youtube_dl/extractor/escapist.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_urllib_request
   7
   8 from ..utils import (
   9     determine_ext,
  10     clean_html,
  11     int_or_none,
  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         }
  51     }, {
  52         'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer',
  53         'md5': '9e8c437b0dbb0387d3bd3255ca77f6bf',
  54         'info_dict': {
  55             'id': '10044',
  56             'ext': 'mp4',
  57             'description': 'This week, Zero Punctuation reviews Evolve.',
  58             'title': 'Evolve - One vs Multiplayer',
  59             'thumbnail': 're:^https?://.*\.jpg$',
  60             'duration': 304,
  61         }
  62     }]
  63
  64     def _real_extract(self, url):
  65         video_id = self._match_id(url)
  66         webpage = self._download_webpage(url, video_id)
  67
  68         imsVideo = self._parse_json(
  69             self._search_regex(
  70                 r'imsVideo\.play\(({.+?})\);', webpage, 'imsVideo'),
  71             video_id)
  72         video_id = imsVideo['videoID']
  73         key = imsVideo['hash']
  74
  75         config_req = compat_urllib_request.Request(
  76             'http://www.escapistmagazine.com/videos/'
  77             'vidconfig.php?videoID=%s&hash=%s' % (video_id, key))
  78         config_req.add_header('Referer', url)
  79         config = self._download_webpage(config_req, video_id, 'Downloading video config')
  80
  81         data = json.loads(_decrypt_config(key, config))
  82
  83         title = clean_html(data['videoData']['title'])
  84         duration = data['videoData']['duration'] / 1000
  85
  86         formats = [{
  87             'url': video['src'],
  88             'format_id': '%s-%sp' % (determine_ext(video['src']), video['res']),
  89             'height': int_or_none(video.get('res')),
  90         } for video in data['files']['videos']]
  91         self._sort_formats(formats)
  92
  93         return {
  94             'id': video_id,
  95             'formats': formats,
  96             'title': title,
  97             'thumbnail': self._og_search_thumbnail(webpage),
  98             'description': self._og_search_description(webpage),
  99             'duration': duration,
 100         }