aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/eighttracks.py
blob: 9a44f89f3fe801047ef283e9b1fa410c8b88cb37 (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
# coding: utf-8
from __future__ import unicode_literals

import json
import random

from .common import InfoExtractor
from ..compat import (
    compat_str,
)
from ..utils import (
    ExtractorError,
)


class EightTracksIE(InfoExtractor):
    IE_NAME = '8tracks'
    _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
    _TEST = {
        'name': 'EightTracks',
        'url': 'http://8tracks.com/ytdl/youtube-dl-test-tracks-a',
        'info_dict': {
            'id': '1336550',
            'display_id': 'youtube-dl-test-tracks-a',
            'description': "test chars:  \"'/\\ä↭",
            'title': "youtube-dl test tracks \"'/\\ä↭<>",
        },
        'playlist': [
            {
                'md5': '96ce57f24389fc8734ce47f4c1abcc55',
                'info_dict': {
                    'id': '11885610',
                    'ext': 'm4a',
                    'title': "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
                    'uploader_id': 'ytdl'
                }
            },
            {
                'md5': '4ab26f05c1f7291ea460a3920be8021f',
                'info_dict': {
                    'id': '11885608',
                    'ext': 'm4a',
                    'title': "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
                    'uploader_id': 'ytdl'
                }
            },
            {
                'md5': 'd30b5b5f74217410f4689605c35d1fd7',
                'info_dict': {
                    'id': '11885679',
                    'ext': 'm4a',
                    'title': "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
                    'uploader_id': 'ytdl'
                }
            },
            {
                'md5': '4eb0a669317cd725f6bbd336a29f923a',
                'info_dict': {
                    'id': '11885680',
                    'ext': 'm4a',
                    'title': "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
                    'uploader_id': 'ytdl'
                }
            },
            {
                'md5': '1893e872e263a2705558d1d319ad19e8',
                'info_dict': {
                    'id': '11885682',
                    'ext': 'm4a',
                    'title': "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
                    'uploader_id': 'ytdl'
                }
            },
            {
                'md5': 'b673c46f47a216ab1741ae8836af5899',
                'info_dict': {
                    'id': '11885683',
                    'ext': 'm4a',
                    'title': "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
                    'uploader_id': 'ytdl'
                }
            },
            {
                'md5': '1d74534e95df54986da7f5abf7d842b7',
                'info_dict': {
                    'id': '11885684',
                    'ext': 'm4a',
                    'title': "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
                    'uploader_id': 'ytdl'
                }
            },
            {
                'md5': 'f081f47af8f6ae782ed131d38b9cd1c0',
                'info_dict': {
                    'id': '11885685',
                    'ext': 'm4a',
                    'title': "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
                    'uploader_id': 'ytdl'
                }
            }
        ]
    }

    def _real_extract(self, url):
        playlist_id = self._match_id(url)

        webpage = self._download_webpage(url, playlist_id)

        data = self._parse_json(
            self._search_regex(
                r"(?s)PAGE\.mix\s*=\s*({.+?});\n", webpage, 'trax information'),
            playlist_id)

        session = str(random.randint(0, 1000000000))
        mix_id = data['id']
        track_count = data['tracks_count']
        duration = data['duration']
        avg_song_duration = float(duration) / track_count
        # duration is sometimes negative, use predefined avg duration
        if avg_song_duration <= 0:
            avg_song_duration = 300
        first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
        next_url = first_url
        entries = []

        for i in range(track_count):
            api_json = None
            download_tries = 0

            while api_json is None:
                try:
                    api_json = self._download_webpage(
                        next_url, playlist_id,
                        note='Downloading song information %d/%d' % (i + 1, track_count),
                        errnote='Failed to download song information')
                except ExtractorError:
                    if download_tries > 3:
                        raise
                    else:
                        download_tries += 1
                        self._sleep(avg_song_duration, playlist_id)

            api_data = json.loads(api_json)
            track_data = api_data['set']['track']
            info = {
                'id': compat_str(track_data['id']),
                'url': track_data['track_file_stream_url'],
                'title': track_data['performer'] + ' - ' + track_data['name'],
                'raw_title': track_data['name'],
                'uploader_id': data['user']['login'],
                'ext': 'm4a',
            }
            entries.append(info)

            next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (
                session, mix_id, track_data['id'])
        return {
            '_type': 'playlist',
            'entries': entries,
            'id': compat_str(mix_id),
            'display_id': playlist_id,
            'title': data.get('name'),
            'description': data.get('description'),
        }