Raphaël G. Git Repositories - youtubedl/blob - 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?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}(?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     _FORMAT_PREFERENCES = {
  88         'wvm-STBMain': -10,
  89         'wvm-iPadMain': -20,
  90         'wvm-iPhoneMain': -30,
  91         'wvm-Android': -40,
  92     }
  93     _API_USER = 'tvpapi_147'
  94     _API_PASS = '11111'
  95
  96     def _real_extract(self, url):
  97         video_id = self._match_id(url)
  98
  99         webpage = self._download_webpage(
 100             url, video_id, note='Downloading video page')
 101
 102         api_user = self._search_regex(
 103             r'apiUser\s*:\s*(["\'])(?P<user>.+?)\1', webpage, 'apiUser',
 104             default=self._API_USER, group='user')
 105         api_pass = self._search_regex(
 106             r'apiPass\s*:\s*(["\'])(?P<pass>.+?)\1', webpage, 'apiPass',
 107             default=self._API_PASS, group='pass')
 108
 109         params = {
 110             'initObj': {
 111                 'Locale': {
 112                     'LocaleLanguage': '',
 113                     'LocaleCountry': '',
 114                     'LocaleDevice': '',
 115                     'LocaleUserState': 0
 116                 },
 117                 'Platform': 0,
 118                 'SiteGuid': 0,
 119                 'DomainID': '0',
 120                 'UDID': '',
 121                 'ApiUser': api_user,
 122                 'ApiPass': api_pass
 123             },
 124             'MediaID': video_id,
 125             'mediaType': 0,
 126         }
 127
 128         req = sanitized_Request(
 129             'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo',
 130             json.dumps(params).encode('utf-8'))
 131         info = self._download_json(req, video_id, 'Downloading video info json')
 132
 133         title = info['MediaName']
 134
 135         formats = []
 136         for video_file in info.get('Files', []):
 137             video_url, vid_format = video_file.get('URL'), video_file.get('Format')
 138             if not video_url or video_url == 'NA' or not vid_format:
 139                 continue
 140             ext = determine_ext(video_url)
 141             vid_format = vid_format.replace(' ', '')
 142             # if geo-restricted, m3u8 is inaccessible, but mp4 is okay
 143             if ext == 'm3u8':
 144                 formats.extend(self._extract_m3u8_formats(
 145                     video_url, video_id, ext='mp4', m3u8_id=vid_format,
 146                     note='Downloading %s m3u8 information' % vid_format,
 147                     errnote='Failed to download %s m3u8 information' % vid_format,
 148                     fatal=False))
 149             elif ext == 'mpd':
 150                 formats.extend(self._extract_mpd_formats(
 151                     video_url, video_id, mpd_id=vid_format,
 152                     note='Downloading %s MPD manifest' % vid_format,
 153                     errnote='Failed to download %s MPD manifest' % vid_format,
 154                     fatal=False))
 155             elif ext == 'ism':
 156                 formats.extend(self._extract_ism_formats(
 157                     video_url, video_id, ism_id=vid_format,
 158                     note='Downloading %s ISM manifest' % vid_format,
 159                     errnote='Failed to download %s ISM manifest' % vid_format,
 160                     fatal=False))
 161             elif ext in ('mp4', 'wvm'):
 162                 # wvm are drm-protected files
 163                 formats.append({
 164                     'ext': ext,
 165                     'url': video_url,
 166                     'format_id': vid_format,
 167                     'preference': self._FORMAT_PREFERENCES.get(ext + '-' + vid_format) or -1,
 168                     'format_note': 'DRM-protected video' if ext == 'wvm' else None
 169                 })
 170         if not formats:
 171             # Most likely because geo-blocked
 172             raise ExtractorError('No downloadable videos found', expected=True)
 173         self._sort_formats(formats)
 174
 175         duration = int_or_none(info.get('Duration'))
 176         description = info.get('Description')
 177         created_at = parse_iso8601(info.get('CreationDate') or None)
 178
 179         average_rating = float_or_none(info.get('Rating'))
 180         view_count = int_or_none(info.get('ViewCounter') or info.get('view_counter'))
 181         like_count = int_or_none(info.get('LikeCounter') or info.get('like_counter'))
 182
 183         thumbnails = []
 184         for picture in info.get('Pictures', []):
 185             if not isinstance(picture, dict):
 186                 continue
 187             pic_url = picture.get('URL')
 188             if not pic_url:
 189                 continue
 190             thumbnail = {
 191                 'url': pic_url,
 192             }
 193             pic_size = picture.get('PicSize', '')
 194             m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size)
 195             if m:
 196                 thumbnail.update({
 197                     'width': int(m.group('width')),
 198                     'height': int(m.group('height')),
 199                 })
 200             thumbnails.append(thumbnail)
 201
 202         return {
 203             'id': video_id,
 204             'title': title,
 205             'description': description,
 206             'duration': duration,
 207             'timestamp': created_at,
 208             'average_rating': average_rating,
 209             'view_count': view_count,
 210             'like_count': like_count,
 211             'thumbnails': thumbnails,
 212             'formats': formats,
 213         }