_ Git - youtube-dl/blob - youtube_dl/extractor/eighttracks.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import random
   6 import re
   7
   8 from .common import InfoExtractor
   9 from ..compat import (
  10     compat_str,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14 )
  15
  16
  17 class EightTracksIE(InfoExtractor):
  18     IE_NAME = '8tracks'
  19     _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
  20     _TEST = {
  21         "name": "EightTracks",
  22         "url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
  23         "info_dict": {
  24             'id': '1336550',
  25             'display_id': 'youtube-dl-test-tracks-a',
  26             "description": "test chars:  \"'/\\ä↭",
  27             "title": "youtube-dl test tracks \"'/\\ä↭<>",
  28         },
  29         "playlist": [
  30             {
  31                 "md5": "96ce57f24389fc8734ce47f4c1abcc55",
  32                 "info_dict": {
  33                     "id": "11885610",
  34                     "ext": "m4a",
  35                     "title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
  36                     "uploader_id": "ytdl"
  37                 }
  38             },
  39             {
  40                 "md5": "4ab26f05c1f7291ea460a3920be8021f",
  41                 "info_dict": {
  42                     "id": "11885608",
  43                     "ext": "m4a",
  44                     "title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
  45                     "uploader_id": "ytdl"
  46                 }
  47             },
  48             {
  49                 "md5": "d30b5b5f74217410f4689605c35d1fd7",
  50                 "info_dict": {
  51                     "id": "11885679",
  52                     "ext": "m4a",
  53                     "title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
  54                     "uploader_id": "ytdl"
  55                 }
  56             },
  57             {
  58                 "md5": "4eb0a669317cd725f6bbd336a29f923a",
  59                 "info_dict": {
  60                     "id": "11885680",
  61                     "ext": "m4a",
  62                     "title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
  63                     "uploader_id": "ytdl"
  64                 }
  65             },
  66             {
  67                 "md5": "1893e872e263a2705558d1d319ad19e8",
  68                 "info_dict": {
  69                     "id": "11885682",
  70                     "ext": "m4a",
  71                     "title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
  72                     "uploader_id": "ytdl"
  73                 }
  74             },
  75             {
  76                 "md5": "b673c46f47a216ab1741ae8836af5899",
  77                 "info_dict": {
  78                     "id": "11885683",
  79                     "ext": "m4a",
  80                     "title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
  81                     "uploader_id": "ytdl"
  82                 }
  83             },
  84             {
  85                 "md5": "1d74534e95df54986da7f5abf7d842b7",
  86                 "info_dict": {
  87                     "id": "11885684",
  88                     "ext": "m4a",
  89                     "title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
  90                     "uploader_id": "ytdl"
  91                 }
  92             },
  93             {
  94                 "md5": "f081f47af8f6ae782ed131d38b9cd1c0",
  95                 "info_dict": {
  96                     "id": "11885685",
  97                     "ext": "m4a",
  98                     "title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
  99                     "uploader_id": "ytdl"
 100                 }
 101             }
 102         ]
 103     }
 104
 105     def _real_extract(self, url):
 106         playlist_id = self._match_id(url)
 107
 108         webpage = self._download_webpage(url, playlist_id)
 109
 110         data = self._parse_json(
 111             self._search_regex(
 112                 r"(?s)PAGE\.mix\s*=\s*({.+?});\n", webpage, 'trax information'),
 113             playlist_id)
 114
 115         session = str(random.randint(0, 1000000000))
 116         mix_id = data['id']
 117         track_count = data['tracks_count']
 118         duration = data['duration']
 119         avg_song_duration = float(duration) / track_count
 120         # duration is sometimes negative, use predefined avg duration
 121         if avg_song_duration <= 0:
 122             avg_song_duration = 300
 123         first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
 124         next_url = first_url
 125         entries = []
 126
 127         for i in range(track_count):
 128             api_json = None
 129             download_tries = 0
 130
 131             while api_json is None:
 132                 try:
 133                     api_json = self._download_webpage(
 134                         next_url, playlist_id,
 135                         note='Downloading song information %d/%d' % (i + 1, track_count),
 136                         errnote='Failed to download song information')
 137                 except ExtractorError:
 138                     if download_tries > 3:
 139                         raise
 140                     else:
 141                         download_tries += 1
 142                         self._sleep(avg_song_duration, playlist_id)
 143
 144             api_data = json.loads(api_json)
 145             track_data = api_data['set']['track']
 146             info = {
 147                 'id': compat_str(track_data['id']),
 148                 'url': track_data['track_file_stream_url'],
 149                 'title': track_data['performer'] + ' - ' + track_data['name'],
 150                 'raw_title': track_data['name'],
 151                 'uploader_id': data['user']['login'],
 152                 'ext': 'm4a',
 153             }
 154             entries.append(info)
 155
 156             next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (
 157                 session, mix_id, track_data['id'])
 158         return {
 159             '_type': 'playlist',
 160             'entries': entries,
 161             'id': compat_str(mix_id),
 162             'display_id': playlist_id,
 163             'title': data.get('name'),
 164             'description': data.get('description'),
 165         }