Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/gaia.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_str,
   9     compat_urllib_parse_unquote,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     int_or_none,
  14     str_or_none,
  15     strip_or_none,
  16     try_get,
  17     urlencode_postdata,
  18 )
  19
  20
  21 class GaiaIE(InfoExtractor):
  22     _VALID_URL = r'https?://(?:www\.)?gaia\.com/video/(?P<id>[^/?]+).*?\bfullplayer=(?P<type>feature|preview)'
  23     _TESTS = [{
  24         'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=feature',
  25         'info_dict': {
  26             'id': '89356',
  27             'ext': 'mp4',
  28             'title': 'Connecting with Universal Consciousness',
  29             'description': 'md5:844e209ad31b7d31345f5ed689e3df6f',
  30             'upload_date': '20151116',
  31             'timestamp': 1447707266,
  32             'duration': 936,
  33         },
  34         'params': {
  35             # m3u8 download
  36             'skip_download': True,
  37         },
  38     }, {
  39         'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=preview',
  40         'info_dict': {
  41             'id': '89351',
  42             'ext': 'mp4',
  43             'title': 'Connecting with Universal Consciousness',
  44             'description': 'md5:844e209ad31b7d31345f5ed689e3df6f',
  45             'upload_date': '20151116',
  46             'timestamp': 1447707266,
  47             'duration': 53,
  48         },
  49         'params': {
  50             # m3u8 download
  51             'skip_download': True,
  52         },
  53     }]
  54     _NETRC_MACHINE = 'gaia'
  55     _jwt = None
  56
  57     def _real_initialize(self):
  58         auth = self._get_cookies('https://www.gaia.com/').get('auth')
  59         if auth:
  60             auth = self._parse_json(
  61                 compat_urllib_parse_unquote(auth.value),
  62                 None, fatal=False)
  63         if not auth:
  64             username, password = self._get_login_info()
  65             if username is None:
  66                 return
  67             auth = self._download_json(
  68                 'https://auth.gaia.com/v1/login',
  69                 None, data=urlencode_postdata({
  70                     'username': username,
  71                     'password': password
  72                 }))
  73             if auth.get('success') is False:
  74                 raise ExtractorError(', '.join(auth['messages']), expected=True)
  75         if auth:
  76             self._jwt = auth.get('jwt')
  77
  78     def _real_extract(self, url):
  79         display_id, vtype = re.search(self._VALID_URL, url).groups()
  80         node_id = self._download_json(
  81             'https://brooklyn.gaia.com/pathinfo', display_id, query={
  82                 'path': 'video/' + display_id,
  83             })['id']
  84         node = self._download_json(
  85             'https://brooklyn.gaia.com/node/%d' % node_id, node_id)
  86         vdata = node[vtype]
  87         media_id = compat_str(vdata['nid'])
  88         title = node['title']
  89
  90         headers = None
  91         if self._jwt:
  92             headers = {'Authorization': 'Bearer ' + self._jwt}
  93         media = self._download_json(
  94             'https://brooklyn.gaia.com/media/' + media_id,
  95             media_id, headers=headers)
  96         formats = self._extract_m3u8_formats(
  97             media['mediaUrls']['bcHLS'], media_id, 'mp4')
  98         self._sort_formats(formats)
  99
 100         subtitles = {}
 101         text_tracks = media.get('textTracks', {})
 102         for key in ('captions', 'subtitles'):
 103             for lang, sub_url in text_tracks.get(key, {}).items():
 104                 subtitles.setdefault(lang, []).append({
 105                     'url': sub_url,
 106                 })
 107
 108         fivestar = node.get('fivestar', {})
 109         fields = node.get('fields', {})
 110
 111         def get_field_value(key, value_key='value'):
 112             return try_get(fields, lambda x: x[key][0][value_key])
 113
 114         return {
 115             'id': media_id,
 116             'display_id': display_id,
 117             'title': title,
 118             'formats': formats,
 119             'description': strip_or_none(get_field_value('body') or get_field_value('teaser')),
 120             'timestamp': int_or_none(node.get('created')),
 121             'subtitles': subtitles,
 122             'duration': int_or_none(vdata.get('duration')),
 123             'like_count': int_or_none(try_get(fivestar, lambda x: x['up_count']['value'])),
 124             'dislike_count': int_or_none(try_get(fivestar, lambda x: x['down_count']['value'])),
 125             'comment_count': int_or_none(node.get('comment_count')),
 126             'series': try_get(node, lambda x: x['series']['title'], compat_str),
 127             'season_number': int_or_none(get_field_value('season')),
 128             'season_id': str_or_none(get_field_value('series_nid', 'nid')),
 129             'episode_number': int_or_none(get_field_value('episode')),
 130         }