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