yt_dlp/extractor/internetvideoarchive.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import parse_qs
   8
   9
  10 class InternetVideoArchiveIE(InfoExtractor):
  11     _VALID_URL = r'https?://video\.internetvideoarchive\.net/(?:player|flash/players)/.*?\?.*?publishedid.*?'
  12
  13     _TEST = {
  14         'url': 'http://video.internetvideoarchive.net/player/6/configuration.ashx?customerid=69249&publishedid=194487&reporttag=vdbetatitle&playerid=641&autolist=0&domain=www.videodetective.com&maxrate=high&minrate=low&socialplayer=false',
  15         'info_dict': {
  16             'id': '194487',
  17             'ext': 'mp4',
  18             'title': 'Kick-Ass 2',
  19             'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a',
  20         },
  21         'params': {
  22             # m3u8 download
  23             'skip_download': True,
  24         },
  25     }
  26
  27     @staticmethod
  28     def _build_json_url(query):
  29         return 'http://video.internetvideoarchive.net/player/6/configuration.ashx?' + query
  30
  31     def _real_extract(self, url):
  32         query = parse_qs(url)
  33         video_id = query['publishedid'][0]
  34         data = self._download_json(
  35             'https://video.internetvideoarchive.net/videojs7/videojs7.ivasettings.ashx',
  36             video_id, data=json.dumps({
  37                 'customerid': query['customerid'][0],
  38                 'publishedid': video_id,
  39             }).encode())
  40         title = data['Title']
  41         formats = self._extract_m3u8_formats(
  42             data['VideoUrl'], video_id, 'mp4',
  43             'm3u8_native', m3u8_id='hls', fatal=False)
  44         file_url = formats[0]['url']
  45         if '.ism/' in file_url:
  46             replace_url = lambda x: re.sub(r'\.ism/[^?]+', '.ism/' + x, file_url)
  47             formats.extend(self._extract_f4m_formats(
  48                 replace_url('.f4m'), video_id, f4m_id='hds', fatal=False))
  49             formats.extend(self._extract_mpd_formats(
  50                 replace_url('.mpd'), video_id, mpd_id='dash', fatal=False))
  51             formats.extend(self._extract_ism_formats(
  52                 replace_url('Manifest'), video_id, ism_id='mss', fatal=False))
  53         self._sort_formats(formats)
  54
  55         return {
  56             'id': video_id,
  57             'title': title,
  58             'formats': formats,
  59             'thumbnail': data.get('PosterUrl'),
  60             'description': data.get('Description'),
  61         }