c85b4c458d95882f56675fa135aab1f3492b6194
[youtube-dl] / 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     float_or_none,
13 )
14
15
16 def _decrypt_config(key, string):
17     a = ''
18     i = ''
19     r = ''
20
21     while len(a) < (len(string) / 2):
22         a += key
23
24     a = a[0:int(len(string) / 2)]
25
26     t = 0
27     while t < len(string):
28         i += chr(int(string[t] + string[t + 1], 16))
29         t += 2
30
31     icko = [s for s in i]
32
33     for t, c in enumerate(a):
34         r += chr(ord(c) ^ ord(icko[t]))
35
36     return r
37
38
39 class EscapistIE(InfoExtractor):
40     _VALID_URL = r'https?://?(?:www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
41     _TESTS = [{
42         'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
43         'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
44         'info_dict': {
45             'id': '6618',
46             'ext': 'mp4',
47             'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
48             'title': "Breaking Down Baldur's Gate",
49             'thumbnail': 're:^https?://.*\.jpg$',
50             'duration': 264,
51             'uploader': 'The Escapist',
52         }
53     }, {
54         'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer',
55         'md5': '9e8c437b0dbb0387d3bd3255ca77f6bf',
56         'info_dict': {
57             'id': '10044',
58             'ext': 'mp4',
59             'description': 'This week, Zero Punctuation reviews Evolve.',
60             'title': 'Evolve - One vs Multiplayer',
61             'thumbnail': 're:^https?://.*\.jpg$',
62             'duration': 304,
63             'uploader': 'The Escapist',
64         }
65     }]
66
67     def _real_extract(self, url):
68         video_id = self._match_id(url)
69         webpage = self._download_webpage(url, video_id)
70
71         ims_video = self._parse_json(
72             self._search_regex(
73                 r'imsVideo\.play\(({.+?})\);', webpage, 'imsVideo'),
74             video_id)
75         video_id = ims_video['videoID']
76         key = ims_video['hash']
77
78         config_req = compat_urllib_request.Request(
79             'http://www.escapistmagazine.com/videos/'
80             'vidconfig.php?videoID=%s&hash=%s' % (video_id, key))
81         config_req.add_header('Referer', url)
82         config = self._download_webpage(config_req, video_id, 'Downloading video config')
83
84         data = json.loads(_decrypt_config(key, config))
85
86         video_data = data['videoData']
87
88         title = clean_html(video_data['title'])
89         duration = float_or_none(video_data.get('duration'), 1000)
90         uploader = video_data.get('publisher')
91
92         formats = [{
93             'url': video['src'],
94             'format_id': '%s-%sp' % (determine_ext(video['src']), video['res']),
95             'height': int_or_none(video.get('res')),
96         } for video in data['files']['videos']]
97         self._sort_formats(formats)
98
99         return {
100             'id': video_id,
101             'formats': formats,
102             'title': title,
103             'thumbnail': self._og_search_thumbnail(webpage),
104             'description': self._og_search_description(webpage),
105             'duration': duration,
106             'uploader': uploader,
107         }