New upstream version 2019.06.08

[youtubedl] / youtube_dl / extractor / toutv.py

diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py
index 54c2d0aa6c0d234f9f747550ab841c409bfbc079..00f58a087df6741d34e282eac16052c6ac83450d 100644 (file)
--- a/youtube_dl/extractor/toutv.py
+++ b/youtube_dl/extractor/toutv.py
@@ -1,15 +1,23 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
-from ..utils import int_or_none
+import json
 
+from .radiocanada import RadioCanadaIE
+from ..compat import compat_HTTPError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    merge_dicts,
+)
 
-class TouTvIE(InfoExtractor):
+
+class TouTvIE(RadioCanadaIE):
+    _NETRC_MACHINE = 'toutv'
     IE_NAME = 'tou.tv'
-    _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+/S[0-9]+E[0-9]+)'
+    _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+[EC][0-9]+)?)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17',
         'info_dict': {
             'id': '122017',
@@ -22,20 +30,64 @@ class TouTvIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         },
-    }
+        'skip': '404 Not Found',
+    }, {
+        'url': 'http://ici.tou.tv/hackers',
+        'only_matching': True,
+    }, {
+        'url': 'https://ici.tou.tv/l-age-adulte/S01C501',
+        'only_matching': True,
+    }]
+    _CLIENT_KEY = '4dd36440-09d5-4468-8923-b6d91174ad36'
+
+    def _real_initialize(self):
+        email, password = self._get_login_info()
+        if email is None:
+            return
+        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/ytdl-org/youtube-dl/issues/13994).
+        if metadata.get('IsDrm'):
+            self.report_warning('This video is probably DRM protected.', path)
         video_id = metadata['IdMedia']
         details = metadata['Details']
-        title = details['OriginalTitle']
 
-        return {
-            '_type': 'url_transparent',
-            'url': 'radiocanada:%s:%s' % (metadata.get('AppCode', 'toutv'), video_id),
+        return merge_dicts({
             'id': video_id,
-            'title': title,
+            '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))