mirror/yt-dlc
1
0
Fork 0
mirror of https://github.com/blackjack4494/yt-dlc.git synced 2025-01-03 05:36:07 +00:00
Code Issues Releases Wiki Activity

[youtube] stop loading pages if videos are already seen

Browse source
This commit is contained in:
insaneracist 2020-11-10 14:38:13 -08:00
parent 965a404be3
commit 29e9c94948
1 changed files with 11 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
youtube_dlc/extractor/youtube.py
View file

@ -2894,6 +2894,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
yt_initial = self._get_yt_initial_data('', page) yt_initial = self._get_yt_initial_data('', page)
if yt_initial: if yt_initial:
playlist_items = try_get(yt_initial, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'][0]['tabRenderer']['content']['sectionListRenderer']['contents'][0]['itemSectionRenderer']['contents'][0]['playlistVideoListRenderer']['contents'], list) playlist_items = try_get(yt_initial, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'][0]['tabRenderer']['content']['sectionListRenderer']['contents'][0]['itemSectionRenderer']['contents'][0]['playlistVideoListRenderer']['contents'], list)
video_ids = []
entries = [] entries = []
playlist_page = 1 playlist_page = 1
api_key = self._search_regex( api_key = self._search_regex(
@ -2908,6 +2909,10 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
item_video = try_get(item, lambda x: x['playlistVideoRenderer'], dict) item_video = try_get(item, lambda x: x['playlistVideoRenderer'], dict)
if item_video: if item_video:
video_id = try_get(item_video, lambda x: x['videoId'], compat_str) video_id = try_get(item_video, lambda x: x['videoId'], compat_str)
if video_id in video_ids:
continue
else:
video_ids.append(video_id)
entry = { entry = {
'_type': 'url', '_type': 'url',
'duration': int_or_none(try_get(item_video, lambda x: x['lengthSeconds'], compat_str)), 'duration': int_or_none(try_get(item_video, lambda x: x['lengthSeconds'], compat_str)),
@ -2927,7 +2932,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
'context': { 'context': {
'client': { 'client': {
'clientName': 'WEB', 'clientName': 'WEB',
'clientVersion': api_client_version, 'clientVersion': api_client_version
} }
}, },
'continuation': continuation_token 'continuation': continuation_token
@ -2941,7 +2946,11 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
video_id=playlist_id) video_id=playlist_id)
playlist_items_new = try_get(response, lambda x: x['onResponseReceivedActions'][0]['appendContinuationItemsAction']['continuationItems'], list) playlist_items_new = try_get(response, lambda x: x['onResponseReceivedActions'][0]['appendContinuationItemsAction']['continuationItems'], list)
if playlist_items_new: if playlist_items_new:
playlist_items.extend(playlist_items_new) # load more pages until we get a page of all videos already in the playlist (some playlists loop)
video_ids_new = [try_get(i, lambda x: x['playlistVideoRenderer']['videoId'], compat_str) for i in playlist_items_new]
video_ids_new = [i for i in video_ids_new if i and i not in video_ids]
if video_ids_new:
playlist_items.extend(playlist_items_new)
playlist_title = try_get(yt_initial, lambda x: x['microformat']['microformatDataRenderer']['title'], compat_str) playlist_title = try_get(yt_initial, lambda x: x['microformat']['microformatDataRenderer']['title'], compat_str)
playlist_description = try_get(yt_initial, lambda x: x['microformat']['microformatDataRenderer']['description'], compat_str) playlist_description = try_get(yt_initial, lambda x: x['microformat']['microformatDataRenderer']['description'], compat_str)