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)/(?:series|clips|movies)/(?:[^/]+/)+(?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
  78     _FORMAT_PREFERENCES = {
  79         'wvm-STBMain': -10,
  80         'wvm-iPadMain': -20,
  81         'wvm-iPhoneMain': -30,
  82         'wvm-Android': -40,
  83     }
  84     _API_USER = 'tvpapi_147'
  85     _API_PASS = '11111'
  86
  87     def _real_extract(self, url):
  88         video_id = self._match_id(url)
  89
  90         webpage = self._download_webpage(
  91             url, video_id, note='Downloading video page')
  92
  93         api_user = self._search_regex(
  94             r'apiUser\s*:\s*(["\'])(?P<user>.+?)\1', webpage, 'apiUser',
  95             default=self._API_USER, group='user')
  96         api_pass = self._search_regex(
  97             r'apiPass\s*:\s*(["\'])(?P<pass>.+?)\1', webpage, 'apiPass',
  98             default=self._API_PASS, group='pass')
  99
 100         params = {
 101             'initObj': {
 102                 'Locale': {
 103                     'LocaleLanguage': '',
 104                     'LocaleCountry': '',
 105                     'LocaleDevice': '',
 106                     'LocaleUserState': 0
 107                 },
 108                 'Platform': 0,
 109                 'SiteGuid': 0,
 110                 'DomainID': '0',
 111                 'UDID': '',
 112                 'ApiUser': api_user,
 113                 'ApiPass': api_pass
 114             },
 115             'MediaID': video_id,
 116             'mediaType': 0,
 117         }
 118
 119         req = sanitized_Request(
 120             'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo',
 121             json.dumps(params).encode('utf-8'))
 122         info = self._download_json(req, video_id, 'Downloading video info json')
 123
 124         title = info['MediaName']
 125
 126         formats = []
 127         for video_file in info.get('Files', []):
 128             video_url, vid_format = video_file.get('URL'), video_file.get('Format')
 129             if not video_url or not vid_format:
 130                 continue
 131             ext = determine_ext(video_url)
 132             vid_format = vid_format.replace(' ', '')
 133             # if geo-restricted, m3u8 is inaccessible, but mp4 is okay
 134             if ext == 'm3u8':
 135                 formats.extend(self._extract_m3u8_formats(
 136                     video_url, video_id, ext='mp4', m3u8_id=vid_format,
 137                     note='Downloading %s m3u8 information' % vid_format,
 138                     errnote='Failed to download %s m3u8 information' % vid_format,
 139                     fatal=False))
 140             elif ext in ('mp4', 'wvm'):
 141                 # wvm are drm-protected files
 142                 formats.append({
 143                     'ext': ext,
 144                     'url': video_url,
 145                     'format_id': vid_format,
 146                     'preference': self._FORMAT_PREFERENCES.get(ext + '-' + vid_format) or -1,
 147                     'format_note': 'DRM-protected video' if ext == 'wvm' else None
 148                 })
 149         if not formats:
 150             # Most likely because geo-blocked
 151             raise ExtractorError('No downloadable videos found', expected=True)
 152         self._sort_formats(formats)
 153
 154         duration = int_or_none(info.get('Duration'))
 155         description = info.get('Description')
 156         created_at = parse_iso8601(info.get('CreationDate') or None)
 157
 158         average_rating = float_or_none(info.get('Rating'))
 159         view_count = int_or_none(info.get('ViewCounter') or info.get('view_counter'))
 160         like_count = int_or_none(info.get('LikeCounter') or info.get('like_counter'))
 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         return {
 182             'id': video_id,
 183             'title': title,
 184             'description': description,
 185             'duration': duration,
 186             'timestamp': created_at,
 187             'average_rating': average_rating,
 188             'view_count': view_count,
 189             'like_count': like_count,
 190             'thumbnails': thumbnails,
 191             'formats': formats,
 192         }