X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ftoutv.py;h=44b022fcaa46ebc872422961a902bc1271cb3f94;hb=HEAD;hp=f1ab91cf2bc3b4b7f29627f19c2c1163a7f9e85c;hpb=8fecc7353df35f6cac305c04a4e203fb2bbb4827;p=youtube-dl diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py index f1ab91cf2..44b022fca 100644 --- a/youtube_dl/extractor/toutv.py +++ b/youtube_dl/extractor/toutv.py @@ -1,14 +1,14 @@ # coding: utf-8 from __future__ import unicode_literals -import re +import json from .radiocanada import RadioCanadaIE +from ..compat import compat_HTTPError from ..utils import ( - extract_attributes, + ExtractorError, int_or_none, merge_dicts, - urlencode_postdata, ) @@ -38,54 +38,42 @@ class TouTvIE(RadioCanadaIE): 'url': 'https://ici.tou.tv/l-age-adulte/S01C501', 'only_matching': True, }] + _CLIENT_KEY = '90505c8d-9c34-4f34-8da1-3a85bdc6d4f4' def _real_initialize(self): email, password = self._get_login_info() if email is None: return - login_webpage = self._download_webpage( - 'https://services.radio-canada.ca/auth/oauth/v2/authorize', - None, 'Downloading login page', query={ - 'client_id': '4dd36440-09d5-4468-8923-b6d91174ad36', - 'redirect_uri': 'https://ici.tou.tv/logincallback', - 'response_type': 'token', - 'scope': 'id.write media-validation.read', - 'state': '/', - }) - - def extract_form_url_and_data(wp, default_form_url, form_spec_re=''): - form, form_elem = re.search( - r'(?s)((]+?%s[^>]*?>).+?)' % form_spec_re, wp).groups() - form_data = self._hidden_inputs(form) - form_url = extract_attributes(form_elem).get('action') or default_form_url - return form_url, form_data - - post_url, form_data = extract_form_url_and_data( - login_webpage, - 'https://services.radio-canada.ca/auth/oauth/v2/authorize/login', - r'(?:id|name)="Form-login"') - form_data.update({ - 'login-email': email, - 'login-password': password, - }) - consent_webpage = self._download_webpage( - post_url, None, 'Logging in', data=urlencode_postdata(form_data)) - post_url, form_data = extract_form_url_and_data( - consent_webpage, - 'https://services.radio-canada.ca/auth/oauth/v2/authorize/consent') - _, urlh = self._download_webpage_handle( - post_url, None, 'Following Redirection', - data=urlencode_postdata(form_data)) - self._access_token = self._search_regex( - r'access_token=([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})', - urlh.geturl(), 'access token') + try: + self._access_token = self._download_json( + 'https://services.radio-canada.ca/toutv/profiling/accounts/login', + None, 'Logging in', data=json.dumps({ + 'ClientId': self._CLIENT_KEY, + 'ClientSecret': '34026772-244b-49b6-8b06-317b30ac9a20', + 'Email': email, + 'Password': password, + 'Scope': 'id.write media-validation.read', + }).encode(), headers={ + 'Authorization': 'client-key ' + self._CLIENT_KEY, + 'Content-Type': 'application/json;charset=utf-8', + })['access_token'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + error = self._parse_json(e.cause.read().decode(), None)['Message'] + raise ExtractorError(error, expected=True) + raise self._claims = self._call_api('validation/v2/getClaims')['claims'] def _real_extract(self, url): path = self._match_id(url) - metadata = self._download_json('http://ici.tou.tv/presentation/%s' % path, path) + metadata = self._download_json( + 'https://services.radio-canada.ca/toutv/presentation/%s' % path, path, query={ + 'client_key': self._CLIENT_KEY, + 'device': 'web', + 'version': 4, + }) # IsDrm does not necessarily mean the video is DRM protected (see - # https://github.com/rg3/youtube-dl/issues/13994). + # https://github.com/ytdl-org/youtube-dl/issues/13994). if metadata.get('IsDrm'): self.report_warning('This video is probably DRM protected.', path) video_id = metadata['IdMedia'] @@ -94,6 +82,12 @@ class TouTvIE(RadioCanadaIE): return merge_dicts({ 'id': video_id, 'title': details.get('OriginalTitle'), + 'description': details.get('Description'), 'thumbnail': details.get('ImageUrl'), 'duration': int_or_none(details.get('LengthInSeconds')), + 'series': metadata.get('ProgramTitle'), + 'season_number': int_or_none(metadata.get('SeasonNumber')), + 'season': metadata.get('SeasonTitle'), + 'episode_number': int_or_none(metadata.get('EpisodeNumber')), + 'episode': metadata.get('EpisodeTitle'), }, self._extract_info(metadata.get('AppCode', 'toutv'), video_id))