0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-04 04:07:26 +00:00
yt-dlp/yt_dlp/extractor/gaia.py

121 lines
4.3 KiB
Python
Raw Normal View History

import urllib.parse
2019-01-09 13:23:26 +00:00
from .common import InfoExtractor
from ..utils import (
ExtractorError,
2019-01-09 13:23:26 +00:00
int_or_none,
str_or_none,
strip_or_none,
try_get,
urlencode_postdata,
2019-01-09 13:23:26 +00:00
)
class GaiaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gaia\.com/video/(?P<id>[^/?]+).*?\bfullplayer=(?P<type>feature|preview)'
_TESTS = [{
'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=feature',
'info_dict': {
'id': '89356',
'ext': 'mp4',
'title': 'Connecting with Universal Consciousness',
'description': 'md5:844e209ad31b7d31345f5ed689e3df6f',
'upload_date': '20151116',
'timestamp': 1447707266,
'duration': 936,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=preview',
'info_dict': {
'id': '89351',
'ext': 'mp4',
'title': 'Connecting with Universal Consciousness',
'description': 'md5:844e209ad31b7d31345f5ed689e3df6f',
'upload_date': '20151116',
'timestamp': 1447707266,
'duration': 53,
},
'params': {
# m3u8 download
'skip_download': True,
},
}]
_NETRC_MACHINE = 'gaia'
_jwt = None
def _real_initialize(self):
auth = self._get_cookies('https://www.gaia.com/').get('auth')
if auth:
auth = self._parse_json(urllib.parse.unquote(auth.value), None, fatal=False)
self._jwt = auth.get('jwt')
2019-01-09 13:23:26 +00:00
def _perform_login(self, username, password):
if self._jwt:
return
auth = self._download_json(
'https://auth.gaia.com/v1/login',
None, data=urlencode_postdata({
'username': username,
'password': password,
}))
if auth.get('success') is False:
raise ExtractorError(', '.join(auth['messages']), expected=True)
self._jwt = auth.get('jwt')
2019-01-09 13:23:26 +00:00
def _real_extract(self, url):
display_id, vtype = self._match_valid_url(url).groups()
2019-01-09 13:23:26 +00:00
node_id = self._download_json(
'https://brooklyn.gaia.com/pathinfo', display_id, query={
'path': 'video/' + display_id,
})['id']
node = self._download_json(
'https://brooklyn.gaia.com/node/%d' % node_id, node_id)
vdata = node[vtype]
media_id = str(vdata['nid'])
2019-01-09 13:23:26 +00:00
title = node['title']
headers = None
if self._jwt:
headers = {'Authorization': 'Bearer ' + self._jwt}
2019-01-09 13:23:26 +00:00
media = self._download_json(
'https://brooklyn.gaia.com/media/' + media_id,
media_id, headers=headers)
2019-01-09 13:23:26 +00:00
formats = self._extract_m3u8_formats(
media['mediaUrls']['bcHLS'], media_id, 'mp4')
subtitles = {}
text_tracks = media.get('textTracks', {})
for key in ('captions', 'subtitles'):
for lang, sub_url in text_tracks.get(key, {}).items():
subtitles.setdefault(lang, []).append({
'url': sub_url,
})
fivestar = node.get('fivestar', {})
fields = node.get('fields', {})
def get_field_value(key, value_key='value'):
return try_get(fields, lambda x: x[key][0][value_key])
return {
'id': media_id,
'display_id': display_id,
'title': title,
'formats': formats,
'description': strip_or_none(get_field_value('body') or get_field_value('teaser')),
'timestamp': int_or_none(node.get('created')),
'subtitles': subtitles,
'duration': int_or_none(vdata.get('duration')),
'like_count': int_or_none(try_get(fivestar, lambda x: x['up_count']['value'])),
'dislike_count': int_or_none(try_get(fivestar, lambda x: x['down_count']['value'])),
'comment_count': int_or_none(node.get('comment_count')),
'series': try_get(node, lambda x: x['series']['title'], str),
2019-01-09 13:23:26 +00:00
'season_number': int_or_none(get_field_value('season')),
'season_id': str_or_none(get_field_value('series_nid', 'nid')),
'episode_number': int_or_none(get_field_value('episode')),
}