projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| e7b6caef | 1 | # coding: utf-8 |
| 2 | from __future__ import unicode_literals | |
| 3 | ||
| 4 | import re | |
| 5 | ||
| 6 | from .common import InfoExtractor | |
| 72310315 | 7 | from ..compat import compat_str |
| e7b6caef | 8 | from ..utils import ( |
| 9 | ExtractorError, | |
| 10 | int_or_none, | |
| e7b6caef | 11 | ) |
| 12 | ||
| 13 | ||
| 14 | class ViuBaseIE(InfoExtractor): | |
| 72310315 | 15 | def _real_initialize(self): |
| e7b6caef | 16 | viu_auth_res = self._request_webpage( |
| 72310315 RA |
17 | 'https://www.viu.com/api/apps/v2/authenticate', None, |
| 18 | 'Requesting Viu auth', query={ | |
| 19 | 'acct': 'test', | |
| 20 | 'appid': 'viu_desktop', | |
| 21 | 'fmt': 'json', | |
| 22 | 'iid': 'guest', | |
| 23 | 'languageid': 'default', | |
| 24 | 'platform': 'desktop', | |
| 25 | 'userid': 'guest', | |
| 26 | 'useridtype': 'guest', | |
| 27 | 'ver': '1.0' | |
| e7b6caef | 28 | }) |
| 72310315 RA |
29 | self._auth_token = viu_auth_res.info()['X-VIU-AUTH'] |
| 30 | ||
| 31 | def _call_api(self, path, *args, **kwargs): | |
| 32 | headers = self.geo_verification_headers() | |
| 33 | headers.update({ | |
| 34 | 'X-VIU-AUTH': self._auth_token | |
| 35 | }) | |
| 36 | headers.update(kwargs.get('headers', {})) | |
| 37 | kwargs['headers'] = headers | |
| 38 | response = self._download_json( | |
| 39 | 'https://www.viu.com/api/' + path, *args, **kwargs)['response'] | |
| 40 | if response.get('status') != 'success': | |
| 41 | raise ExtractorError('%s said: %s' % ( | |
| 42 | self.IE_NAME, response['message']), expected=True) | |
| 43 | return response | |
| e7b6caef | 44 | |
| 45 | ||
| 46 | class ViuIE(ViuBaseIE): | |
| 72310315 | 47 | _VALID_URL = r'(?:viu:|https?://www\.viu\.com/[a-z]{2}/media/)(?P<id>\d+)' |
| e7b6caef | 48 | _TESTS = [{ |
| e7b6caef | 49 | 'url': 'https://www.viu.com/en/media/1116705532?containerId=playlist-22168059', |
| 50 | 'info_dict': { | |
| 51 | 'id': '1116705532', | |
| 52 | 'ext': 'mp4', | |
| 72310315 | 53 | 'title': 'Citizen Khan - Ep 1', |
| e7b6caef | 54 | 'description': 'md5:d7ea1604f49e5ba79c212c551ce2110e', |
| 55 | }, | |
| 56 | 'params': { | |
| 57 | 'skip_download': 'm3u8 download', | |
| 58 | }, | |
| 59 | 'skip': 'Geo-restricted to India', | |
| 60 | }, { | |
| 61 | 'url': 'https://www.viu.com/en/media/1130599965', | |
| 62 | 'info_dict': { | |
| 63 | 'id': '1130599965', | |
| 64 | 'ext': 'mp4', | |
| 65 | 'title': 'Jealousy Incarnate - Episode 1', | |
| 66 | 'description': 'md5:d3d82375cab969415d2720b6894361e9', | |
| 67 | }, | |
| 68 | 'params': { | |
| 69 | 'skip_download': 'm3u8 download', | |
| 70 | }, | |
| 71 | 'skip': 'Geo-restricted to Indonesia', | |
| 72 | }] | |
| 73 | ||
| 74 | def _real_extract(self, url): | |
| 75 | video_id = self._match_id(url) | |
| 76 | ||
| 72310315 RA |
77 | video_data = self._call_api( |
| 78 | 'clip/load', video_id, 'Downloading video data', query={ | |
| 79 | 'appid': 'viu_desktop', | |
| 80 | 'fmt': 'json', | |
| 81 | 'id': video_id | |
| 82 | })['item'][0] | |
| 83 | ||
| 84 | title = video_data['title'] | |
| 85 | ||
| 86 | m3u8_url = None | |
| 87 | url_path = video_data.get('urlpathd') or video_data.get('urlpath') | |
| 88 | tdirforwhole = video_data.get('tdirforwhole') | |
| 89 | hls_file = video_data.get('hlsfile') | |
| 90 | if url_path and tdirforwhole and hls_file: | |
| 91 | m3u8_url = '%s/%s/%s' % (url_path, tdirforwhole, hls_file) | |
| 92 | else: | |
| 93 | m3u8_url = re.sub( | |
| 94 | r'(/hlsc_)[a-z]+(\d+\.m3u8)', | |
| 95 | r'\1whe\2', video_data['href']) | |
| 96 | formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4') | |
| e7b6caef | 97 | self._sort_formats(formats) |
| 98 | ||
| 99 | subtitles = {} | |
| 72310315 RA |
100 | for key, value in video_data.items(): |
| 101 | mobj = re.match(r'^subtitle_(?P<lang>[^_]+)_(?P<ext>(vtt|srt))', key) | |
| 102 | if not mobj: | |
| 103 | continue | |
| 104 | subtitles.setdefault(mobj.group('lang'), []).append({ | |
| 105 | 'url': value, | |
| 106 | 'ext': mobj.group('ext') | |
| 107 | }) | |
| e7b6caef | 108 | |
| 109 | return { | |
| 110 | 'id': video_id, | |
| 111 | 'title': title, | |
| 72310315 RA |
112 | 'description': video_data.get('description'), |
| 113 | 'series': video_data.get('moviealbumshowname'), | |
| 114 | 'episode': title, | |
| 115 | 'episode_number': int_or_none(video_data.get('episodeno')), | |
| 116 | 'duration': int_or_none(video_data.get('duration')), | |
| e7b6caef | 117 | 'formats': formats, |
| 118 | 'subtitles': subtitles, | |
| 119 | } | |
| 120 | ||
| 121 | ||
| 122 | class ViuPlaylistIE(ViuBaseIE): | |
| 123 | IE_NAME = 'viu:playlist' | |
| 72310315 | 124 | _VALID_URL = r'https?://www\.viu\.com/[^/]+/listing/playlist-(?P<id>\d+)' |
| e7b6caef | 125 | _TEST = { |
| 126 | 'url': 'https://www.viu.com/en/listing/playlist-22461380', | |
| 127 | 'info_dict': { | |
| 72310315 | 128 | 'id': '22461380', |
| e7b6caef | 129 | 'title': 'The Good Wife', |
| 130 | }, | |
| 131 | 'playlist_count': 16, | |
| 132 | 'skip': 'Geo-restricted to Indonesia', | |
| 133 | } | |
| 134 | ||
| 135 | def _real_extract(self, url): | |
| 136 | playlist_id = self._match_id(url) | |
| 72310315 RA |
137 | playlist_data = self._call_api( |
| 138 | 'container/load', playlist_id, | |
| 139 | 'Downloading playlist info', query={ | |
| 140 | 'appid': 'viu_desktop', | |
| 141 | 'fmt': 'json', | |
| 142 | 'id': 'playlist-' + playlist_id | |
| 143 | })['container'] | |
| 144 | ||
| 145 | entries = [] | |
| 146 | for item in playlist_data.get('item', []): | |
| 147 | item_id = item.get('id') | |
| 148 | if not item_id: | |
| 149 | continue | |
| 150 | item_id = compat_str(item_id) | |
| 151 | entries.append(self.url_result( | |
| 152 | 'viu:' + item_id, 'Viu', item_id)) | |
| 153 | ||
| 154 | return self.playlist_result( | |
| 155 | entries, playlist_id, playlist_data.get('title')) | |
| 156 | ||
| 157 | ||
| 158 | class ViuOTTIE(InfoExtractor): | |
| 159 | IE_NAME = 'viu:ott' | |
| 160 | _VALID_URL = r'https?://(?:www\.)?viu\.com/ott/(?P<country_code>[a-z]{2})/[a-z]{2}-[a-z]{2}/vod/(?P<id>\d+)' | |
| 161 | _TESTS = [{ | |
| 162 | 'url': 'http://www.viu.com/ott/sg/en-us/vod/3421/The%20Prime%20Minister%20and%20I', | |
| 163 | 'info_dict': { | |
| 164 | 'id': '3421', | |
| 165 | 'ext': 'mp4', | |
| 166 | 'title': 'A New Beginning', | |
| 167 | 'description': 'md5:1e7486a619b6399b25ba6a41c0fe5b2c', | |
| 168 | }, | |
| 169 | 'params': { | |
| 170 | 'skip_download': 'm3u8 download', | |
| 171 | }, | |
| 172 | 'skip': 'Geo-restricted to Singapore', | |
| 173 | }, { | |
| 174 | 'url': 'http://www.viu.com/ott/hk/zh-hk/vod/7123/%E5%A4%A7%E4%BA%BA%E5%A5%B3%E5%AD%90', | |
| 175 | 'info_dict': { | |
| 176 | 'id': '7123', | |
| 177 | 'ext': 'mp4', | |
| 178 | 'title': '這就是我的生活之道', | |
| 179 | 'description': 'md5:4eb0d8b08cf04fcdc6bbbeb16043434f', | |
| 180 | }, | |
| 181 | 'params': { | |
| 182 | 'skip_download': 'm3u8 download', | |
| 183 | }, | |
| 184 | 'skip': 'Geo-restricted to Hong Kong', | |
| 185 | }] | |
| 186 | ||
| 187 | def _real_extract(self, url): | |
| 188 | country_code, video_id = re.match(self._VALID_URL, url).groups() | |
| 189 | ||
| 190 | product_data = self._download_json( | |
| 191 | 'http://www.viu.com/ott/%s/index.php' % country_code, video_id, | |
| 192 | 'Downloading video info', query={ | |
| 193 | 'r': 'vod/ajax-detail', | |
| 194 | 'platform_flag_label': 'web', | |
| 195 | 'product_id': video_id, | |
| 196 | })['data'] | |
| 197 | ||
| 198 | video_data = product_data.get('current_product') | |
| 199 | if not video_data: | |
| 200 | raise ExtractorError('This video is not available in your region.', expected=True) | |
| 201 | ||
| 202 | stream_data = self._download_json( | |
| 203 | 'https://d1k2us671qcoau.cloudfront.net/distribute_web_%s.php' % country_code, | |
| 204 | video_id, 'Downloading stream info', query={ | |
| 205 | 'ccs_product_id': video_data['ccs_product_id'], | |
| 206 | })['data']['stream'] | |
| 207 | ||
| 208 | stream_sizes = stream_data.get('size', {}) | |
| 209 | formats = [] | |
| 210 | for vid_format, stream_url in stream_data.get('url', {}).items(): | |
| 211 | height = int_or_none(self._search_regex( | |
| 212 | r's(\d+)p', vid_format, 'height', default=None)) | |
| 213 | formats.append({ | |
| 214 | 'format_id': vid_format, | |
| 215 | 'url': stream_url, | |
| 216 | 'height': height, | |
| 217 | 'ext': 'mp4', | |
| 218 | 'filesize': int_or_none(stream_sizes.get(vid_format)) | |
| 219 | }) | |
| 220 | self._sort_formats(formats) | |
| 221 | ||
| 222 | subtitles = {} | |
| 223 | for sub in video_data.get('subtitle', []): | |
| 224 | sub_url = sub.get('url') | |
| 225 | if not sub_url: | |
| 226 | continue | |
| 227 | subtitles.setdefault(sub.get('name'), []).append({ | |
| 228 | 'url': sub_url, | |
| 229 | 'ext': 'srt', | |
| 230 | }) | |
| 231 | ||
| 232 | title = video_data['synopsis'].strip() | |
| 233 | ||
| 234 | return { | |
| 235 | 'id': video_id, | |
| 236 | 'title': title, | |
| 237 | 'description': video_data.get('description'), | |
| 238 | 'series': product_data.get('series', {}).get('name'), | |
| 239 | 'episode': title, | |
| 240 | 'episode_number': int_or_none(video_data.get('number')), | |
| 241 | 'duration': int_or_none(stream_data.get('duration')), | |
| 242 | 'thumbnail': video_data.get('cover_image_url'), | |
| 243 | 'formats': formats, | |
| 244 | 'subtitles': subtitles, | |
| 245 | } |