]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/tf1.py
[worldstarhiphop] Small cleanup
[yt-dlp.git] / youtube_dl / extractor / tf1.py
CommitLineData
705f6f35
JMF
1# coding: utf-8
2
3import json
4import re
5
6from .common import InfoExtractor
7
8class TF1IE(InfoExtractor):
0725f584 9 """TF1 uses the wat.tv player."""
705f6f35
JMF
10 _VALID_URL = r'http://videos.tf1.fr/.*-(.*?).html'
11 _TEST = {
12 u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
8244288d 13 u'file': u'10635995.mp4',
0725f584 14 u'md5': u'2e378cc28b9957607d5e88f274e637d8',
705f6f35 15 u'info_dict': {
8244288d
JMF
16 u'title': u'Citroën Grand C4 Picasso 2013 : présentation officielle',
17 u'description': u'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
705f6f35
JMF
18 }
19 }
20
21 def _real_extract(self, url):
22 mobj = re.match(self._VALID_URL, url)
23 id = mobj.group(1)
24 webpage = self._download_webpage(url, id)
25 embed_url = self._html_search_regex(r'"(https://www.wat.tv/embedframe/.*?)"',
26 webpage, 'embed url')
27 embed_page = self._download_webpage(embed_url, id, u'Downloading embed player page')
28 wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')
29 wat_info = self._download_webpage('http://www.wat.tv/interface/contentv3/%s' % wat_id, id, u'Downloading Wat info')
30 wat_info = json.loads(wat_info)['media']
31 wat_url = wat_info['url']
32 return self.url_result(wat_url, 'Wat')