Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/viu.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_kwargs,
   9     compat_str,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     int_or_none,
  14 )
  15
  16
  17 class ViuBaseIE(InfoExtractor):
  18     def _real_initialize(self):
  19         viu_auth_res = self._request_webpage(
  20             'https://www.viu.com/api/apps/v2/authenticate', None,
  21             'Requesting Viu auth', query={
  22                 'acct': 'test',
  23                 'appid': 'viu_desktop',
  24                 'fmt': 'json',
  25                 'iid': 'guest',
  26                 'languageid': 'default',
  27                 'platform': 'desktop',
  28                 'userid': 'guest',
  29                 'useridtype': 'guest',
  30                 'ver': '1.0'
  31             }, headers=self.geo_verification_headers())
  32         self._auth_token = viu_auth_res.info()['X-VIU-AUTH']
  33
  34     def _call_api(self, path, *args, **kwargs):
  35         headers = self.geo_verification_headers()
  36         headers.update({
  37             'X-VIU-AUTH': self._auth_token
  38         })
  39         headers.update(kwargs.get('headers', {}))
  40         kwargs['headers'] = headers
  41         response = self._download_json(
  42             'https://www.viu.com/api/' + path, *args,
  43             **compat_kwargs(kwargs))['response']
  44         if response.get('status') != 'success':
  45             raise ExtractorError('%s said: %s' % (
  46                 self.IE_NAME, response['message']), expected=True)
  47         return response
  48
  49
  50 class ViuIE(ViuBaseIE):
  51     _VALID_URL = r'(?:viu:|https?://[^/]+\.viu\.com/[a-z]{2}/media/)(?P<id>\d+)'
  52     _TESTS = [{
  53         'url': 'https://www.viu.com/en/media/1116705532?containerId=playlist-22168059',
  54         'info_dict': {
  55             'id': '1116705532',
  56             'ext': 'mp4',
  57             'title': 'Citizen Khan - Ep 1',
  58             'description': 'md5:d7ea1604f49e5ba79c212c551ce2110e',
  59         },
  60         'params': {
  61             'skip_download': 'm3u8 download',
  62         },
  63         'skip': 'Geo-restricted to India',
  64     }, {
  65         'url': 'https://www.viu.com/en/media/1130599965',
  66         'info_dict': {
  67             'id': '1130599965',
  68             'ext': 'mp4',
  69             'title': 'Jealousy Incarnate - Episode 1',
  70             'description': 'md5:d3d82375cab969415d2720b6894361e9',
  71         },
  72         'params': {
  73             'skip_download': 'm3u8 download',
  74         },
  75         'skip': 'Geo-restricted to Indonesia',
  76     }, {
  77         'url': 'https://india.viu.com/en/media/1126286865',
  78         'only_matching': True,
  79     }]
  80
  81     def _real_extract(self, url):
  82         video_id = self._match_id(url)
  83
  84         video_data = self._call_api(
  85             'clip/load', video_id, 'Downloading video data', query={
  86                 'appid': 'viu_desktop',
  87                 'fmt': 'json',
  88                 'id': video_id
  89             })['item'][0]
  90
  91         title = video_data['title']
  92
  93         m3u8_url = None
  94         url_path = video_data.get('urlpathd') or video_data.get('urlpath')
  95         tdirforwhole = video_data.get('tdirforwhole')
  96         # #EXT-X-BYTERANGE is not supported by native hls downloader
  97         # and ffmpeg (#10955)
  98         # hls_file = video_data.get('hlsfile')
  99         hls_file = video_data.get('jwhlsfile')
 100         if url_path and tdirforwhole and hls_file:
 101             m3u8_url = '%s/%s/%s' % (url_path, tdirforwhole, hls_file)
 102         else:
 103             # m3u8_url = re.sub(
 104             #     r'(/hlsc_)[a-z]+(\d+\.m3u8)',
 105             #     r'\1whe\2', video_data['href'])
 106             m3u8_url = video_data['href']
 107         formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
 108         self._sort_formats(formats)
 109
 110         subtitles = {}
 111         for key, value in video_data.items():
 112             mobj = re.match(r'^subtitle_(?P<lang>[^_]+)_(?P<ext>(vtt|srt))', key)
 113             if not mobj:
 114                 continue
 115             subtitles.setdefault(mobj.group('lang'), []).append({
 116                 'url': value,
 117                 'ext': mobj.group('ext')
 118             })
 119
 120         return {
 121             'id': video_id,
 122             'title': title,
 123             'description': video_data.get('description'),
 124             'series': video_data.get('moviealbumshowname'),
 125             'episode': title,
 126             'episode_number': int_or_none(video_data.get('episodeno')),
 127             'duration': int_or_none(video_data.get('duration')),
 128             'formats': formats,
 129             'subtitles': subtitles,
 130         }
 131
 132
 133 class ViuPlaylistIE(ViuBaseIE):
 134     IE_NAME = 'viu:playlist'
 135     _VALID_URL = r'https?://www\.viu\.com/[^/]+/listing/playlist-(?P<id>\d+)'
 136     _TEST = {
 137         'url': 'https://www.viu.com/en/listing/playlist-22461380',
 138         'info_dict': {
 139             'id': '22461380',
 140             'title': 'The Good Wife',
 141         },
 142         'playlist_count': 16,
 143         'skip': 'Geo-restricted to Indonesia',
 144     }
 145
 146     def _real_extract(self, url):
 147         playlist_id = self._match_id(url)
 148         playlist_data = self._call_api(
 149             'container/load', playlist_id,
 150             'Downloading playlist info', query={
 151                 'appid': 'viu_desktop',
 152                 'fmt': 'json',
 153                 'id': 'playlist-' + playlist_id
 154             })['container']
 155
 156         entries = []
 157         for item in playlist_data.get('item', []):
 158             item_id = item.get('id')
 159             if not item_id:
 160                 continue
 161             item_id = compat_str(item_id)
 162             entries.append(self.url_result(
 163                 'viu:' + item_id, 'Viu', item_id))
 164
 165         return self.playlist_result(
 166             entries, playlist_id, playlist_data.get('title'))
 167
 168
 169 class ViuOTTIE(InfoExtractor):
 170     IE_NAME = 'viu:ott'
 171     _VALID_URL = r'https?://(?:www\.)?viu\.com/ott/(?P<country_code>[a-z]{2})/[a-z]{2}-[a-z]{2}/vod/(?P<id>\d+)'
 172     _TESTS = [{
 173         'url': 'http://www.viu.com/ott/sg/en-us/vod/3421/The%20Prime%20Minister%20and%20I',
 174         'info_dict': {
 175             'id': '3421',
 176             'ext': 'mp4',
 177             'title': 'A New Beginning',
 178             'description': 'md5:1e7486a619b6399b25ba6a41c0fe5b2c',
 179         },
 180         'params': {
 181             'skip_download': 'm3u8 download',
 182         },
 183         'skip': 'Geo-restricted to Singapore',
 184     }, {
 185         'url': 'http://www.viu.com/ott/hk/zh-hk/vod/7123/%E5%A4%A7%E4%BA%BA%E5%A5%B3%E5%AD%90',
 186         'info_dict': {
 187             'id': '7123',
 188             'ext': 'mp4',
 189             'title': '這就是我的生活之道',
 190             'description': 'md5:4eb0d8b08cf04fcdc6bbbeb16043434f',
 191         },
 192         'params': {
 193             'skip_download': 'm3u8 download',
 194         },
 195         'skip': 'Geo-restricted to Hong Kong',
 196     }]
 197
 198     _AREA_ID = {
 199         'HK': 1,
 200         'SG': 2,
 201         'TH': 4,
 202         'PH': 5,
 203     }
 204
 205     def _real_extract(self, url):
 206         country_code, video_id = re.match(self._VALID_URL, url).groups()
 207
 208         query = {
 209             'r': 'vod/ajax-detail',
 210             'platform_flag_label': 'web',
 211             'product_id': video_id,
 212         }
 213
 214         area_id = self._AREA_ID.get(country_code.upper())
 215         if area_id:
 216             query['area_id'] = area_id
 217
 218         product_data = self._download_json(
 219             'http://www.viu.com/ott/%s/index.php' % country_code, video_id,
 220             'Downloading video info', query=query)['data']
 221
 222         video_data = product_data.get('current_product')
 223         if not video_data:
 224             raise ExtractorError('This video is not available in your region.', expected=True)
 225
 226         stream_data = self._download_json(
 227             'https://d1k2us671qcoau.cloudfront.net/distribute_web_%s.php' % country_code,
 228             video_id, 'Downloading stream info', query={
 229                 'ccs_product_id': video_data['ccs_product_id'],
 230             }, headers={
 231                 'Referer': url,
 232                 'Origin': re.search(r'https?://[^/]+', url).group(0),
 233             })['data']['stream']
 234
 235         stream_sizes = stream_data.get('size', {})
 236         formats = []
 237         for vid_format, stream_url in stream_data.get('url', {}).items():
 238             height = int_or_none(self._search_regex(
 239                 r's(\d+)p', vid_format, 'height', default=None))
 240             formats.append({
 241                 'format_id': vid_format,
 242                 'url': stream_url,
 243                 'height': height,
 244                 'ext': 'mp4',
 245                 'filesize': int_or_none(stream_sizes.get(vid_format))
 246             })
 247         self._sort_formats(formats)
 248
 249         subtitles = {}
 250         for sub in video_data.get('subtitle', []):
 251             sub_url = sub.get('url')
 252             if not sub_url:
 253                 continue
 254             subtitles.setdefault(sub.get('name'), []).append({
 255                 'url': sub_url,
 256                 'ext': 'srt',
 257             })
 258
 259         title = video_data['synopsis'].strip()
 260
 261         return {
 262             'id': video_id,
 263             'title': title,
 264             'description': video_data.get('description'),
 265             'series': product_data.get('series', {}).get('name'),
 266             'episode': title,
 267             'episode_number': int_or_none(video_data.get('number')),
 268             'duration': int_or_none(stream_data.get('duration')),
 269             'thumbnail': video_data.get('cover_image_url'),
 270             'formats': formats,
 271             'subtitles': subtitles,
 272         }