yt_dlp/extractor/eighttracks.py

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