_ Git - youtube-dl/blob - youtube_dl/extractor/toutv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .radiocanada import RadioCanadaIE
   7 from ..utils import (
   8     extract_attributes,
   9     int_or_none,
  10     merge_dicts,
  11     urlencode_postdata,
  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
  42     def _real_initialize(self):
  43         email, password = self._get_login_info()
  44         if email is None:
  45             return
  46         login_webpage = self._download_webpage(
  47             'https://services.radio-canada.ca/auth/oauth/v2/authorize',
  48             None, 'Downloading login page', query={
  49                 'client_id': '4dd36440-09d5-4468-8923-b6d91174ad36',
  50                 'redirect_uri': 'https://ici.tou.tv/logincallback',
  51                 'response_type': 'token',
  52                 'scope': 'id.write media-validation.read',
  53                 'state': '/',
  54             })
  55
  56         def extract_form_url_and_data(wp, default_form_url, form_spec_re=''):
  57             form, form_elem = re.search(
  58                 r'(?s)((<form[^>]+?%s[^>]*?>).+?</form>)' % form_spec_re, wp).groups()
  59             form_data = self._hidden_inputs(form)
  60             form_url = extract_attributes(form_elem).get('action') or default_form_url
  61             return form_url, form_data
  62
  63         post_url, form_data = extract_form_url_and_data(
  64             login_webpage,
  65             'https://services.radio-canada.ca/auth/oauth/v2/authorize/login',
  66             r'(?:id|name)="Form-login"')
  67         form_data.update({
  68             'login-email': email,
  69             'login-password': password,
  70         })
  71         consent_webpage = self._download_webpage(
  72             post_url, None, 'Logging in', data=urlencode_postdata(form_data))
  73         post_url, form_data = extract_form_url_and_data(
  74             consent_webpage,
  75             'https://services.radio-canada.ca/auth/oauth/v2/authorize/consent')
  76         _, urlh = self._download_webpage_handle(
  77             post_url, None, 'Following Redirection',
  78             data=urlencode_postdata(form_data))
  79         self._access_token = self._search_regex(
  80             r'access_token=([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
  81             urlh.geturl(), 'access token')
  82         self._claims = self._call_api('validation/v2/getClaims')['claims']
  83
  84     def _real_extract(self, url):
  85         path = self._match_id(url)
  86         metadata = self._download_json('http://ici.tou.tv/presentation/%s' % path, path)
  87         # IsDrm does not necessarily mean the video is DRM protected (see
  88         # https://github.com/rg3/youtube-dl/issues/13994).
  89         if metadata.get('IsDrm'):
  90             self.report_warning('This video is probably DRM protected.', path)
  91         video_id = metadata['IdMedia']
  92         details = metadata['Details']
  93
  94         return merge_dicts({
  95             'id': video_id,
  96             'title': details.get('OriginalTitle'),
  97             'thumbnail': details.get('ImageUrl'),
  98             'duration': int_or_none(details.get('LengthInSeconds')),
  99         }, self._extract_info(metadata.get('AppCode', 'toutv'), video_id))