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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     determine_ext,
   6     clean_html,
   7     int_or_none,
   8     float_or_none,
   9 )
  10
  11
  12 def _decrypt_config(key, string):
  13     a = ''
  14     i = ''
  15     r = ''
  16
  17     while len(a) < (len(string) / 2):
  18         a += key
  19
  20     a = a[0:int(len(string) / 2)]
  21
  22     t = 0
  23     while t < len(string):
  24         i += chr(int(string[t] + string[t + 1], 16))
  25         t += 2
  26
  27     icko = [s for s in i]
  28
  29     for t, c in enumerate(a):
  30         r += chr(ord(c) ^ ord(icko[t]))
  31
  32     return r
  33
  34
  35 class EscapistIE(InfoExtractor):
  36     _VALID_URL = r'https?://?(?:(?:www|v1)\.)?escapistmagazine\.com/videos/view/[^/]+/(?P<id>[0-9]+)'
  37     _TESTS = [{
  38         'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
  39         'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
  40         'info_dict': {
  41             'id': '6618',
  42             'ext': 'mp4',
  43             '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.",
  44             'title': "Breaking Down Baldur's Gate",
  45             'thumbnail': r're:^https?://.*\.jpg$',
  46             'duration': 264,
  47             'uploader': 'The Escapist',
  48         }
  49     }, {
  50         'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer',
  51         'md5': '9e8c437b0dbb0387d3bd3255ca77f6bf',
  52         'info_dict': {
  53             'id': '10044',
  54             'ext': 'mp4',
  55             'description': 'This week, Zero Punctuation reviews Evolve.',
  56             'title': 'Evolve - One vs Multiplayer',
  57             'thumbnail': r're:^https?://.*\.jpg$',
  58             'duration': 304,
  59             'uploader': 'The Escapist',
  60         }
  61     }, {
  62         'url': 'http://escapistmagazine.com/videos/view/the-escapist-presents/6618',
  63         'only_matching': True,
  64     }, {
  65         'url': 'https://v1.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
  66         'only_matching': True,
  67     }]
  68
  69     def _real_extract(self, url):
  70         video_id = self._match_id(url)
  71         webpage = self._download_webpage(url, video_id)
  72
  73         ims_video = self._parse_json(
  74             self._search_regex(
  75                 r'imsVideo\.play\(({.+?})\);', webpage, 'imsVideo'),
  76             video_id)
  77         video_id = ims_video['videoID']
  78         key = ims_video['hash']
  79
  80         config = self._download_webpage(
  81             'http://www.escapistmagazine.com/videos/vidconfig.php',
  82             video_id, 'Downloading video config', headers={
  83                 'Referer': url,
  84             }, query={
  85                 'videoID': video_id,
  86                 'hash': key,
  87             })
  88
  89         data = self._parse_json(_decrypt_config(key, config), video_id)
  90
  91         video_data = data['videoData']
  92
  93         title = clean_html(video_data['title'])
  94
  95         formats = [{
  96             'url': video['src'],
  97             'format_id': '%s-%sp' % (determine_ext(video['src']), video['res']),
  98             'height': int_or_none(video.get('res')),
  99         } for video in data['files']['videos']]
 100         self._sort_formats(formats)
 101
 102         return {
 103             'id': video_id,
 104             'formats': formats,
 105             'title': title,
 106             'thumbnail': self._og_search_thumbnail(webpage) or data.get('poster'),
 107             'description': self._og_search_description(webpage),
 108             'duration': float_or_none(video_data.get('duration'), 1000),
 109             'uploader': video_data.get('publisher'),
 110             'series': video_data.get('show'),
 111         }