_ Git - youtube-dl/blob - youtube_dl/extractor/escapist.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     determine_ext,
   8     clean_html,
   9     int_or_none,
  10     float_or_none,
  11     sanitized_Request,
  12 )
  13
  14
  15 def _decrypt_config(key, string):
  16     a = ''
  17     i = ''
  18     r = ''
  19
  20     while len(a) < (len(string) / 2):
  21         a += key
  22
  23     a = a[0:int(len(string) / 2)]
  24
  25     t = 0
  26     while t < len(string):
  27         i += chr(int(string[t] + string[t + 1], 16))
  28         t += 2
  29
  30     icko = [s for s in i]
  31
  32     for t, c in enumerate(a):
  33         r += chr(ord(c) ^ ord(icko[t]))
  34
  35     return r
  36
  37
  38 class EscapistIE(InfoExtractor):
  39     _VALID_URL = r'https?://?(?:www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
  40     _TESTS = [{
  41         'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
  42         'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
  43         'info_dict': {
  44             'id': '6618',
  45             'ext': 'mp4',
  46             'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
  47             'title': "Breaking Down Baldur's Gate",
  48             'thumbnail': 're:^https?://.*\.jpg$',
  49             'duration': 264,
  50             'uploader': 'The Escapist',
  51         }
  52     }, {
  53         'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer',
  54         'md5': '9e8c437b0dbb0387d3bd3255ca77f6bf',
  55         'info_dict': {
  56             'id': '10044',
  57             'ext': 'mp4',
  58             'description': 'This week, Zero Punctuation reviews Evolve.',
  59             'title': 'Evolve - One vs Multiplayer',
  60             'thumbnail': 're:^https?://.*\.jpg$',
  61             'duration': 304,
  62             'uploader': 'The Escapist',
  63         }
  64     }]
  65
  66     def _real_extract(self, url):
  67         video_id = self._match_id(url)
  68         webpage = self._download_webpage(url, video_id)
  69
  70         ims_video = self._parse_json(
  71             self._search_regex(
  72                 r'imsVideo\.play\(({.+?})\);', webpage, 'imsVideo'),
  73             video_id)
  74         video_id = ims_video['videoID']
  75         key = ims_video['hash']
  76
  77         config_req = sanitized_Request(
  78             'http://www.escapistmagazine.com/videos/'
  79             'vidconfig.php?videoID=%s&hash=%s' % (video_id, key))
  80         config_req.add_header('Referer', url)
  81         config = self._download_webpage(config_req, video_id, 'Downloading video config')
  82
  83         data = json.loads(_decrypt_config(key, config))
  84
  85         video_data = data['videoData']
  86
  87         title = clean_html(video_data['title'])
  88         duration = float_or_none(video_data.get('duration'), 1000)
  89         uploader = video_data.get('publisher')
  90
  91         formats = [{
  92             'url': video['src'],
  93             'format_id': '%s-%sp' % (determine_ext(video['src']), video['res']),
  94             'height': int_or_none(video.get('res')),
  95         } for video in data['files']['videos']]
  96         self._sort_formats(formats)
  97
  98         return {
  99             'id': video_id,
 100             'formats': formats,
 101             'title': title,
 102             'thumbnail': self._og_search_thumbnail(webpage),
 103             'description': self._og_search_description(webpage),
 104             'duration': duration,
 105             'uploader': uploader,
 106         }