1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-05 10:19:30 +08:00
youtube-dl/youtube_dl/extractor/tf1.py

38 lines
1.4 KiB
Python
Raw Normal View History

2013-06-29 21:18:19 +08:00
# coding: utf-8
2014-03-29 22:05:15 +08:00
from __future__ import unicode_literals
2013-06-29 21:18:19 +08:00
import re
from .common import InfoExtractor
2014-03-29 22:05:15 +08:00
2013-06-29 21:18:19 +08:00
class TF1IE(InfoExtractor):
"""TF1 uses the wat.tv player."""
2014-03-29 22:05:15 +08:00
_VALID_URL = r'http://videos\.tf1\.fr/.*-(?P<id>.*?)\.html'
2013-06-29 21:18:19 +08:00
_TEST = {
2014-03-29 22:05:15 +08:00
'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
'info_dict': {
'id': '10635995',
'ext': 'mp4',
'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle',
'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
},
'params': {
# Sometimes wat serves the whole file with the --test option
'skip_download': True,
},
2013-06-29 21:18:19 +08:00
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-03-29 22:05:15 +08:00
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
embed_url = self._html_search_regex(
r'"(https://www.wat.tv/embedframe/.*?)"', webpage, 'embed url')
embed_page = self._download_webpage(embed_url, video_id,
2014-11-24 04:39:15 +08:00
'Downloading embed player page')
2013-06-29 21:18:19 +08:00
wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')
2014-03-29 22:05:15 +08:00
wat_info = self._download_json(
'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id)
return self.url_result(wat_info['media']['url'], 'Wat')