aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/openload.py
blob: 435aec28e2fbf20e29399c12281ff7d7c6a9fa3f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_chr
from ..utils import (
    determine_ext,
    ExtractorError,
)


class OpenloadIE(InfoExtractor):
    _VALID_URL = r'https?://(?:openload\.(?:co|io)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'

    _TESTS = [{
        'url': 'https://openload.co/f/kUEfGclsU9o',
        'md5': 'bf1c059b004ebc7a256f89408e65c36e',
        'info_dict': {
            'id': 'kUEfGclsU9o',
            'ext': 'mp4',
            'title': 'skyrim_no-audio_1080.mp4',
            'thumbnail': r're:^https?://.*\.jpg$',
        },
    }, {
        'url': 'https://openload.co/embed/rjC09fkPLYs',
        'info_dict': {
            'id': 'rjC09fkPLYs',
            'ext': 'mp4',
            'title': 'movie.mp4',
            'thumbnail': r're:^https?://.*\.jpg$',
            'subtitles': {
                'en': [{
                    'ext': 'vtt',
                }],
            },
        },
        'params': {
            'skip_download': True,  # test subtitles only
        },
    }, {
        'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
        'only_matching': True,
    }, {
        'url': 'https://openload.io/f/ZAn6oz-VZGE/',
        'only_matching': True,
    }, {
        'url': 'https://openload.co/f/_-ztPaZtMhM/',
        'only_matching': True,
    }, {
        # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
        # for title and ext
        'url': 'https://openload.co/embed/Sxz5sADo82g/',
        'only_matching': True,
    }, {
        'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
        'only_matching': True,
    }]

    @staticmethod
    def _extract_urls(webpage):
        return re.findall(
            r'<iframe[^>]+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)',
            webpage)

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)

        if 'File not found' in webpage or 'deleted by the owner' in webpage:
            raise ExtractorError('File not found', expected=True)

        ol_id = self._search_regex(
            '<span[^>]+id="[^"]+"[^>]*>([0-9A-Za-z]+)</span>',
            webpage, 'openload ID')

        video_url_chars = []

        first_char = ord(ol_id[0])
        key = first_char - 55
        maxKey = max(2, key)
        key = min(maxKey, len(ol_id) - 38)
        t = ol_id[key:key + 36]

        hashMap = {}
        v = ol_id.replace(t, '')
        h = 0

        while h < len(t):
            f = t[h:h + 3]
            i = int(f, 8)
            hashMap[h / 3] = i
            h += 3

        h = 0
        H = 0
        while h < len(v):
            B = ''
            C = ''
            if len(v) >= h + 2:
                B = v[h:h + 2]
            if len(v) >= h + 3:
                C = v[h:h + 3]
            i = int(B, 16)
            h += 2
            if H % 3 == 0:
                i = int(C, 8)
                h += 1
            elif H % 2 == 0 and H != 0 and ord(v[H - 1]) < 60:
                i = int(C, 10)
                h += 1
            index = H % 12

            A = hashMap[index]
            i ^= 213
            i ^= A
            video_url_chars.append(compat_chr(i))
            H += 1

        video_url = 'https://openload.co/stream/%s?mime=true'
        video_url = video_url % (''.join(video_url_chars))

        title = self._og_search_title(webpage, default=None) or self._search_regex(
            r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
            'title', default=None) or self._html_search_meta(
            'description', webpage, 'title', fatal=True)

        entries = self._parse_html5_media_entries(url, webpage, video_id)
        subtitles = entries[0]['subtitles'] if entries else None

        info_dict = {
            'id': video_id,
            'title': title,
            'thumbnail': self._og_search_thumbnail(webpage, default=None),
            'url': video_url,
            # Seems all videos have extensions in their titles
            'ext': determine_ext(title, 'mp4'),
            'subtitles': subtitles,
        }
        return info_dict