Archives/yt-dlp
2
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-15 18:12:58 +00:00
Code Issues Projects Releases Wiki Activity

[Peertube] Add channel extractor (#1023)

Browse Source 
Authored by: u-spec-png
This commit is contained in:
u-spec-png 2021-09-19 17:47:41 +00:00 committed by GitHub
parent 3cd786dbd7
commit cb2ec90e91
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 58 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

85
yt_dlp/extractor/peertube.py
View File

@ -1297,13 +1297,15 @@ def channel_data(field, type_):
class PeerTubePlaylistIE(InfoExtractor): class PeerTubePlaylistIE(InfoExtractor):
IE_NAME = 'PeerTube:Playlist' IE_NAME = 'PeerTube:Playlist'
_TYPES = {
'a': 'accounts',
'c': 'video-channels',
'w/p': 'video-playlists',
}
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
(?: https?://(?P<host>%s)/(?P<type>(?:%s))/
https?://(?P<host>%s)/w/p/ (?P<id>[^/]+)
) ''' % (PeerTubeIE._INSTANCES_RE, '|'.join(_TYPES.keys()))
(?P<id>%s)
''' % (PeerTubeIE._INSTANCES_RE, PeerTubeIE._UUID_RE)
_API_BASE = 'https://%s/api/v1/video-playlists/%s%s'
_TESTS = [{ _TESTS = [{
'url': 'https://peertube.tux.ovh/w/p/3af94cba-95e8-4b74-b37a-807ab6d82526', 'url': 'https://peertube.tux.ovh/w/p/3af94cba-95e8-4b74-b37a-807ab6d82526',
'info_dict': { 'info_dict': {
@ -1331,41 +1333,70 @@ class PeerTubePlaylistIE(InfoExtractor):
'timestamp': 1599676222, 'timestamp': 1599676222,
}, },
'playlist_mincount': 9, 'playlist_mincount': 9,
}, {
'url': 'https://peertube2.cpy.re/a/chocobozzz/videos',
'info_dict': {
'id': 'chocobozzz',
'timestamp': 1553874564,
'title': 'chocobozzz',
},
'playlist_mincount': 2,
}, {
'url': 'https://framatube.org/c/bf54d359-cfad-4935-9d45-9d6be93f63e8/videos',
'info_dict': {
'id': 'bf54d359-cfad-4935-9d45-9d6be93f63e8',
'timestamp': 1519917377,
'title': 'Les vidéos de Framasoft',
},
'playlist_mincount': 345,
}, {
'url': 'https://peertube2.cpy.re/c/blender_open_movies@video.blender.org/videos',
'info_dict': {
'id': 'blender_open_movies@video.blender.org',
'timestamp': 1542287810,
'title': 'Official Blender Open Movies',
},
'playlist_mincount': 11,
}] }]
_API_BASE = 'https://%s/api/v1/%s/%s%s'
_PAGE_SIZE = 30 _PAGE_SIZE = 30
def _call_api(self, host, uuid, path, note=None, errnote=None, fatal=True): def call_api(self, host, name, path, base, **kwargs):
return self._download_json( return self._download_json(
self._API_BASE % (host, uuid, path), uuid, self._API_BASE % (host, base, name, path), name, **kwargs)
note=note, errnote=errnote, fatal=fatal)
def _fetch_page(self, host, uuid, page): def fetch_page(self, host, id, type, page):
page += 1 page += 1
video_data = self._call_api( video_data = self.call_api(
host, uuid, f'/videos?sort=-createdAt&start={self._PAGE_SIZE * (page - 1)}&count={self._PAGE_SIZE}', host, id,
note=f'Downloading page {page}').get('data', []) f'/videos?sort=-createdAt&start={self._PAGE_SIZE * (page - 1)}&count={self._PAGE_SIZE}&nsfw=both',
type, note=f'Downloading page {page}').get('data', [])
for video in video_data: for video in video_data:
shortUUID = try_get(video, lambda x: x['video']['shortUUID']) shortUUID = video.get('shortUUID') or try_get(video, lambda x: x['video']['shortUUID'])
video_title = try_get(video, lambda x: x['video']['name']) video_title = video.get('name') or try_get(video, lambda x: x['video']['name'])
yield self.url_result( yield self.url_result(
f'https://{host}/w/{shortUUID}', PeerTubeIE.ie_key(), f'https://{host}/w/{shortUUID}', PeerTubeIE.ie_key(),
video_id=shortUUID, video_title=video_title) video_id=shortUUID, video_title=video_title)
def _real_extract(self, url): def _extract_playlist(self, host, type, id):
host, playlist_id = self._match_valid_url(url).group('host', 'id') info = self.call_api(host, id, '', type, note='Downloading playlist information', fatal=False)
playlist_info = self._call_api(host, playlist_id, '', note='Downloading playlist information', fatal=False)
playlist_title = playlist_info.get('displayName') playlist_title = info.get('displayName')
playlist_description = playlist_info.get('description') playlist_description = info.get('description')
playlist_timestamp = unified_timestamp(playlist_info.get('createdAt')) playlist_timestamp = unified_timestamp(info.get('createdAt'))
channel = try_get(playlist_info, lambda x: x['ownerAccount']['name']) channel = try_get(info, lambda x: x['ownerAccount']['name']) or info.get('displayName')
channel_id = try_get(playlist_info, lambda x: x['ownerAccount']['id']) channel_id = try_get(info, lambda x: x['ownerAccount']['id']) or info.get('id')
thumbnail = playlist_info.get('thumbnailPath') thumbnail = info.get('thumbnailPath')
thumbnail = f'https://{host}{thumbnail}' thumbnail = f'https://{host}{thumbnail}' if thumbnail else None
entries = OnDemandPagedList(functools.partial( entries = OnDemandPagedList(functools.partial(
self._fetch_page, host, playlist_id), self._PAGE_SIZE) self.fetch_page, host, id, type), self._PAGE_SIZE)
return self.playlist_result( return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description, entries, id, playlist_title, playlist_description,
timestamp=playlist_timestamp, channel=channel, channel_id=channel_id, thumbnail=thumbnail) timestamp=playlist_timestamp, channel=channel, channel_id=channel_id, thumbnail=thumbnail)
def _real_extract(self, url):
type, host, id = self._match_valid_url(url).group('type', 'host', 'id')
type = self._TYPES[type]
return self._extract_playlist(host, type, id)