From 6449cd807e07e04eb88b1a34063e00677de0713e Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 30 Jan 2015 04:43:50 +0100 Subject: [PATCH] [youtube] Fall back to embed webpage when content is blocked on main (Fixes #4717) --- youtube_dl/extractor/youtube.py | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index bc5fa0b39..a9e444351 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -28,6 +28,7 @@ get_element_by_attribute, get_element_by_id, int_or_none, + js_to_json, OnDemandPagedList, orderedSet, unescapeHTML, @@ -809,6 +810,7 @@ def _real_extract(self, url): player_url = None # Get video info + embed_webpage = None if re.search(r'player-age-gate-content">', video_webpage) is not None: age_gate = True # We simulate the access to the video from www.youtube.com/v/{video_id} @@ -1016,10 +1018,21 @@ def _map_to_format_list(urlmap): url += '&signature=' + url_data['sig'][0] elif 's' in url_data: encrypted_sig = url_data['s'][0] + ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' jsplayer_url_json = self._search_regex( - r'"assets":.+?"js":\s*("[^"]+")', - embed_webpage if age_gate else video_webpage, 'JS player URL') + ASSETS_RE, + embed_webpage if age_gate else video_webpage, + 'JS player URL (1)', default=None) + if not jsplayer_url_json and not age_gate: + # We need the embed website after all + if embed_webpage is None: + embed_url = proto + '://www.youtube.com/embed/%s' % video_id + embed_webpage = self._download_webpage( + embed_url, video_id, 'Downloading embed webpage') + jsplayer_url_json = self._search_regex( + ASSETS_RE, embed_webpage, 'JS player URL') + player_url = json.loads(jsplayer_url_json) if player_url is None: player_url_json = self._search_regex(