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     sanitized_Request,
  15 )
  16
  17
  18 class ToggleIE(InfoExtractor):
  19     IE_NAME = 'toggle'
  20     _VALID_URL = r'https?://video\.toggle\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)'
  21     _TESTS = [{
  22         'url': 'http://video.toggle.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://video.toggle.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://video.toggle.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://video.toggle.sg/zh/series/zero-calling-s2-hd/ep13/336367',
  69         'only_matching': True,
  70     }, {
  71         'url': 'http://video.toggle.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
  72         'only_matching': True,
  73     }, {
  74         'url': 'http://video.toggle.sg/en/movies/seven-days/321936',
  75         'only_matching': True,
  76     }, {
  77         'url': 'https://video.toggle.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
  78         'only_matching': True,
  79     }, {
  80         'url': 'http://video.toggle.sg/en/channels/eleven-plus/401585',
  81         'only_matching': True,
  82     }]
  83
  84     _FORMAT_PREFERENCES = {
  85         'wvm-STBMain': -10,
  86         'wvm-iPadMain': -20,
  87         'wvm-iPhoneMain': -30,
  88         'wvm-Android': -40,
  89     }
  90     _API_USER = 'tvpapi_147'
  91     _API_PASS = '11111'
  92
  93     def _real_extract(self, url):
  94         video_id = self._match_id(url)
  95
  96         webpage = self._download_webpage(
  97             url, video_id, note='Downloading video page')
  98
  99         api_user = self._search_regex(
 100             r'apiUser\s*:\s*(["\'])(?P<user>.+?)\1', webpage, 'apiUser',
 101             default=self._API_USER, group='user')
 102         api_pass = self._search_regex(
 103             r'apiPass\s*:\s*(["\'])(?P<pass>.+?)\1', webpage, 'apiPass',
 104             default=self._API_PASS, group='pass')
 105
 106         params = {
 107             'initObj': {
 108                 'Locale': {
 109                     'LocaleLanguage': '',
 110                     'LocaleCountry': '',
 111                     'LocaleDevice': '',
 112                     'LocaleUserState': 0
 113                 },
 114                 'Platform': 0,
 115                 'SiteGuid': 0,
 116                 'DomainID': '0',
 117                 'UDID': '',
 118                 'ApiUser': api_user,
 119                 'ApiPass': api_pass
 120             },
 121             'MediaID': video_id,
 122             'mediaType': 0,
 123         }
 124
 125         req = sanitized_Request(
 126             'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo',
 127             json.dumps(params).encode('utf-8'))
 128         info = self._download_json(req, video_id, 'Downloading video info json')
 129
 130         title = info['MediaName']
 131
 132         formats = []
 133         for video_file in info.get('Files', []):
 134             video_url, vid_format = video_file.get('URL'), video_file.get('Format')
 135             if not video_url or video_url == 'NA' or not vid_format:
 136                 continue
 137             ext = determine_ext(video_url)
 138             vid_format = vid_format.replace(' ', '')
 139             # if geo-restricted, m3u8 is inaccessible, but mp4 is okay
 140             if ext == 'm3u8':
 141                 formats.extend(self._extract_m3u8_formats(
 142                     video_url, video_id, ext='mp4', m3u8_id=vid_format,
 143                     note='Downloading %s m3u8 information' % vid_format,
 144                     errnote='Failed to download %s m3u8 information' % vid_format,
 145                     fatal=False))
 146             elif ext == 'mpd':
 147                 formats.extend(self._extract_mpd_formats(
 148                     video_url, video_id, mpd_id=vid_format,
 149                     note='Downloading %s MPD manifest' % vid_format,
 150                     errnote='Failed to download %s MPD manifest' % vid_format,
 151                     fatal=False))
 152             elif ext == 'ism':
 153                 formats.extend(self._extract_ism_formats(
 154                     video_url, video_id, ism_id=vid_format,
 155                     note='Downloading %s ISM manifest' % vid_format,
 156                     errnote='Failed to download %s ISM manifest' % vid_format,
 157                     fatal=False))
 158             elif ext in ('mp4', 'wvm'):
 159                 # wvm are drm-protected files
 160                 formats.append({
 161                     'ext': ext,
 162                     'url': video_url,
 163                     'format_id': vid_format,
 164                     'preference': self._FORMAT_PREFERENCES.get(ext + '-' + vid_format) or -1,
 165                     'format_note': 'DRM-protected video' if ext == 'wvm' else None
 166                 })
 167         if not formats:
 168             # Most likely because geo-blocked
 169             raise ExtractorError('No downloadable videos found', expected=True)
 170         self._sort_formats(formats)
 171
 172         duration = int_or_none(info.get('Duration'))
 173         description = info.get('Description')
 174         created_at = parse_iso8601(info.get('CreationDate') or None)
 175
 176         average_rating = float_or_none(info.get('Rating'))
 177         view_count = int_or_none(info.get('ViewCounter') or info.get('view_counter'))
 178         like_count = int_or_none(info.get('LikeCounter') or info.get('like_counter'))
 179
 180         thumbnails = []
 181         for picture in info.get('Pictures', []):
 182             if not isinstance(picture, dict):
 183                 continue
 184             pic_url = picture.get('URL')
 185             if not pic_url:
 186                 continue
 187             thumbnail = {
 188                 'url': pic_url,
 189             }
 190             pic_size = picture.get('PicSize', '')
 191             m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size)
 192             if m:
 193                 thumbnail.update({
 194                     'width': int(m.group('width')),
 195                     'height': int(m.group('height')),
 196                 })
 197             thumbnails.append(thumbnail)
 198
 199         return {
 200             'id': video_id,
 201             'title': title,
 202             'description': description,
 203             'duration': duration,
 204             'timestamp': created_at,
 205             'average_rating': average_rating,
 206             'view_count': view_count,
 207             'like_count': like_count,
 208             'thumbnails': thumbnails,
 209             'formats': formats,
 210         }