[youtube] Skip unsupported adaptive stream type (#18804)

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

diff --git a/youtube_dl/extractor/canvas.py b/youtube_dl/extractor/canvas.py
index c7e9b8ff9c4970724aa2a2496a29db892df76ed2..174fd9e2b4b00b384b1737a1df058050e4603de9 100644 (file)
--- a/youtube_dl/extractor/canvas.py
+++ b/youtube_dl/extractor/canvas.py
@@ -5,14 +5,13 @@ import json
 
 from .common import InfoExtractor
 from .gigya import GigyaBaseIE
-
-
 from ..compat import compat_HTTPError
 from ..utils import (
     ExtractorError,
     strip_or_none,
     float_or_none,
     int_or_none,
+    merge_dicts,
     parse_iso8601,
 )
 
@@ -192,7 +191,7 @@ class VrtNUIE(GigyaBaseIE):
             'season_number': 1,
             'episode_number': 1,
         },
-        # 'skip': 'This video is only available for registered users'
+        'skip': 'This video is only available for registered users'
     }]
     _NETRC_MACHINE = 'vrtnu'
     _APIKEY = '3_0Z2HujMtiWq_pkAjgnS2Md2E11a1AwZjYiBETtwNE-EoEHDINgtnvcAOpNgmrVGy'
@@ -204,7 +203,7 @@ class VrtNUIE(GigyaBaseIE):
     def _login(self):
         username, password = self._get_login_info()
         if username is None:
-            self.raise_login_required()
+            return
 
         auth_data = {
             'APIKey': self._APIKEY,
@@ -248,11 +247,15 @@ class VrtNUIE(GigyaBaseIE):
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, display_id)
+        webpage, urlh = self._download_webpage_handle(url, display_id)
+
+        info = self._search_json_ld(webpage, display_id, default={})
 
-        title = self._html_search_regex(
+        # title is optional here since it may be extracted by extractor
+        # that is delegated from here
+        title = strip_or_none(self._html_search_regex(
             r'(?ms)<h1 class="content__heading">(.+?)</h1>',
-            webpage, 'title').strip()
+            webpage, 'title', default=None))
 
         description = self._html_search_regex(
             r'(?ms)<div class="content__description">(.+?)</div>',
@@ -278,20 +281,26 @@ class VrtNUIE(GigyaBaseIE):
             webpage, 'release_date', default=None))
 
         # If there's a ? or a # in the URL, remove them and everything after
-        clean_url = url.split('?')[0].split('#')[0].strip('/')
+        clean_url = urlh.geturl().split('?')[0].split('#')[0].strip('/')
         securevideo_url = clean_url + '.mssecurevideo.json'
 
-        json = self._download_json(securevideo_url, display_id)
+        try:
+            video = self._download_json(securevideo_url, display_id)
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                self.raise_login_required()
+            raise
+
         # We are dealing with a '../<show>.relevant' URL
-        redirect_url = json.get('url')
+        redirect_url = video.get('url')
         if redirect_url:
-            return self.url_result('https:' + redirect_url)
-        else:
-            # There is only one entry, but with an unknown key, so just get
-            # the first one
-            video_id = list(json.values())[0].get('videoid')
+            return self.url_result(self._proto_relative_url(redirect_url, 'https:'))
 
-        return {
+        # There is only one entry, but with an unknown key, so just get
+        # the first one
+        video_id = list(video.values())[0].get('videoid')
+
+        return merge_dicts(info, {
             '_type': 'url_transparent',
             'url': 'https://mediazone.vrt.be/api/v1/vrtvideo/assets/%s' % video_id,
             'ie_key': CanvasIE.ie_key(),
@@ -303,4 +312,4 @@ class VrtNUIE(GigyaBaseIE):
             'season_number': season_number,
             'episode_number': episode_number,
             'release_date': release_date,
-        }
+        })