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