Merge pull request #57 from insaneracist/youtube-mix-fix

[youtube] fix: extract mix playlist ids from ytInitialData (#33)
This commit is contained in:
Tom-Oliver Heidel 2020-11-03 10:33:58 +01:00 committed by GitHub
commit 7166f47b18
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -279,6 +279,15 @@ def _download_webpage_handle(self, *args, **kwargs):
return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle( return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle(
*args, **compat_kwargs(kwargs)) *args, **compat_kwargs(kwargs))
def _get_yt_initial_data(self, video_id, webpage):
config = self._search_regex(
(r'window\["ytInitialData"\]\s*=\s*(.*?)(?<=});',
r'var\s+ytInitialData\s*=\s*(.*?)(?<=});'),
webpage, 'ytInitialData', default=None)
if config:
return self._parse_json(
uppercase_escape(config), video_id, fatal=False)
def _real_initialize(self): def _real_initialize(self):
if self._downloader is None: if self._downloader is None:
return return
@ -1398,15 +1407,6 @@ def _get_ytplayer_config(self, video_id, webpage):
return self._parse_json( return self._parse_json(
uppercase_escape(config), video_id, fatal=False) uppercase_escape(config), video_id, fatal=False)
def _get_yt_initial_data(self, video_id, webpage):
config = self._search_regex(
(r'window\["ytInitialData"\]\s*=\s*(.*?)(?<=});',
r'var\s+ytInitialData\s*=\s*(.*?)(?<=});'),
webpage, 'ytInitialData', default=None)
if config:
return self._parse_json(
uppercase_escape(config), video_id, fatal=False)
def _get_music_metadata_from_yt_initial(self, yt_initial): def _get_music_metadata_from_yt_initial(self, yt_initial):
music_metadata = [] music_metadata = []
key_map = { key_map = {
@ -2828,6 +2828,16 @@ def extract_videos_from_page(self, page):
return zip(ids_in_page, titles_in_page) return zip(ids_in_page, titles_in_page)
def _extract_mix_ids_from_yt_initial(self, yt_initial):
ids = []
playlist_contents = try_get(yt_initial, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist']['contents'], list)
if playlist_contents:
for item in playlist_contents:
videoId = try_get(item, lambda x: x['playlistPanelVideoRenderer']['videoId'], compat_str)
if videoId:
ids.append(videoId)
return ids
def _extract_mix(self, playlist_id): def _extract_mix(self, playlist_id):
# The mixes are generated from a single video # The mixes are generated from a single video
# the id of the playlist is just 'RD' + video_id # the id of the playlist is just 'RD' + video_id
@ -2841,6 +2851,13 @@ def _extract_mix(self, playlist_id):
r'''(?xs)data-video-username=".*?".*? r'''(?xs)data-video-username=".*?".*?
href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id), href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id),
webpage)) webpage))
# if no ids in html of page, try using embedded json
if (len(new_ids) == 0):
yt_initial = self._get_yt_initial_data(playlist_id, webpage)
if yt_initial:
new_ids = self._extract_mix_ids_from_yt_initial(yt_initial)
# Fetch new pages until all the videos are repeated, it seems that # Fetch new pages until all the videos are repeated, it seems that
# there are always 51 unique videos. # there are always 51 unique videos.
new_ids = [_id for _id in new_ids if _id not in ids] new_ids = [_id for _id in new_ids if _id not in ids]