X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ftoutv.py;h=f1ab91cf2bc3b4b7f29627f19c2c1163a7f9e85c;hb=91effe22a091035bc5abace2fcf562a0db89090f;hp=e59ed266109d16e12e7c64a9ba499ef4c116e449;hpb=a88d461dff67205fcec684426afbcbeb4b0e7cf5;p=youtube-dl

diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py
index e59ed2661..f1ab91cf2 100644
--- a/youtube_dl/extractor/toutv.py
+++ b/youtube_dl/extractor/toutv.py
@@ -1,22 +1,21 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
+import re
+
+from .radiocanada import RadioCanadaIE
 from ..utils import (
+    extract_attributes,
     int_or_none,
-    js_to_json,
+    merge_dicts,
     urlencode_postdata,
-    extract_attributes,
-    smuggle_url,
 )
 
 
-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]+)?)'
-    _access_token = None
-    _claims = None
+    _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+[EC][0-9]+)?)'
 
     _TESTS = [{
         'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17',
@@ -35,44 +34,52 @@ class TouTvIE(InfoExtractor):
     }, {
         '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
-        state = 'http://ici.tou.tv//'
-        webpage = self._download_webpage(state, None, 'Downloading homepage')
-        toutvlogin = self._parse_json(self._search_regex(
-            r'(?s)toutvlogin\s*=\s*({.+?});', webpage, 'toutvlogin'), None, js_to_json)
-        authorize_url = toutvlogin['host'] + '/auth/oauth/v2/authorize'
         login_webpage = self._download_webpage(
-            authorize_url, None, 'Downloading login page', query={
-                'client_id': toutvlogin['clientId'],
-                'redirect_uri': 'https://ici.tou.tv/login/loginCallback',
+            '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': 'media-drmt openid profile email id.write media-validation.read.privileged',
-                'state': state,
+                'scope': 'id.write media-validation.read',
+                'state': '/',
             })
-        login_form = self._search_regex(
-            r'(?s)(<form[^>]+(?:id|name)="Form-login".+?</form>)', login_webpage, 'login form')
-        form_data = self._hidden_inputs(login_form)
+
+        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,
         })
-        post_url = extract_attributes(login_form).get('action') or authorize_url
-        _, urlh = self._download_webpage_handle(
+        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._download_json(
-            'https://services.radio-canada.ca/media/validation/v2/getClaims',
-            None, 'Extracting Claims', query={
-                'token': self._access_token,
-                'access_token': self._access_token,
-            })['claims']
+        self._claims = self._call_api('validation/v2/getClaims')['claims']
 
     def _real_extract(self, url):
         path = self._match_id(url)
@@ -83,19 +90,10 @@ class TouTvIE(InfoExtractor):
             self.report_warning('This video is probably DRM protected.', path)
         video_id = metadata['IdMedia']
         details = metadata['Details']
-        title = details['OriginalTitle']
-        video_url = 'radiocanada:%s:%s' % (metadata.get('AppCode', 'toutv'), video_id)
-        if self._access_token and self._claims:
-            video_url = smuggle_url(video_url, {
-                'access_token': self._access_token,
-                'claims': self._claims,
-            })
 
-        return {
-            '_type': 'url_transparent',
-            'url': video_url,
+        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))