_ Git - youtube-dl/blob - youtube_dl/extractor/togglesg.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     int_or_none,
  12     parse_iso8601,
  13     sanitized_Request,
  14 )
  15
  16
  17 class ToggleSgIE(InfoExtractor):
  18     IE_NAME = 'togglesg'
  19     _VALID_URL = r'https?://video\.toggle\.sg/(?:en|zh)/(?:series|clips|movies)/.+?/(?P<id>[0-9]+)'
  20     _TESTS = [{
  21         'url': 'http://video.toggle.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
  22         'info_dict': {
  23             'id': '343115',
  24             'ext': 'mp4',
  25             'title': 'Lion Moms Premiere',
  26             'description': 'md5:aea1149404bff4d7f7b6da11fafd8e6b',
  27             'upload_date': '20150910',
  28             'timestamp': 1441858274,
  29         },
  30         'params': {
  31             'skip_download': 'm3u8 download',
  32         }
  33     }, {
  34         'note': 'DRM-protected video',
  35         'url': 'http://video.toggle.sg/en/movies/dug-s-special-mission/341413',
  36         'info_dict': {
  37             'id': '341413',
  38             'ext': 'wvm',
  39             'title': 'Dug\'s Special Mission',
  40             'description': 'md5:e86c6f4458214905c1772398fabc93e0',
  41             'upload_date': '20150827',
  42             'timestamp': 1440644006,
  43         },
  44         'params': {
  45             'skip_download': 'DRM-protected wvm download',
  46         }
  47     }, {
  48         'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
  49         'url': 'http://video.toggle.sg/en/series/28th-sea-games-5-show/ep11/332861',
  50         'info_dict': {
  51             'id': '332861',
  52             'ext': 'mp4',
  53             'title': '28th SEA Games (5 Show) -  Episode  11',
  54             'description': 'md5:3cd4f5f56c7c3b1340c50a863f896faa',
  55             'upload_date': '20150605',
  56             'timestamp': 1433480166,
  57         },
  58         'params': {
  59             'skip_download': 'DRM-protected wvm download',
  60         },
  61         'skip': 'm3u8 links are geo-restricted'
  62     }, {
  63         'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
  64         'only_matching': True,
  65     }, {
  66         'url': 'http://video.toggle.sg/zh/series/zero-calling-s2-hd/ep13/336367',
  67         'only_matching': True,
  68     }, {
  69         'url': 'http://video.toggle.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
  70         'only_matching': True,
  71     }, {
  72         'url': 'http://video.toggle.sg/en/movies/seven-days/321936',
  73         'only_matching': True,
  74     }]
  75
  76     _FORMAT_PREFERENCES = {
  77         'wvm-STBMain': -10,
  78         'wvm-iPadMain': -20,
  79         'wvm-iPhoneMain': -30,
  80         'wvm-Android': -40,
  81     }
  82     _API_USER = 'tvpapi_147'
  83     _API_PASS = '11111'
  84
  85     def _real_extract(self, url):
  86         video_id = self._match_id(url)
  87
  88         webpage = self._download_webpage(
  89             url, video_id, note='Downloading video page')
  90
  91         api_user = self._search_regex(
  92             r'apiUser\s*:\s*(["\'])(?P<user>.+?)\1', webpage, 'apiUser',
  93             default=self._API_USER, group='user')
  94         api_pass = self._search_regex(
  95             r'apiPass\s*:\s*(["\'])(?P<pass>.+?)\1', webpage, 'apiPass',
  96             default=self._API_PASS, group='pass')
  97
  98         params = {
  99             'initObj': {
 100                 'Locale': {
 101                     'LocaleLanguage': '',
 102                     'LocaleCountry': '',
 103                     'LocaleDevice': '',
 104                     'LocaleUserState': 0
 105                 },
 106                 'Platform': 0,
 107                 'SiteGuid': 0,
 108                 'DomainID': '0',
 109                 'UDID': '',
 110                 'ApiUser': api_user,
 111                 'ApiPass': api_pass
 112             },
 113             'MediaID': video_id,
 114             'mediaType': 0,
 115         }
 116
 117         req = sanitized_Request(
 118             'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo',
 119             json.dumps(params).encode('utf-8'))
 120         info = self._download_json(req, video_id, 'Downloading video info json')
 121
 122         title = info['MediaName']
 123
 124         formats = []
 125         for video_file in info.get('Files', []):
 126             ext = determine_ext(video_file['URL'])
 127             vid_format = video_file['Format'].replace(' ', '')
 128             # if geo-restricted, m3u8 is inaccessible, but mp4 is okay
 129             if ext == 'm3u8':
 130                 m3u8_formats = self._extract_m3u8_formats(
 131                     video_file['URL'], video_id, ext='mp4', m3u8_id=vid_format,
 132                     note='Downloading %s m3u8 information' % vid_format,
 133                     errnote='Failed to download %s m3u8 information' % vid_format,
 134                     fatal=False)
 135                 if m3u8_formats:
 136                     formats.extend(m3u8_formats)
 137             elif ext in ('mp4', 'wvm'):
 138                 # wvm are drm-protected files
 139                 formats.append({
 140                     'ext': ext,
 141                     'url': video_file['URL'],
 142                     'format_id': vid_format,
 143                     'preference': self._FORMAT_PREFERENCES.get(ext + '-' + vid_format) or -1,
 144                     'format_note': 'DRM-protected video' if ext == 'wvm' else None
 145                 })
 146         if not formats:
 147             # Most likely because geo-blocked
 148             raise ExtractorError('No downloadable videos found', expected=True)
 149         self._sort_formats(formats)
 150
 151         duration = int_or_none(info.get('Duration'))
 152         description = info.get('Description')
 153         created_at = parse_iso8601(info.get('CreationDate') or None)
 154
 155         thumbnails = []
 156         for picture in info.get('Pictures', []):
 157             if not isinstance(picture, dict):
 158                 continue
 159             pic_url = picture.get('URL')
 160             if not pic_url:
 161                 continue
 162             thumbnail = {
 163                 'url': pic_url,
 164             }
 165             pic_size = picture.get('PicSize', '')
 166             m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size)
 167             if m:
 168                 thumbnail.update({
 169                     'width': int(m.group('width')),
 170                     'height': int(m.group('height')),
 171                 })
 172             thumbnails.append(thumbnail)
 173
 174         return {
 175             'id': video_id,
 176             'title': title,
 177             'description': description,
 178             'duration': duration,
 179             'timestamp': created_at,
 180             'thumbnails': thumbnails,
 181             'formats': formats,
 182         }