[youtube] Add more invidious instances

[youtube-dl] / youtube_dl / extractor / toutv.py

diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py
index 54c2d0aa6c0d234f9f747550ab841c409bfbc079..f1ab91cf2bc3b4b7f29627f19c2c1163a7f9e85c 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 re
 
+from .radiocanada import RadioCanadaIE
+from ..utils import (
+    extract_attributes,
+    int_or_none,
+    merge_dicts,
+    urlencode_postdata,
+)
 
-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 +30,70 @@ 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,
+    }]
+
+    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)((<form[^>]+?%s[^>]*?>).+?</form>)' % 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')
+        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)
+        # IsDrm does not necessarily mean the video is DRM protected (see
+        # https://github.com/rg3/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'),
             'thumbnail': details.get('ImageUrl'),
             'duration': int_or_none(details.get('LengthInSeconds')),
-        }
+        }, self._extract_info(metadata.get('AppCode', 'toutv'), video_id))