yt_dlp/extractor/eighttracks.py

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