yt_dlp/extractor/toggle.py

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