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