]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/tfo.py
[iprima] Improve video id extraction (#26507) (closes #26494)
[youtube-dl.git] / youtube_dl / extractor / tfo.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import json
5
6 from .common import InfoExtractor
7 from ..utils import (
8     HEADRequest,
9     ExtractorError,
10     int_or_none,
11     clean_html,
12 )
13
14
15 class TFOIE(InfoExtractor):
16     _GEO_COUNTRIES = ['CA']
17     _VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)'
18     _TEST = {
19         'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon',
20         'md5': 'cafbe4f47a8dae0ca0159937878100d6',
21         'info_dict': {
22             'id': '7da3d50e495c406b8fc0b997659cc075',
23             'ext': 'mp4',
24             'title': 'Video Game Hackathon',
25             'description': 'md5:558afeba217c6c8d96c60e5421795c07',
26         }
27     }
28
29     def _real_extract(self, url):
30         video_id = self._match_id(url)
31         self._request_webpage(HEADRequest('http://www.tfo.org/'), video_id)
32         infos = self._download_json(
33             'http://www.tfo.org/api/web/video/get_infos', video_id, data=json.dumps({
34                 'product_id': video_id,
35             }).encode(), headers={
36                 'X-tfo-session': self._get_cookies('http://www.tfo.org/')['tfo-session'].value,
37             })
38         if infos.get('success') == 0:
39             if infos.get('code') == 'ErrGeoBlocked':
40                 self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
41             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(infos['msg'])), expected=True)
42         video_data = infos['data']
43
44         return {
45             '_type': 'url_transparent',
46             'id': video_id,
47             'url': 'limelight:media:' + video_data['llid'],
48             'title': video_data['title'],
49             'description': video_data.get('description'),
50             'series': video_data.get('collection'),
51             'season_number': int_or_none(video_data.get('season')),
52             'episode_number': int_or_none(video_data.get('episode')),
53             'duration': int_or_none(video_data.get('duration')),
54             'ie_key': 'LimelightMedia',
55         }