]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/eighttracks.py
[ard] Improve _VALID_URL (closes #25134) (#25198)
[youtube-dl.git] / youtube_dl / extractor / eighttracks.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import json
5 import random
6
7 from .common import InfoExtractor
8 from ..compat import (
9     compat_str,
10 )
11 from ..utils import (
12     ExtractorError,
13 )
14
15
16 class EightTracksIE(InfoExtractor):
17     IE_NAME = '8tracks'
18     _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
19     _TEST = {
20         'name': 'EightTracks',
21         'url': 'http://8tracks.com/ytdl/youtube-dl-test-tracks-a',
22         'info_dict': {
23             'id': '1336550',
24             'display_id': 'youtube-dl-test-tracks-a',
25             'description': "test chars:  \"'/\\ä↭",
26             'title': "youtube-dl test tracks \"'/\\ä↭<>",
27         },
28         'playlist': [
29             {
30                 'md5': '96ce57f24389fc8734ce47f4c1abcc55',
31                 'info_dict': {
32                     'id': '11885610',
33                     'ext': 'm4a',
34                     'title': "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
35                     'uploader_id': 'ytdl'
36                 }
37             },
38             {
39                 'md5': '4ab26f05c1f7291ea460a3920be8021f',
40                 'info_dict': {
41                     'id': '11885608',
42                     'ext': 'm4a',
43                     'title': "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
44                     'uploader_id': 'ytdl'
45                 }
46             },
47             {
48                 'md5': 'd30b5b5f74217410f4689605c35d1fd7',
49                 'info_dict': {
50                     'id': '11885679',
51                     'ext': 'm4a',
52                     'title': "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
53                     'uploader_id': 'ytdl'
54                 }
55             },
56             {
57                 'md5': '4eb0a669317cd725f6bbd336a29f923a',
58                 'info_dict': {
59                     'id': '11885680',
60                     'ext': 'm4a',
61                     'title': "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
62                     'uploader_id': 'ytdl'
63                 }
64             },
65             {
66                 'md5': '1893e872e263a2705558d1d319ad19e8',
67                 'info_dict': {
68                     'id': '11885682',
69                     'ext': 'm4a',
70                     'title': "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
71                     'uploader_id': 'ytdl'
72                 }
73             },
74             {
75                 'md5': 'b673c46f47a216ab1741ae8836af5899',
76                 'info_dict': {
77                     'id': '11885683',
78                     'ext': 'm4a',
79                     'title': "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
80                     'uploader_id': 'ytdl'
81                 }
82             },
83             {
84                 'md5': '1d74534e95df54986da7f5abf7d842b7',
85                 'info_dict': {
86                     'id': '11885684',
87                     'ext': 'm4a',
88                     'title': "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
89                     'uploader_id': 'ytdl'
90                 }
91             },
92             {
93                 'md5': 'f081f47af8f6ae782ed131d38b9cd1c0',
94                 'info_dict': {
95                     'id': '11885685',
96                     'ext': 'm4a',
97                     'title': "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
98                     'uploader_id': 'ytdl'
99                 }
100             }
101         ]
102     }
103
104     def _real_extract(self, url):
105         playlist_id = self._match_id(url)
106
107         webpage = self._download_webpage(url, playlist_id)
108
109         data = self._parse_json(
110             self._search_regex(
111                 r"(?s)PAGE\.mix\s*=\s*({.+?});\n", webpage, 'trax information'),
112             playlist_id)
113
114         session = str(random.randint(0, 1000000000))
115         mix_id = data['id']
116         track_count = data['tracks_count']
117         duration = data['duration']
118         avg_song_duration = float(duration) / track_count
119         # duration is sometimes negative, use predefined avg duration
120         if avg_song_duration <= 0:
121             avg_song_duration = 300
122         first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
123         next_url = first_url
124         entries = []
125
126         for i in range(track_count):
127             api_json = None
128             download_tries = 0
129
130             while api_json is None:
131                 try:
132                     api_json = self._download_webpage(
133                         next_url, playlist_id,
134                         note='Downloading song information %d/%d' % (i + 1, track_count),
135                         errnote='Failed to download song information')
136                 except ExtractorError:
137                     if download_tries > 3:
138                         raise
139                     else:
140                         download_tries += 1
141                         self._sleep(avg_song_duration, playlist_id)
142
143             api_data = json.loads(api_json)
144             track_data = api_data['set']['track']
145             info = {
146                 'id': compat_str(track_data['id']),
147                 'url': track_data['track_file_stream_url'],
148                 'title': track_data['performer'] + ' - ' + track_data['name'],
149                 'raw_title': track_data['name'],
150                 'uploader_id': data['user']['login'],
151                 'ext': 'm4a',
152             }
153             entries.append(info)
154
155             next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (
156                 session, mix_id, track_data['id'])
157         return {
158             '_type': 'playlist',
159             'entries': entries,
160             'id': compat_str(mix_id),
161             'display_id': playlist_id,
162             'title': data.get('name'),
163             'description': data.get('description'),
164         }