]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/toutv.py
Update changelog.
[youtubedl] / youtube_dl / extractor / toutv.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import json
5
6 from .radiocanada import RadioCanadaIE
7 from ..compat import compat_HTTPError
8 from ..utils import (
9 ExtractorError,
10 int_or_none,
11 merge_dicts,
12 )
13
14
15 class TouTvIE(RadioCanadaIE):
16 _NETRC_MACHINE = 'toutv'
17 IE_NAME = 'tou.tv'
18 _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+[EC][0-9]+)?)'
19
20 _TESTS = [{
21 'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17',
22 'info_dict': {
23 'id': '122017',
24 'ext': 'mp4',
25 'title': 'Saison 2015 Épisode 17',
26 'description': 'La photo de famille 2',
27 'upload_date': '20100717',
28 },
29 'params': {
30 # m3u8 download
31 'skip_download': True,
32 },
33 'skip': '404 Not Found',
34 }, {
35 'url': 'http://ici.tou.tv/hackers',
36 'only_matching': True,
37 }, {
38 'url': 'https://ici.tou.tv/l-age-adulte/S01C501',
39 'only_matching': True,
40 }]
41 _CLIENT_KEY = '90505c8d-9c34-4f34-8da1-3a85bdc6d4f4'
42
43 def _real_initialize(self):
44 email, password = self._get_login_info()
45 if email is None:
46 return
47 try:
48 self._access_token = self._download_json(
49 'https://services.radio-canada.ca/toutv/profiling/accounts/login',
50 None, 'Logging in', data=json.dumps({
51 'ClientId': self._CLIENT_KEY,
52 'ClientSecret': '34026772-244b-49b6-8b06-317b30ac9a20',
53 'Email': email,
54 'Password': password,
55 'Scope': 'id.write media-validation.read',
56 }).encode(), headers={
57 'Authorization': 'client-key ' + self._CLIENT_KEY,
58 'Content-Type': 'application/json;charset=utf-8',
59 })['access_token']
60 except ExtractorError as e:
61 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
62 error = self._parse_json(e.cause.read().decode(), None)['Message']
63 raise ExtractorError(error, expected=True)
64 raise
65 self._claims = self._call_api('validation/v2/getClaims')['claims']
66
67 def _real_extract(self, url):
68 path = self._match_id(url)
69 metadata = self._download_json(
70 'https://services.radio-canada.ca/toutv/presentation/%s' % path, path, query={
71 'client_key': self._CLIENT_KEY,
72 'device': 'web',
73 'version': 4,
74 })
75 # IsDrm does not necessarily mean the video is DRM protected (see
76 # https://github.com/ytdl-org/youtube-dl/issues/13994).
77 if metadata.get('IsDrm'):
78 self.report_warning('This video is probably DRM protected.', path)
79 video_id = metadata['IdMedia']
80 details = metadata['Details']
81
82 return merge_dicts({
83 'id': video_id,
84 'title': details.get('OriginalTitle'),
85 'description': details.get('Description'),
86 'thumbnail': details.get('ImageUrl'),
87 'duration': int_or_none(details.get('LengthInSeconds')),
88 'series': metadata.get('ProgramTitle'),
89 'season_number': int_or_none(metadata.get('SeasonNumber')),
90 'season': metadata.get('SeasonTitle'),
91 'episode_number': int_or_none(metadata.get('EpisodeNumber')),
92 'episode': metadata.get('EpisodeTitle'),
93 }, self._extract_info(metadata.get('AppCode', 'toutv'), video_id))