yt_dlp/extractor/toggle.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     determine_ext,
  10     float_or_none,
  11     int_or_none,
  12     parse_iso8601,
  13     strip_or_none,
  14 )
  15
  16
  17 class ToggleIE(InfoExtractor):
  18     IE_NAME = 'toggle'
  19     _VALID_URL = r'(?:https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}|toggle:)(?P<id>[0-9]+)'
  20     _TESTS = [{
  21         'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
  22         'info_dict': {
  23             'id': '343115',
  24             'ext': 'mp4',
  25             'title': 'Lion Moms Premiere',
  26             'description': 'md5:aea1149404bff4d7f7b6da11fafd8e6b',
  27             'upload_date': '20150910',
  28             'timestamp': 1441858274,
  29         },
  30         'params': {
  31             'skip_download': 'm3u8 download',
  32         }
  33     }, {
  34         'note': 'DRM-protected video',
  35         'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413',
  36         'info_dict': {
  37             'id': '341413',
  38             'ext': 'wvm',
  39             'title': 'Dug\'s Special Mission',
  40             'description': 'md5:e86c6f4458214905c1772398fabc93e0',
  41             'upload_date': '20150827',
  42             'timestamp': 1440644006,
  43         },
  44         'params': {
  45             'skip_download': 'DRM-protected wvm download',
  46         }
  47     }, {
  48         # this also tests correct video id extraction
  49         'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
  50         'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
  51         'info_dict': {
  52             'id': '332861',
  53             'ext': 'mp4',
  54             'title': '28th SEA Games (5 Show) -  Episode  11',
  55             'description': 'md5:3cd4f5f56c7c3b1340c50a863f896faa',
  56             'upload_date': '20150605',
  57             'timestamp': 1433480166,
  58         },
  59         'params': {
  60             'skip_download': 'DRM-protected wvm download',
  61         },
  62         'skip': 'm3u8 links are geo-restricted'
  63     }, {
  64         'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
  65         'only_matching': True,
  66     }, {
  67         'url': 'http://www.mewatch.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
  68         'only_matching': True,
  69     }, {
  70         'url': 'http://www.mewatch.sg/zh/series/zero-calling-s2-hd/ep13/336367',
  71         'only_matching': True,
  72     }, {
  73         'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
  74         'only_matching': True,
  75     }, {
  76         'url': 'http://www.mewatch.sg/en/movies/seven-days/321936',
  77         'only_matching': True,
  78     }, {
  79         'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
  80         'only_matching': True,
  81     }, {
  82         'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585',
  83         'only_matching': True,
  84     }]
  85
  86     _API_USER = 'tvpapi_147'
  87     _API_PASS = '11111'
  88
  89     def _real_extract(self, url):
  90         video_id = self._match_id(url)
  91
  92         params = {
  93             'initObj': {
  94                 'Locale': {
  95                     'LocaleLanguage': '',
  96                     'LocaleCountry': '',
  97                     'LocaleDevice': '',
  98                     'LocaleUserState': 0
  99                 },
 100                 'Platform': 0,
 101                 'SiteGuid': 0,
 102                 'DomainID': '0',
 103                 'UDID': '',
 104                 'ApiUser': self._API_USER,
 105                 'ApiPass': self._API_PASS
 106             },
 107             'MediaID': video_id,
 108             'mediaType': 0,
 109         }
 110
 111         info = self._download_json(
 112             'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo',
 113             video_id, 'Downloading video info json', data=json.dumps(params).encode('utf-8'))
 114
 115         title = info['MediaName']
 116
 117         formats = []
 118         for video_file in info.get('Files', []):
 119             video_url, vid_format = video_file.get('URL'), video_file.get('Format')
 120             if not video_url or video_url == 'NA' or not vid_format:
 121                 continue
 122             ext = determine_ext(video_url)
 123             vid_format = vid_format.replace(' ', '')
 124             # if geo-restricted, m3u8 is inaccessible, but mp4 is okay
 125             if ext == 'm3u8':
 126                 m3u8_formats = self._extract_m3u8_formats(
 127                     video_url, video_id, ext='mp4', m3u8_id=vid_format,
 128                     note='Downloading %s m3u8 information' % vid_format,
 129                     errnote='Failed to download %s m3u8 information' % vid_format,
 130                     fatal=False)
 131                 for f in m3u8_formats:
 132                     # Apple FairPlay Streaming
 133                     if '/fpshls/' in f['url']:
 134                         continue
 135                     formats.append(f)
 136             elif ext == 'mpd':
 137                 formats.extend(self._extract_mpd_formats(
 138                     video_url, video_id, mpd_id=vid_format,
 139                     note='Downloading %s MPD manifest' % vid_format,
 140                     errnote='Failed to download %s MPD manifest' % vid_format,
 141                     fatal=False))
 142             elif ext == 'ism':
 143                 formats.extend(self._extract_ism_formats(
 144                     video_url, video_id, ism_id=vid_format,
 145                     note='Downloading %s ISM manifest' % vid_format,
 146                     errnote='Failed to download %s ISM manifest' % vid_format,
 147                     fatal=False))
 148             elif ext == 'mp4':
 149                 formats.append({
 150                     'ext': ext,
 151                     'url': video_url,
 152                     'format_id': vid_format,
 153                 })
 154         if not formats:
 155             for meta in (info.get('Metas') or []):
 156                 if (not self.get_param('allow_unplayable_formats')
 157                         and meta.get('Key') == 'Encryption' and meta.get('Value') == '1'):
 158                     self.report_drm(video_id)
 159             # Most likely because geo-blocked if no formats and no DRM
 160         self._sort_formats(formats)
 161
 162         thumbnails = []
 163         for picture in info.get('Pictures', []):
 164             if not isinstance(picture, dict):
 165                 continue
 166             pic_url = picture.get('URL')
 167             if not pic_url:
 168                 continue
 169             thumbnail = {
 170                 'url': pic_url,
 171             }
 172             pic_size = picture.get('PicSize', '')
 173             m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size)
 174             if m:
 175                 thumbnail.update({
 176                     'width': int(m.group('width')),
 177                     'height': int(m.group('height')),
 178                 })
 179             thumbnails.append(thumbnail)
 180
 181         def counter(prefix):
 182             return int_or_none(
 183                 info.get(prefix + 'Counter') or info.get(prefix.lower() + '_counter'))
 184
 185         return {
 186             'id': video_id,
 187             'title': title,
 188             'description': strip_or_none(info.get('Description')),
 189             'duration': int_or_none(info.get('Duration')),
 190             'timestamp': parse_iso8601(info.get('CreationDate') or None),
 191             'average_rating': float_or_none(info.get('Rating')),
 192             'view_count': counter('View'),
 193             'like_count': counter('Like'),
 194             'thumbnails': thumbnails,
 195             'formats': formats,
 196         }
 197
 198
 199 class MeWatchIE(InfoExtractor):
 200     IE_NAME = 'mewatch'
 201     _VALID_URL = r'https?://(?:(?:www|live)\.)?mewatch\.sg/watch/[^/?#&]+-(?P<id>[0-9]+)'
 202     _TESTS = [{
 203         'url': 'https://www.mewatch.sg/watch/Recipe-Of-Life-E1-179371',
 204         'info_dict': {
 205             'id': '1008625',
 206             'ext': 'mp4',
 207             'title': 'Recipe Of Life 味之道',
 208             'timestamp': 1603306526,
 209             'description': 'md5:6e88cde8af2068444fc8e1bc3ebf257c',
 210             'upload_date': '20201021',
 211         },
 212         'params': {
 213             'skip_download': 'm3u8 download',
 214         },
 215     }, {
 216         'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-搜密。打卡。小红点-S2-E1-176232',
 217         'only_matching': True,
 218     }, {
 219         'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-%E6%90%9C%E5%AF%86%E3%80%82%E6%89%93%E5%8D%A1%E3%80%82%E5%B0%8F%E7%BA%A2%E7%82%B9-S2-E1-176232',
 220         'only_matching': True,
 221     }, {
 222         'url': 'https://live.mewatch.sg/watch/Recipe-Of-Life-E41-189759',
 223         'only_matching': True,
 224     }]
 225
 226     def _real_extract(self, url):
 227         item_id = self._match_id(url)
 228         custom_id = self._download_json(
 229             'https://cdn.mewatch.sg/api/items/' + item_id,
 230             item_id, query={'segments': 'all'})['customId']
 231         return self.url_result(
 232             'toggle:' + custom_id, ToggleIE.ie_key(), custom_id)