aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/audiomack.py
blob: f3bd4d4447f559a8bd924f7d796a1a9faf24b9d3 (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
# coding: utf-8
from __future__ import unicode_literals

import itertools
import time

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


class AudiomackIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?audiomack\.com/song/(?P<id>[\w/-]+)'
    IE_NAME = 'audiomack'
    _TESTS = [
        # hosted on audiomack
        {
            'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary',
            'info_dict':
            {
                'id': '310086',
                'ext': 'mp3',
                'uploader': 'Roosh Williams',
                'title': 'Extraordinary'
            }
        },
        # audiomack wrapper around soundcloud song
        {
            'add_ie': ['Soundcloud'],
            'url': 'http://www.audiomack.com/song/hip-hop-daily/black-mamba-freestyle',
            'info_dict': {
                'id': '258901379',
                'ext': 'mp3',
                'description': 'mamba day freestyle for the legend Kobe Bryant ',
                'title': 'Black Mamba Freestyle [Prod. By Danny Wolf]',
                'uploader': 'ILOVEMAKONNEN',
                'upload_date': '20160414',
            }
        },
    ]

    def _real_extract(self, url):
        # URLs end with [uploader name]/[uploader title]
        # this title is whatever the user types in, and is rarely
        # the proper song title.  Real metadata is in the api response
        album_url_tag = self._match_id(url)

        # Request the extended version of the api for extra fields like artist and title
        api_response = self._download_json(
            'http://www.audiomack.com/api/music/url/song/%s?extended=1&_=%d' % (
                album_url_tag, time.time()),
            album_url_tag)

        # API is inconsistent with errors
        if 'url' not in api_response or not api_response['url'] or 'error' in api_response:
            raise ExtractorError('Invalid url %s' % url)

        # Audiomack wraps a lot of soundcloud tracks in their branded wrapper
        # if so, pass the work off to the soundcloud extractor
        if SoundcloudIE.suitable(api_response['url']):
            return {'_type': 'url', 'url': api_response['url'], 'ie_key': 'Soundcloud'}

        return {
            'id': api_response.get('id', album_url_tag),
            'uploader': api_response.get('artist'),
            'title': api_response.get('title'),
            'url': api_response['url'],
        }


class AudiomackAlbumIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?audiomack\.com/album/(?P<id>[\w/-]+)'
    IE_NAME = 'audiomack:album'
    _TESTS = [
        # Standard album playlist
        {
            'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape',
            'playlist_count': 15,
            'info_dict':
            {
                'id': '812251',
                'title': 'Tha Tour: Part 2 (Official Mixtape)'
            }
        },
        # Album playlist ripped from fakeshoredrive with no metadata
        {
            'url': 'http://www.audiomack.com/album/fakeshoredrive/ppp-pistol-p-project',
            'info_dict': {
                'title': 'PPP (Pistol P Project)',
                'id': '837572',
            },
            'playlist': [{
                'info_dict': {
                    'title': 'PPP (Pistol P Project) - 9. Heaven or Hell (CHIMACA) ft Zuse (prod by DJ FU)',
                    'id': '837577',
                    'ext': 'mp3',
                    'uploader': 'Lil Herb a.k.a. G Herbo',
                }
            }],
            'params': {
                'playliststart': 9,
                'playlistend': 9,
            }
        }
    ]

    def _real_extract(self, url):
        # URLs end with [uploader name]/[uploader title]
        # this title is whatever the user types in, and is rarely
        # the proper song title.  Real metadata is in the api response
        album_url_tag = self._match_id(url)
        result = {'_type': 'playlist', 'entries': []}
        # There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata
        # Therefore we don't know how many songs the album has and must infi-loop until failure
        for track_no in itertools.count():
            # Get song's metadata
            api_response = self._download_json(
                'http://www.audiomack.com/api/music/url/album/%s/%d?extended=1&_=%d'
                % (album_url_tag, track_no, time.time()), album_url_tag,
                note='Querying song information (%d)' % (track_no + 1))

            # Total failure, only occurs when url is totally wrong
            # Won't happen in middle of valid playlist (next case)
            if 'url' not in api_response or 'error' in api_response:
                raise ExtractorError('Invalid url for track %d of album url %s' % (track_no, url))
            # URL is good but song id doesn't exist - usually means end of playlist
            elif not api_response['url']:
                break
            else:
                # Pull out the album metadata and add to result (if it exists)
                for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]:
                    if apikey in api_response and resultkey not in result:
                        result[resultkey] = api_response[apikey]
                song_id = url_basename(api_response['url']).rpartition('.')[0]
                result['entries'].append({
                    'id': compat_str(api_response.get('id', song_id)),
                    'uploader': api_response.get('artist'),
                    'title': api_response.get('title', song_id),
                    'url': api_response['url'],
                })
        return result