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 import time
   8
   9 from .common import InfoExtractor
  10 from ..utils import (
  11     compat_str,
  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         mobj = re.match(self._VALID_URL, url)
 106         playlist_id = mobj.group('id')
 107
 108         webpage = self._download_webpage(url, playlist_id)
 109
 110         json_like = self._search_regex(
 111             r"(?s)PAGE.mix = (.*?);\n", webpage, 'trax information')
 112         data = json.loads(json_like)
 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 = duration / track_count
 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
 125             api_json = None
 126             download_tries = 0
 127
 128             while api_json is None:
 129                 try:
 130                     api_json = self._download_webpage(
 131                         next_url, playlist_id,
 132                         note='Downloading song information %d/%d' % (i + 1, track_count),
 133                         errnote='Failed to download song information')
 134                 except ExtractorError:
 135                     if download_tries > 3:
 136                         raise
 137                     else:
 138                         download_tries += 1
 139                         time.sleep(avg_song_duration)
 140
 141             api_data = json.loads(api_json)
 142             track_data = api_data['set']['track']
 143             info = {
 144                 'id': compat_str(track_data['id']),
 145                 'url': track_data['track_file_stream_url'],
 146                 'title': track_data['performer'] + u' - ' + track_data['name'],
 147                 'raw_title': track_data['name'],
 148                 'uploader_id': data['user']['login'],
 149                 'ext': 'm4a',
 150             }
 151             entries.append(info)
 152
 153             next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (
 154                 session, mix_id, track_data['id'])
 155         return {
 156             '_type': 'playlist',
 157             'entries': entries,
 158             'id': compat_str(mix_id),
 159             'display_id': playlist_id,
 160             'title': data.get('name'),
 161             'description': data.get('description'),
 162         }