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 compat_str
   8 from ..utils import (
   9     ExtractorError,
  10     int_or_none,
  11 )
  12
  13
  14 class ViuBaseIE(InfoExtractor):
  15     def _real_initialize(self):
  16         viu_auth_res = self._request_webpage(
  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'
  28             }, headers=self.geo_verification_headers())
  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
  44
  45
  46 class ViuIE(ViuBaseIE):
  47     _VALID_URL = r'(?:viu:|https?://[^/]+\.viu\.com/[a-z]{2}/media/)(?P<id>\d+)'
  48     _TESTS = [{
  49         'url': 'https://www.viu.com/en/media/1116705532?containerId=playlist-22168059',
  50         'info_dict': {
  51             'id': '1116705532',
  52             'ext': 'mp4',
  53             'title': 'Citizen Khan - Ep 1',
  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         'url': 'https://india.viu.com/en/media/1126286865',
  74         'only_matching': True,
  75     }]
  76
  77     def _real_extract(self, url):
  78         video_id = self._match_id(url)
  79
  80         video_data = self._call_api(
  81             'clip/load', video_id, 'Downloading video data', query={
  82                 'appid': 'viu_desktop',
  83                 'fmt': 'json',
  84                 'id': video_id
  85             })['item'][0]
  86
  87         title = video_data['title']
  88
  89         m3u8_url = None
  90         url_path = video_data.get('urlpathd') or video_data.get('urlpath')
  91         tdirforwhole = video_data.get('tdirforwhole')
  92         # #EXT-X-BYTERANGE is not supported by native hls downloader
  93         # and ffmpeg (#10955)
  94         # hls_file = video_data.get('hlsfile')
  95         hls_file = video_data.get('jwhlsfile')
  96         if url_path and tdirforwhole and hls_file:
  97             m3u8_url = '%s/%s/%s' % (url_path, tdirforwhole, hls_file)
  98         else:
  99             # m3u8_url = re.sub(
 100             #     r'(/hlsc_)[a-z]+(\d+\.m3u8)',
 101             #     r'\1whe\2', video_data['href'])
 102             m3u8_url = video_data['href']
 103         formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
 104         self._sort_formats(formats)
 105
 106         subtitles = {}
 107         for key, value in video_data.items():
 108             mobj = re.match(r'^subtitle_(?P<lang>[^_]+)_(?P<ext>(vtt|srt))', key)
 109             if not mobj:
 110                 continue
 111             subtitles.setdefault(mobj.group('lang'), []).append({
 112                 'url': value,
 113                 'ext': mobj.group('ext')
 114             })
 115
 116         return {
 117             'id': video_id,
 118             'title': title,
 119             'description': video_data.get('description'),
 120             'series': video_data.get('moviealbumshowname'),
 121             'episode': title,
 122             'episode_number': int_or_none(video_data.get('episodeno')),
 123             'duration': int_or_none(video_data.get('duration')),
 124             'formats': formats,
 125             'subtitles': subtitles,
 126         }
 127
 128
 129 class ViuPlaylistIE(ViuBaseIE):
 130     IE_NAME = 'viu:playlist'
 131     _VALID_URL = r'https?://www\.viu\.com/[^/]+/listing/playlist-(?P<id>\d+)'
 132     _TEST = {
 133         'url': 'https://www.viu.com/en/listing/playlist-22461380',
 134         'info_dict': {
 135             'id': '22461380',
 136             'title': 'The Good Wife',
 137         },
 138         'playlist_count': 16,
 139         'skip': 'Geo-restricted to Indonesia',
 140     }
 141
 142     def _real_extract(self, url):
 143         playlist_id = self._match_id(url)
 144         playlist_data = self._call_api(
 145             'container/load', playlist_id,
 146             'Downloading playlist info', query={
 147                 'appid': 'viu_desktop',
 148                 'fmt': 'json',
 149                 'id': 'playlist-' + playlist_id
 150             })['container']
 151
 152         entries = []
 153         for item in playlist_data.get('item', []):
 154             item_id = item.get('id')
 155             if not item_id:
 156                 continue
 157             item_id = compat_str(item_id)
 158             entries.append(self.url_result(
 159                 'viu:' + item_id, 'Viu', item_id))
 160
 161         return self.playlist_result(
 162             entries, playlist_id, playlist_data.get('title'))
 163
 164
 165 class ViuOTTIE(InfoExtractor):
 166     IE_NAME = 'viu:ott'
 167     _VALID_URL = r'https?://(?:www\.)?viu\.com/ott/(?P<country_code>[a-z]{2})/[a-z]{2}-[a-z]{2}/vod/(?P<id>\d+)'
 168     _TESTS = [{
 169         'url': 'http://www.viu.com/ott/sg/en-us/vod/3421/The%20Prime%20Minister%20and%20I',
 170         'info_dict': {
 171             'id': '3421',
 172             'ext': 'mp4',
 173             'title': 'A New Beginning',
 174             'description': 'md5:1e7486a619b6399b25ba6a41c0fe5b2c',
 175         },
 176         'params': {
 177             'skip_download': 'm3u8 download',
 178         },
 179         'skip': 'Geo-restricted to Singapore',
 180     }, {
 181         'url': 'http://www.viu.com/ott/hk/zh-hk/vod/7123/%E5%A4%A7%E4%BA%BA%E5%A5%B3%E5%AD%90',
 182         'info_dict': {
 183             'id': '7123',
 184             'ext': 'mp4',
 185             'title': '這就是我的生活之道',
 186             'description': 'md5:4eb0d8b08cf04fcdc6bbbeb16043434f',
 187         },
 188         'params': {
 189             'skip_download': 'm3u8 download',
 190         },
 191         'skip': 'Geo-restricted to Hong Kong',
 192     }]
 193
 194     def _real_extract(self, url):
 195         country_code, video_id = re.match(self._VALID_URL, url).groups()
 196
 197         product_data = self._download_json(
 198             'http://www.viu.com/ott/%s/index.php' % country_code, video_id,
 199             'Downloading video info', query={
 200                 'r': 'vod/ajax-detail',
 201                 'platform_flag_label': 'web',
 202                 'product_id': video_id,
 203             })['data']
 204
 205         video_data = product_data.get('current_product')
 206         if not video_data:
 207             raise ExtractorError('This video is not available in your region.', expected=True)
 208
 209         stream_data = self._download_json(
 210             'https://d1k2us671qcoau.cloudfront.net/distribute_web_%s.php' % country_code,
 211             video_id, 'Downloading stream info', query={
 212                 'ccs_product_id': video_data['ccs_product_id'],
 213             })['data']['stream']
 214
 215         stream_sizes = stream_data.get('size', {})
 216         formats = []
 217         for vid_format, stream_url in stream_data.get('url', {}).items():
 218             height = int_or_none(self._search_regex(
 219                 r's(\d+)p', vid_format, 'height', default=None))
 220             formats.append({
 221                 'format_id': vid_format,
 222                 'url': stream_url,
 223                 'height': height,
 224                 'ext': 'mp4',
 225                 'filesize': int_or_none(stream_sizes.get(vid_format))
 226             })
 227         self._sort_formats(formats)
 228
 229         subtitles = {}
 230         for sub in video_data.get('subtitle', []):
 231             sub_url = sub.get('url')
 232             if not sub_url:
 233                 continue
 234             subtitles.setdefault(sub.get('name'), []).append({
 235                 'url': sub_url,
 236                 'ext': 'srt',
 237             })
 238
 239         title = video_data['synopsis'].strip()
 240
 241         return {
 242             'id': video_id,
 243             'title': title,
 244             'description': video_data.get('description'),
 245             'series': product_data.get('series', {}).get('name'),
 246             'episode': title,
 247             'episode_number': int_or_none(video_data.get('number')),
 248             'duration': int_or_none(stream_data.get('duration')),
 249             'thumbnail': video_data.get('cover_image_url'),
 250             'formats': formats,
 251             'subtitles': subtitles,
 252         }