1# coding: utf-8 2from __future__ import unicode_literals 3 4import re 5 6from .common import InfoExtractor 7from ..utils import ( 8 int_or_none, 9 urlencode_postdata, 10 compat_str, 11 ExtractorError, 12) 13 14 15class CuriosityStreamBaseIE(InfoExtractor): 16 _NETRC_MACHINE = 'curiositystream' 17 _auth_token = None 18 19 def _handle_errors(self, result): 20 error = result.get('error', {}).get('message') 21 if error: 22 if isinstance(error, dict): 23 error = ', '.join(error.values()) 24 raise ExtractorError( 25 '%s said: %s' % (self.IE_NAME, error), expected=True) 26 27 def _call_api(self, path, video_id, query=None): 28 headers = {} 29 if self._auth_token: 30 headers['X-Auth-Token'] = self._auth_token 31 result = self._download_json( 32 self._API_BASE_URL + path, video_id, headers=headers, query=query) 33 self._handle_errors(result) 34 return result['data'] 35 36 def _real_initialize(self): 37 email, password = self._get_login_info() 38 if email is None: 39 return 40 result = self._download_json( 41 'https://api.curiositystream.com/v1/login', None, 42 note='Logging in', data=urlencode_postdata({ 43 'email': email, 44 'password': password, 45 })) 46 self._handle_errors(result) 47 CuriosityStreamBaseIE._auth_token = result['message']['auth_token'] 48 49 50class CuriosityStreamIE(CuriosityStreamBaseIE): 51 IE_NAME = 'curiositystream' 52 _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)' 53 _TESTS = [{ 54 'url': 'https://app.curiositystream.com/video/2', 55 'info_dict': { 56 'id': '2', 57 'ext': 'mp4', 58 'title': 'How Did You Develop The Internet?', 59 'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.', 60 'channel': 'Curiosity Stream', 61 'categories': ['Technology', 'Interview'], 62 'average_rating': 96.79, 63 'series_id': '2', 64 }, 65 'params': { 66 # m3u8 download 67 'skip_download': True, 68 }, 69 }] 70 71 _API_BASE_URL = 'https://api.curiositystream.com/v1/media/' 72 73 def _real_extract(self, url): 74 video_id = self._match_id(url) 75 76 formats = [] 77 for encoding_format in ('m3u8', 'mpd'): 78 media = self._call_api(video_id, video_id, query={ 79 'encodingsNew': 'true', 80 'encodingsFormat': encoding_format, 81 }) 82 for encoding in media.get('encodings', []): 83 playlist_url = encoding.get('master_playlist_url') 84 if encoding_format == 'm3u8': 85 # use `m3u8` entry_protocol until EXT-X-MAP is properly supported by `m3u8_native` entry_protocol 86 formats.extend(self._extract_m3u8_formats( 87 playlist_url, video_id, 'mp4', 88 m3u8_id='hls', fatal=False)) 89 elif encoding_format == 'mpd': 90 formats.extend(self._extract_mpd_formats( 91 playlist_url, video_id, mpd_id='dash', fatal=False)) 92 encoding_url = encoding.get('url') 93 file_url = encoding.get('file_url') 94 if not encoding_url and not file_url: 95 continue 96 f = { 97 'width': int_or_none(encoding.get('width')), 98 'height': int_or_none(encoding.get('height')), 99 'vbr': int_or_none(encoding.get('video_bitrate')), 100 'abr': int_or_none(encoding.get('audio_bitrate')), 101 'filesize': int_or_none(encoding.get('size_in_bytes')), 102 'vcodec': encoding.get('video_codec'), 103 'acodec': encoding.get('audio_codec'), 104 'container': encoding.get('container_type'), 105 } 106 for f_url in (encoding_url, file_url): 107 if not f_url: 108 continue 109 fmt = f.copy() 110 rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', f_url) 111 if rtmp: 112 fmt.update({ 113 'url': rtmp.group('url'), 114 'play_path': rtmp.group('playpath'), 115 'app': rtmp.group('app'), 116 'ext': 'flv', 117 'format_id': 'rtmp', 118 }) 119 else: 120 fmt.update({ 121 'url': f_url, 122 'format_id': 'http', 123 }) 124 formats.append(fmt) 125 self._sort_formats(formats) 126 127 title = media['title'] 128 129 subtitles = {} 130 for closed_caption in media.get('closed_captions', []): 131 sub_url = closed_caption.get('file') 132 if not sub_url: 133 continue 134 lang = closed_caption.get('code') or closed_caption.get('language') or 'en' 135 subtitles.setdefault(lang, []).append({ 136 'url': sub_url, 137 }) 138 139 return { 140 'id': video_id, 141 'formats': formats, 142 'title': title, 143 'description': media.get('description'), 144 'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'), 145 'duration': int_or_none(media.get('duration')), 146 'tags': media.get('tags'), 147 'subtitles': subtitles, 148 'channel': media.get('producer'), 149 'categories': [media.get('primary_category'), media.get('type')], 150 'average_rating': media.get('rating_percentage'), 151 'series_id': str(media.get('collection_id') or '') or None, 152 } 153 154 155class CuriosityStreamCollectionBaseIE(CuriosityStreamBaseIE): 156 157 def _real_extract(self, url): 158 collection_id = self._match_id(url) 159 collection = self._call_api(collection_id, collection_id) 160 entries = [] 161 for media in collection.get('media', []): 162 media_id = compat_str(media.get('id')) 163 media_type, ie = ('series', CuriosityStreamSeriesIE) if media.get('is_collection') else ('video', CuriosityStreamIE) 164 entries.append(self.url_result( 165 'https://curiositystream.com/%s/%s' % (media_type, media_id), 166 ie=ie.ie_key(), video_id=media_id)) 167 return self.playlist_result( 168 entries, collection_id, 169 collection.get('title'), collection.get('description')) 170 171 172class CuriosityStreamCollectionsIE(CuriosityStreamCollectionBaseIE): 173 IE_NAME = 'curiositystream:collections' 174 _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/collections/(?P<id>\d+)' 175 _API_BASE_URL = 'https://api.curiositystream.com/v2/collections/' 176 _TESTS = [{ 177 'url': 'https://curiositystream.com/collections/86', 178 'info_dict': { 179 'id': '86', 180 'title': 'Staff Picks', 181 'description': 'Wondering where to start? Here are a few of our favorite series and films... from our couch to yours.', 182 }, 183 'playlist_mincount': 7, 184 }, { 185 'url': 'https://curiositystream.com/collections/36', 186 'only_matching': True, 187 }] 188 189 190class CuriosityStreamSeriesIE(CuriosityStreamCollectionBaseIE): 191 IE_NAME = 'curiositystream:series' 192 _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:series|collection)/(?P<id>\d+)' 193 _API_BASE_URL = 'https://api.curiositystream.com/v2/series/' 194 _TESTS = [{ 195 'url': 'https://curiositystream.com/series/2', 196 'info_dict': { 197 'id': '2', 198 'title': 'Curious Minds: The Internet', 199 'description': 'How is the internet shaping our lives in the 21st Century?', 200 }, 201 'playlist_mincount': 16, 202 }, { 203 'url': 'https://curiositystream.com/collection/2', 204 'only_matching': True, 205 }] 206