_ Git - youtube-dl/blob - youtube_dl/extractor/curiositystream.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     urlencode_postdata,
   8     compat_str,
   9     ExtractorError,
  10 )
  11
  12
  13 class CuriosityStreamBaseIE(InfoExtractor):
  14     _NETRC_MACHINE = 'curiositystream'
  15     _auth_token = None
  16     _API_BASE_URL = 'https://api.curiositystream.com/v1/'
  17
  18     def _handle_errors(self, result):
  19         error = result.get('error', {}).get('message')
  20         if error:
  21             if isinstance(error, dict):
  22                 error = ', '.join(error.values())
  23             raise ExtractorError(
  24                 '%s said: %s' % (self.IE_NAME, error), expected=True)
  25
  26     def _call_api(self, path, video_id):
  27         headers = {}
  28         if self._auth_token:
  29             headers['X-Auth-Token'] = self._auth_token
  30         result = self._download_json(
  31             self._API_BASE_URL + path, video_id, headers=headers)
  32         self._handle_errors(result)
  33         return result['data']
  34
  35     def _real_initialize(self):
  36         if not self._auth_token:
  37             user = self._downloader.cache.load('curiositystream', 'user') or {}
  38             self._auth_token = user.get('auth_token')
  39             if not self._auth_token:
  40                 (email, password) = self._get_login_info()
  41                 if email is None:
  42                     return
  43                 result = self._download_json(
  44                     self._API_BASE_URL + 'login', None, data=urlencode_postdata({
  45                         'email': email,
  46                         'password': password,
  47                     }))
  48                 self._handle_errors(result)
  49                 self._auth_token = result['message']['auth_token']
  50                 self._downloader.cache.store(
  51                     'curiositystream', 'user', {
  52                         'auth_token': self._auth_token,
  53                     })
  54
  55     def _extract_media_info(self, media):
  56         video_id = compat_str(media['id'])
  57         limelight_media_id = media['limelight_media_id']
  58         title = media['title']
  59
  60         subtitles = {}
  61         for closed_caption in media.get('closed_captions', []):
  62             sub_url = closed_caption.get('file')
  63             if not sub_url:
  64                 continue
  65             lang = closed_caption.get('code') or closed_caption.get('language') or 'en'
  66             subtitles.setdefault(lang, []).append({
  67                 'url': sub_url,
  68             })
  69
  70         return {
  71             '_type': 'url_transparent',
  72             'id': video_id,
  73             'url': 'limelight:media:' + limelight_media_id,
  74             'title': title,
  75             'description': media.get('description'),
  76             'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'),
  77             'duration': int_or_none(media.get('duration')),
  78             'tags': media.get('tags'),
  79             'subtitles': subtitles,
  80             'ie_key': 'LimelightMedia',
  81         }
  82
  83
  84 class CuriosityStreamIE(CuriosityStreamBaseIE):
  85     IE_NAME = 'curiositystream'
  86     _VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)'
  87     _TEST = {
  88         'url': 'https://app.curiositystream.com/video/2',
  89         'md5': 'a0074c190e6cddaf86900b28d3e9ee7a',
  90         'info_dict': {
  91             'id': '2',
  92             'ext': 'mp4',
  93             'title': 'How Did You Develop The Internet?',
  94             'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
  95             'timestamp': 1448388615,
  96             'upload_date': '20151124',
  97         }
  98     }
  99
 100     def _real_extract(self, url):
 101         video_id = self._match_id(url)
 102         media = self._call_api('media/' + video_id, video_id)
 103         return self._extract_media_info(media)
 104
 105
 106 class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
 107     IE_NAME = 'curiositystream:collection'
 108     _VALID_URL = r'https?://app\.curiositystream\.com/collection/(?P<id>\d+)'
 109     _TEST = {
 110         'url': 'https://app.curiositystream.com/collection/2',
 111         'info_dict': {
 112             'id': '2',
 113             'title': 'Curious Minds: The Internet',
 114             'description': 'How is the internet shaping our lives in the 21st Century?',
 115         },
 116         'playlist_mincount': 17,
 117     }
 118
 119     def _real_extract(self, url):
 120         collection_id = self._match_id(url)
 121         collection = self._call_api(
 122             'collections/' + collection_id, collection_id)
 123         entries = []
 124         for media in collection.get('media', []):
 125             entries.append(self._extract_media_info(media))
 126         return self.playlist_result(
 127             entries, collection_id,
 128             collection.get('title'), collection.get('description'))