info_dict': { 'info_dict': {
'id': '10635995', 'id': '10635995',
@ -21,14 +21,25 @@ class TF1IE(InfoExtractor):
# Sometimes wat serves the whole file with the --test option # Sometimes wat serves the whole file with the --test option
'skip_download': True, 'skip_download': True,
}, },
}, {
'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
'info_dict': {
'id': '7085291',
'ext': 'mp4',
'title': 'Le grand Mystérioso - Chuggington',
'description': 'Emery rêve qu\'un article lui soit consacré dans le journal.',
},
'params': {
# Sometimes wat serves the whole file with the --test option
'skip_download': True,
},
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
embed_url = self._html_search_regex( embed_url = self._html_search_regex(
r'"(https://www.wat.tv/embedframe/.*?)"', webpage, 'embed url') r'["\'](http(?:s)?://www.wat.tv/embedframe/.*?)["\']', webpage, 'embed url')
embed_page = self._download_webpage(embed_url, video_id, embed_page = self._download_webpage(embed_url, video_id,
'Downloading embed player page') 'Downloading embed player page')
wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id') wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')