summary refs log tree commit diff
path: root/youtube_dl/extractor/vvvvid.py
blob: 5b8ea3665c21157727770a61d3902e5091a51bbf (plain) (blame)
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
199
200
201
202
203
204
205
206
207
208
209
210
211
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    int_or_none,
    str_or_none,
)


class VVVVIDIE(InfoExtractor):
    _VALID_URL_BASE = r'https?://(?:www\.)?vvvvid\.it/(?:#!)?(?:show|anime|film|series)/'
    _VALID_URL = r'%s(?P<show_id>\d+)/[^/]+/(?P<season_id>\d+)/(?P<id>[0-9]+)' % _VALID_URL_BASE
    _TESTS = [{
        # video_type == 'video/vvvvid'
        'url': 'https://www.vvvvid.it/#!show/434/perche-dovrei-guardarlo-di-dario-moccia/437/489048/ping-pong',
        'md5': 'b8d3cecc2e981adc3835adf07f6df91b',
        'info_dict': {
            'id': '489048',
            'ext': 'mp4',
            'title': 'Ping Pong',
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # video_type == 'video/rcs'
        'url': 'https://www.vvvvid.it/#!show/376/death-note-live-action/377/482493/episodio-01',
        'md5': '33e0edfba720ad73a8782157fdebc648',
        'info_dict': {
            'id': '482493',
            'ext': 'mp4',
            'title': 'Episodio 01',
        },
        'params': {
            'skip_download': True,
        },
    }]
    _conn_id = None

    def _real_initialize(self):
        self._conn_id = self._download_json(
            'https://www.vvvvid.it/user/login',
            None, headers=self.geo_verification_headers())['data']['conn_id']

    def _download_info(self, show_id, path, video_id, fatal=True):
        response = self._download_json(
            'https://www.vvvvid.it/vvvvid/ondemand/%s%s' % (show_id, path),
            video_id, headers=self.geo_verification_headers(), query={
                'conn_id': self._conn_id,
            }, fatal=fatal)
        if response['result'] == 'error':
            raise ExtractorError('%s said: %s' % (
                self.IE_NAME, response['message']), expected=True)
        return response['data']

    def _real_extract(self, url):
        show_id, season_id, video_id = re.match(self._VALID_URL, url).groups()

        response = self._download_info(
            show_id, '/season/%s' % season_id, video_id)

        vid = int(video_id)
        video_data = list(filter(
            lambda episode: episode.get('video_id') == vid, response))[0]
        formats = []

        # vvvvid embed_info decryption algorithm is reverse engineered from function $ds(h) at vvvvid.js
        def ds(h):
            g = "MNOPIJKL89+/4567UVWXQRSTEFGHABCDcdefYZabstuvopqr0123wxyzklmnghij"

            def f(m):
                l = []
                o = 0
                b = False
                m_len = len(m)
                while ((not b) and o < m_len):
                    n = m[o] << 2
                    o += 1
                    k = -1
                    j = -1
                    if o < m_len:
                        n += m[o] >> 4
                        o += 1
                        if o < m_len:
                            k = (m[o - 1] << 4) & 255
                            k += m[o] >> 2
                            o += 1
                            if o < m_len:
                                j = (m[o - 1] << 6) & 255
                                j += m[o]
                                o += 1
                            else:
                                b = True
                        else:
                            b = True
                    else:
                        b = True
                    l.append(n)
                    if k != -1:
                        l.append(k)
                    if j != -1:
                        l.append(j)
                return l

            c = []
            for e in h:
                c.append(g.index(e))

            c_len = len(c)
            for e in range(c_len * 2 - 1, -1, -1):
                a = c[e % c_len] ^ c[(e + 1) % c_len]
                c[e % c_len] = a

            c = f(c)
            d = ''
            for e in c:
                d += chr(e)

            return d

        for quality in ('_sd', ''):
            embed_code = video_data.get('embed_info' + quality)
            if not embed_code:
                continue
            embed_code = ds(embed_code)
            video_type = video_data.get('video_type')
            if video_type in ('video/rcs', 'video/kenc'):
                embed_code = re.sub(r'https?://([^/]+)/z/', r'https://\1/i/', embed_code).replace('/manifest.f4m', '/master.m3u8')
                if video_type == 'video/kenc':
                    kenc = self._download_json(
                        'https://www.vvvvid.it/kenc', video_id, query={
                            'action': 'kt',
                            'conn_id': self._conn_id,
                            'url': embed_code,
                        }, fatal=False) or {}
                    kenc_message = kenc.get('message')
                    if kenc_message:
                        embed_code += '?' + ds(kenc_message)
                formats.extend(self._extract_m3u8_formats(
                    embed_code, video_id, 'mp4',
                    m3u8_id='hls', fatal=False))
            else:
                formats.extend(self._extract_wowza_formats(
                    'http://sb.top-ix.org/videomg/_definst_/mp4:%s/playlist.m3u8' % embed_code, video_id))
        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': video_data['title'],
            'formats': formats,
            'thumbnail': video_data.get('thumbnail'),
            'duration': int_or_none(video_data.get('length')),
            'series': video_data.get('show_title'),
            'season_id': season_id,
            'season_number': video_data.get('season_number'),
            'episode_id': str_or_none(video_data.get('id')),
            'episode_number': int_or_none(video_data.get('number')),
            'episode_title': video_data['title'],
            'view_count': int_or_none(video_data.get('views')),
            'like_count': int_or_none(video_data.get('video_likes')),
        }


class VVVVIDShowIE(VVVVIDIE):
    _VALID_URL = r'(?P<base_url>%s(?P<show_id>\d+)/(?P<show_title>[^/]+))/?(?:$|[\?&].*$)?$' % VVVVIDIE._VALID_URL_BASE
    _TESTS = [{
        'url': 'https://www.vvvvid.it/show/156/psyco-pass',
        'info_dict': {
            'id': '156',
            'title': 'Psycho-Pass',
            'description': 'md5:94d572c0bd85894b193b8aebc9a3a806',
        },
        'playlist_count': 46,
    }]

    def _real_extract(self, url):
        base_url, show_id, show_title = re.match(self._VALID_URL, url).groups()

        response = self._download_info(
            show_id, '/seasons/', show_title)

        show_infos = self._download_info(
            show_id, '/info/', show_title, fatal=False)

        entries = []
        for season in response:
            episodes = season.get('episodes') or []
            for episode in episodes:
                season_id = str_or_none(episode.get('season_id'))
                video_id = str_or_none(episode.get('video_id'))
                if not (season_id and video_id):
                    continue

                video_url = '/'.join([base_url, season_id, video_id])

                entries.append({
                    '_type': 'url_transparent',
                    'ie_key': VVVVIDIE.ie_key(),
                    'url': video_url,
                    'title': episode.get('title'),
                    'thumbnail': episode.get('thumbnail'),
                    'description': episode.get('description'),
                    'season_number': int_or_none(episode.get('season_number')),
                    'episode_number': int_or_none(episode.get('number')),
                })
        return self.playlist_result(
            entries, show_id, show_infos.get('title'), show_infos.get('description'))