Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/internetvideoarchive.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_parse_qs,
   9     compat_urlparse,
  10 )
  11
  12
  13 class InternetVideoArchiveIE(InfoExtractor):
  14     _VALID_URL = r'https?://video\.internetvideoarchive\.net/(?:player|flash/players)/.*?\?.*?publishedid.*?'
  15
  16     _TEST = {
  17         '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',
  18         'info_dict': {
  19             'id': '194487',
  20             'ext': 'mp4',
  21             'title': 'Kick-Ass 2',
  22             'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a',
  23         },
  24         'params': {
  25             # m3u8 download
  26             'skip_download': True,
  27         },
  28     }
  29
  30     @staticmethod
  31     def _build_json_url(query):
  32         return 'http://video.internetvideoarchive.net/player/6/configuration.ashx?' + query
  33
  34     def _real_extract(self, url):
  35         query = compat_parse_qs(compat_urlparse.urlparse(url).query)
  36         video_id = query['publishedid'][0]
  37         data = self._download_json(
  38             'https://video.internetvideoarchive.net/videojs7/videojs7.ivasettings.ashx',
  39             video_id, data=json.dumps({
  40                 'customerid': query['customerid'][0],
  41                 'publishedid': video_id,
  42             }).encode())
  43         title = data['Title']
  44         formats = self._extract_m3u8_formats(
  45             data['VideoUrl'], video_id, 'mp4',
  46             'm3u8_native', m3u8_id='hls', fatal=False)
  47         file_url = formats[0]['url']
  48         if '.ism/' in file_url:
  49             replace_url = lambda x: re.sub(r'\.ism/[^?]+', '.ism/' + x, file_url)
  50             formats.extend(self._extract_f4m_formats(
  51                 replace_url('.f4m'), video_id, f4m_id='hds', fatal=False))
  52             formats.extend(self._extract_mpd_formats(
  53                 replace_url('.mpd'), video_id, mpd_id='dash', fatal=False))
  54             formats.extend(self._extract_ism_formats(
  55                 replace_url('Manifest'), video_id, ism_id='mss', fatal=False))
  56         self._sort_formats(formats)
  57
  58         return {
  59             'id': video_id,
  60             'title': title,
  61             'formats': formats,
  62             'thumbnail': data.get('PosterUrl'),
  63             'description': data.get('Description'),
  64         }