summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/xfileshare.py
blob: 08c6d6c7c01f153ba37454a2da0020f8bea49382 (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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
import re

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    decode_packed_codes,
    determine_ext,
    int_or_none,
    js_to_json,
    urlencode_postdata,
)


# based on openload_decode from 2bfeee69b976fe049761dd3012e30b637ee05a58
def aa_decode(aa_code):
    symbol_table = [
        ('7', '((゚ー゚) + (o^_^o))'),
        ('6', '((o^_^o) +(o^_^o))'),
        ('5', '((゚ー゚) + (゚Θ゚))'),
        ('2', '((o^_^o) - (゚Θ゚))'),
        ('4', '(゚ー゚)'),
        ('3', '(o^_^o)'),
        ('1', '(゚Θ゚)'),
        ('0', '(c^_^o)'),
    ]
    delim = '(゚Д゚)[゚ε゚]+'
    ret = ''
    for aa_char in aa_code.split(delim):
        for val, pat in symbol_table:
            aa_char = aa_char.replace(pat, val)
        aa_char = aa_char.replace('+ ', '')
        m = re.match(r'^\d+', aa_char)
        if m:
            ret += chr(int(m.group(0), 8))
        else:
            m = re.match(r'^u([\da-f]+)', aa_char)
            if m:
                ret += chr(int(m.group(1), 16))
    return ret


class XFileShareIE(InfoExtractor):
    _SITES = (
        (r'aparat\.cam', 'Aparat'),
        (r'clipwatching\.com', 'ClipWatching'),
        (r'gounlimited\.to', 'GoUnlimited'),
        (r'govid\.me', 'GoVid'),
        (r'holavid\.com', 'HolaVid'),
        (r'streamty\.com', 'Streamty'),
        (r'thevideobee\.to', 'TheVideoBee'),
        (r'uqload\.com', 'Uqload'),
        (r'vidbom\.com', 'VidBom'),
        (r'vidlo\.us', 'vidlo'),
        (r'vidlocker\.xyz', 'VidLocker'),
        (r'vidshare\.tv', 'VidShare'),
        (r'vup\.to', 'VUp'),
        (r'wolfstream\.tv', 'WolfStream'),
        (r'xvideosharing\.com', 'XVideoSharing'),
    )

    IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
    _VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
                  % '|'.join(site for site in list(zip(*_SITES))[0]))
    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1' % '|'.join(site for site in list(zip(*_SITES))[0])]

    _FILE_NOT_FOUND_REGEXES = (
        r'>(?:404 - )?File Not Found<',
        r'>The file was removed by administrator<',
    )

    _TESTS = [{
        'url': 'https://uqload.com/dltx1wztngdz',
        'md5': '3cfbb65e4c90e93d7b37bcb65a595557',
        'info_dict': {
            'id': 'dltx1wztngdz',
            'ext': 'mp4',
            'title': 'Rick Astley Never Gonna Give You mp4',
            'thumbnail': r're:https://.*\.jpg'
        }
    }, {
        'url': 'http://xvideosharing.com/fq65f94nd2ve',
        'md5': '4181f63957e8fe90ac836fa58dc3c8a6',
        'info_dict': {
            'id': 'fq65f94nd2ve',
            'ext': 'mp4',
            'title': 'sample',
            'thumbnail': r're:http://.*\.jpg',
        },
    }, {
        'url': 'https://aparat.cam/n4d6dh0wvlpr',
        'only_matching': True,
    }, {
        'url': 'https://wolfstream.tv/nthme29v9u2x',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        host, video_id = self._match_valid_url(url).groups()

        url = 'https://%s/' % host + ('embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
        webpage = self._download_webpage(url, video_id)

        if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
            raise ExtractorError('Video %s does not exist' % video_id, expected=True)

        fields = self._hidden_inputs(webpage)

        if fields.get('op') == 'download1':
            countdown = int_or_none(self._search_regex(
                r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
                webpage, 'countdown', default=None))
            if countdown:
                self._sleep(countdown, video_id)

            webpage = self._download_webpage(
                url, video_id, 'Downloading video page',
                data=urlencode_postdata(fields), headers={
                    'Referer': url,
                    'Content-type': 'application/x-www-form-urlencoded',
                })

        title = (self._search_regex(
            (r'style="z-index: [0-9]+;">([^<]+)</span>',
             r'<td nowrap>([^<]+)</td>',
             r'h4-fine[^>]*>([^<]+)<',
             r'>Watch (.+)[ <]',
             r'<h2 class="video-page-head">([^<]+)</h2>',
             r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<',  # streamin.to
             r'title\s*:\s*"([^"]+)"'),  # govid.me
            webpage, 'title', default=None) or self._og_search_title(
            webpage, default=None) or video_id).strip()

        for regex, func in (
                (r'(eval\(function\(p,a,c,k,e,d\){.+)', decode_packed_codes),
                (r'(゚.+)', aa_decode)):
            obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None)
            if obf_code:
                webpage = webpage.replace(obf_code, func(obf_code))

        formats = []

        jwplayer_data = self._search_regex(
            [
                r'jwplayer\("[^"]+"\)\.load\(\[({.+?})\]\);',
                r'jwplayer\("[^"]+"\)\.setup\(({.+?})\);',
            ], webpage,
            'jwplayer data', default=None)
        if jwplayer_data:
            jwplayer_data = self._parse_json(
                jwplayer_data.replace(r"\'", "'"), video_id, js_to_json)
            if jwplayer_data:
                formats = self._parse_jwplayer_data(
                    jwplayer_data, video_id, False,
                    m3u8_id='hls', mpd_id='dash')['formats']

        if not formats:
            urls = []
            for regex in (
                    r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
                    r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
                    r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
                    r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1'):
                for mobj in re.finditer(regex, webpage):
                    video_url = mobj.group('url')
                    if video_url not in urls:
                        urls.append(video_url)

            sources = self._search_regex(
                r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None)
            if sources:
                urls.extend(self._parse_json(sources, video_id))

            formats = []
            for video_url in urls:
                if determine_ext(video_url) == 'm3u8':
                    formats.extend(self._extract_m3u8_formats(
                        video_url, video_id, 'mp4',
                        entry_protocol='m3u8_native', m3u8_id='hls',
                        fatal=False))
                else:
                    formats.append({
                        'url': video_url,
                        'format_id': 'sd',
                    })

        thumbnail = self._search_regex(
            [
                r'<video[^>]+poster="([^"]+)"',
                r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],',
            ], webpage, 'thumbnail', default=None)

        return {
            'id': video_id,
            'title': title,
            'thumbnail': thumbnail,
            'formats': formats,
            'http_headers': {'Referer': url}
        }