From c7121fa7b804d2b9e35dec05f8861e4ebba8afd2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 26 Aug 2017 15:38:38 +0700 Subject: [PATCH] [youtube] Fix controversy videos extraction (closes #14027, closes #14029) --- youtube_dl/extractor/youtube.py | 36 ++++++++++++++++++++++++++++----- 1 file changed, 31 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 2e71795e7..3d0f5a5c9 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1003,6 +1003,27 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'Skipping DASH manifest', ], }, + { + # The following content has been identified by the YouTube community + # as inappropriate or offensive to some audiences. + 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI', + 'info_dict': { + 'id': '6SJNVb0GnPI', + 'ext': 'mp4', + 'title': 'Race Differences in Intelligence', + 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1', + 'duration': 965, + 'upload_date': '20140124', + 'uploader': 'New Century Foundation', + 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', + 'license': 'Standard YouTube License', + 'view_count': int, + }, + 'params': { + 'skip_download': True, + }, + }, { # itag 212 'url': '1t24XAntNCY', @@ -1437,9 +1458,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if dash_mpd and dash_mpd[0] not in dash_mpds: dash_mpds.append(dash_mpd[0]) + is_live = None + view_count = None + + def extract_view_count(v_info): + return int_or_none(try_get(v_info, lambda x: x['view_count'][0])) + # Get video info embed_webpage = None - is_live = 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} @@ -1509,6 +1535,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): continue get_video_info = compat_parse_qs(video_info_webpage) add_dash_mpd(get_video_info) + if view_count is None: + view_count = extract_view_count(get_video_info) if not video_info: video_info = get_video_info if 'token' in get_video_info: @@ -1592,10 +1620,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return self.playlist_result(entries, video_id, video_title, video_description) self.to_screen('Downloading just video %s because of --no-playlist' % video_id) - if 'view_count' in video_info: - view_count = int(video_info['view_count'][0]) - else: - view_count = None + if view_count is None: + view_count = extract_view_count(get_video_info) # Check for "rental" videos if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: