_ 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         (email, password) = self._get_login_info()
  37         if email is None:
  38             return
  39         result = self._download_json(
  40             self._API_BASE_URL + 'login', None, data=urlencode_postdata({
  41                 'email': email,
  42                 'password': password,
  43             }))
  44         self._handle_errors(result)
  45         self._auth_token = result['message']['auth_token']
  46
  47     def _extract_media_info(self, media):
  48         video_id = compat_str(media['id'])
  49         limelight_media_id = media['limelight_media_id']
  50         title = media['title']
  51
  52         subtitles = {}
  53         for closed_caption in media.get('closed_captions', []):
  54             sub_url = closed_caption.get('file')
  55             if not sub_url:
  56                 continue
  57             lang = closed_caption.get('code') or closed_caption.get('language') or 'en'
  58             subtitles.setdefault(lang, []).append({
  59                 'url': sub_url,
  60             })
  61
  62         return {
  63             '_type': 'url_transparent',
  64             'id': video_id,
  65             'url': 'limelight:media:' + limelight_media_id,
  66             'title': title,
  67             'description': media.get('description'),
  68             'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'),
  69             'duration': int_or_none(media.get('duration')),
  70             'tags': media.get('tags'),
  71             'subtitles': subtitles,
  72             'ie_key': 'LimelightMedia',
  73         }
  74
  75
  76 class CuriosityStreamIE(CuriosityStreamBaseIE):
  77     IE_NAME = 'curiositystream'
  78     _VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)'
  79     _TEST = {
  80         'url': 'https://app.curiositystream.com/video/2',
  81         'md5': 'a0074c190e6cddaf86900b28d3e9ee7a',
  82         'info_dict': {
  83             'id': '2',
  84             'ext': 'mp4',
  85             'title': 'How Did You Develop The Internet?',
  86             'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
  87             'timestamp': 1448388615,
  88             'upload_date': '20151124',
  89         }
  90     }
  91
  92     def _real_extract(self, url):
  93         video_id = self._match_id(url)
  94         media = self._call_api('media/' + video_id, video_id)
  95         return self._extract_media_info(media)
  96
  97
  98 class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
  99     IE_NAME = 'curiositystream:collection'
 100     _VALID_URL = r'https?://app\.curiositystream\.com/collection/(?P<id>\d+)'
 101     _TEST = {
 102         'url': 'https://app.curiositystream.com/collection/2',
 103         'info_dict': {
 104             'id': '2',
 105             'title': 'Curious Minds: The Internet',
 106             'description': 'How is the internet shaping our lives in the 21st Century?',
 107         },
 108         'playlist_mincount': 17,
 109     }
 110
 111     def _real_extract(self, url):
 112         collection_id = self._match_id(url)
 113         collection = self._call_api(
 114             'collections/' + collection_id, collection_id)
 115         entries = []
 116         for media in collection.get('media', []):
 117             entries.append(self._extract_media_info(media))
 118         return self.playlist_result(
 119             entries, collection_id,
 120             collection.get('title'), collection.get('description'))