1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-10-31 22:55:26 +00:00

[lbry] add support for short and embed URLs and fix channel metadata extraction

This commit is contained in:
Remita Amine 2020-12-08 10:52:52 +01:00
parent 07333d0062
commit e7eff914cd

View file

@ -11,12 +11,14 @@ from ..utils import (
int_or_none, int_or_none,
mimetype2ext, mimetype2ext,
try_get, try_get,
urljoin,
) )
class LBRYIE(InfoExtractor): class LBRYIE(InfoExtractor):
IE_NAME = 'lbry.tv' IE_NAME = 'lbry.tv'
_VALID_URL = r'https?://(?:www\.)?(?:lbry\.tv|odysee\.com)/(?P<id>@[^:]+:[0-9a-z]+/[^:]+:[0-9a-z])' _CLAIM_ID_REGEX = r'[0-9a-f]{1,40}'
_VALID_URL = r'https?://(?:www\.)?(?:lbry\.tv|odysee\.com)/(?P<id>@[^:]+:{0}/[^:]+:{0}|[^:]+:{0}|\$/embed/[^/]+/{0})'.format(_CLAIM_ID_REGEX)
_TESTS = [{ _TESTS = [{
# Video # Video
'url': 'https://lbry.tv/@Mantega:1/First-day-LBRY:1', 'url': 'https://lbry.tv/@Mantega:1/First-day-LBRY:1',
@ -40,6 +42,11 @@ class LBRYIE(InfoExtractor):
'description': 'md5:661ac4f1db09f31728931d7b88807a61', 'description': 'md5:661ac4f1db09f31728931d7b88807a61',
'timestamp': 1591312601, 'timestamp': 1591312601,
'upload_date': '20200604', 'upload_date': '20200604',
'tags': list,
'duration': 2570,
'channel': 'The LBRY Foundation',
'channel_id': '0ed629d2b9c601300cacf7eabe9da0be79010212',
'channel_url': 'https://lbry.tv/@LBRYFoundation:0ed629d2b9c601300cacf7eabe9da0be79010212',
} }
}, { }, {
'url': 'https://odysee.com/@BrodieRobertson:5/apple-is-tracking-everything-you-do-on:e', 'url': 'https://odysee.com/@BrodieRobertson:5/apple-is-tracking-everything-you-do-on:e',
@ -47,6 +54,15 @@ class LBRYIE(InfoExtractor):
}, { }, {
'url': "https://odysee.com/@ScammerRevolts:b0/I-SYSKEY'D-THE-SAME-SCAMMERS-3-TIMES!:b", 'url': "https://odysee.com/@ScammerRevolts:b0/I-SYSKEY'D-THE-SAME-SCAMMERS-3-TIMES!:b",
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://lbry.tv/Episode-1:e7d93d772bd87e2b62d5ab993c1c3ced86ebb396',
'only_matching': True,
}, {
'url': 'https://lbry.tv/$/embed/Episode-1/e7d93d772bd87e2b62d5ab993c1c3ced86ebb396',
'only_matching': True,
}, {
'url': 'https://lbry.tv/Episode-1:e7',
'only_matching': True,
}] }]
def _call_api_proxy(self, method, display_id, params): def _call_api_proxy(self, method, display_id, params):
@ -59,22 +75,33 @@ class LBRYIE(InfoExtractor):
}).encode())['result'] }).encode())['result']
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url).replace(':', '#') display_id = self._match_id(url)
if display_id.startswith('$/embed/'):
display_id = display_id[8:].replace('/', ':')
else:
display_id = display_id.replace(':', '#')
uri = 'lbry://' + display_id uri = 'lbry://' + display_id
result = self._call_api_proxy( result = self._call_api_proxy(
'resolve', display_id, {'urls': [uri]})[uri] 'resolve', display_id, {'urls': [uri]})[uri]
result_value = result['value'] result_value = result['value']
if result_value.get('stream_type') not in ('video', 'audio'): if result_value.get('stream_type') not in ('video', 'audio'):
raise ExtractorError('Unsupported URL', expected=True) raise ExtractorError('Unsupported URL', expected=True)
claim_id = result['claim_id']
title = result_value['title']
streaming_url = self._call_api_proxy( streaming_url = self._call_api_proxy(
'get', display_id, {'uri': uri})['streaming_url'] 'get', claim_id, {'uri': uri})['streaming_url']
source = result_value.get('source') or {} source = result_value.get('source') or {}
media = result_value.get('video') or result_value.get('audio') or {} media = result_value.get('video') or result_value.get('audio') or {}
signing_channel = result_value.get('signing_channel') or {} signing_channel = result.get('signing_channel') or {}
channel_name = signing_channel.get('name')
channel_claim_id = signing_channel.get('claim_id')
channel_url = None
if channel_name and channel_claim_id:
channel_url = urljoin(url, '/%s:%s' % (channel_name, channel_claim_id))
return { return {
'id': result['claim_id'], 'id': claim_id,
'title': result_value['title'], 'title': title,
'thumbnail': try_get(result_value, lambda x: x['thumbnail']['url'], compat_str), 'thumbnail': try_get(result_value, lambda x: x['thumbnail']['url'], compat_str),
'description': result_value.get('description'), 'description': result_value.get('description'),
'license': result_value.get('license'), 'license': result_value.get('license'),
@ -83,8 +110,9 @@ class LBRYIE(InfoExtractor):
'width': int_or_none(media.get('width')), 'width': int_or_none(media.get('width')),
'height': int_or_none(media.get('height')), 'height': int_or_none(media.get('height')),
'duration': int_or_none(media.get('duration')), 'duration': int_or_none(media.get('duration')),
'channel': signing_channel.get('name'), 'channel': try_get(signing_channel, lambda x: x['value']['title']),
'channel_id': signing_channel.get('claim_id'), 'channel_id': channel_claim_id,
'channel_url': channel_url,
'ext': determine_ext(source.get('name')) or mimetype2ext(source.get('media_type')), 'ext': determine_ext(source.get('name')) or mimetype2ext(source.get('media_type')),
'filesize': int_or_none(source.get('size')), 'filesize': int_or_none(source.get('size')),
'url': streaming_url, 'url': streaming_url,