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 ..utils import (
  10     compat_str,
  11 )
  12
  13
  14 class EightTracksIE(InfoExtractor):
  15     IE_NAME = '8tracks'
  16     _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
  17     _TEST = {
  18         "name": "EightTracks",
  19         "url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
  20         "info_dict": {
  21             'id': '1336550',
  22             'display_id': 'youtube-dl-test-tracks-a',
  23             "description": "test chars:  \"'/\\ä↭",
  24             "title": "youtube-dl test tracks \"'/\\ä↭<>",
  25         },
  26         "playlist": [
  27             {
  28                 "md5": "96ce57f24389fc8734ce47f4c1abcc55",
  29                 "info_dict": {
  30                     "id": "11885610",
  31                     "ext": "m4a",
  32                     "title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
  33                     "uploader_id": "ytdl"
  34                 }
  35             },
  36             {
  37                 "md5": "4ab26f05c1f7291ea460a3920be8021f",
  38                 "info_dict": {
  39                     "id": "11885608",
  40                     "ext": "m4a",
  41                     "title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
  42                     "uploader_id": "ytdl"
  43                 }
  44             },
  45             {
  46                 "md5": "d30b5b5f74217410f4689605c35d1fd7",
  47                 "info_dict": {
  48                     "id": "11885679",
  49                     "ext": "m4a",
  50                     "title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
  51                     "uploader_id": "ytdl"
  52                 }
  53             },
  54             {
  55                 "md5": "4eb0a669317cd725f6bbd336a29f923a",
  56                 "info_dict": {
  57                     "id": "11885680",
  58                     "ext": "m4a",
  59                     "title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
  60                     "uploader_id": "ytdl"
  61                 }
  62             },
  63             {
  64                 "md5": "1893e872e263a2705558d1d319ad19e8",
  65                 "info_dict": {
  66                     "id": "11885682",
  67                     "ext": "m4a",
  68                     "title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
  69                     "uploader_id": "ytdl"
  70                 }
  71             },
  72             {
  73                 "md5": "b673c46f47a216ab1741ae8836af5899",
  74                 "info_dict": {
  75                     "id": "11885683",
  76                     "ext": "m4a",
  77                     "title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
  78                     "uploader_id": "ytdl"
  79                 }
  80             },
  81             {
  82                 "md5": "1d74534e95df54986da7f5abf7d842b7",
  83                 "info_dict": {
  84                     "id": "11885684",
  85                     "ext": "m4a",
  86                     "title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
  87                     "uploader_id": "ytdl"
  88                 }
  89             },
  90             {
  91                 "md5": "f081f47af8f6ae782ed131d38b9cd1c0",
  92                 "info_dict": {
  93                     "id": "11885685",
  94                     "ext": "m4a",
  95                     "title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
  96                     "uploader_id": "ytdl"
  97                 }
  98             }
  99         ]
 100     }
 101
 102     def _real_extract(self, url):
 103         mobj = re.match(self._VALID_URL, url)
 104         playlist_id = mobj.group('id')
 105
 106         webpage = self._download_webpage(url, playlist_id)
 107
 108         json_like = self._search_regex(
 109             r"(?s)PAGE.mix = (.*?);\n", webpage, 'trax information')
 110         data = json.loads(json_like)
 111
 112         session = str(random.randint(0, 1000000000))
 113         mix_id = data['id']
 114         track_count = data['tracks_count']
 115         first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
 116         next_url = first_url
 117         entries = []
 118         for i in range(track_count):
 119             api_json = self._download_webpage(
 120                 next_url, playlist_id,
 121                 note='Downloading song information %d/%d' % (i + 1, track_count),
 122                 errnote='Failed to download song information')
 123             api_data = json.loads(api_json)
 124             track_data = api_data['set']['track']
 125             info = {
 126                 'id': compat_str(track_data['id']),
 127                 'url': track_data['track_file_stream_url'],
 128                 'title': track_data['performer'] + u' - ' + track_data['name'],
 129                 'raw_title': track_data['name'],
 130                 'uploader_id': data['user']['login'],
 131                 'ext': 'm4a',
 132             }
 133             entries.append(info)
 134             next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (
 135                 session, mix_id, track_data['id'])
 136         return {
 137             '_type': 'playlist',
 138             'entries': entries,
 139             'id': compat_str(mix_id),
 140             'display_id': playlist_id,
 141             'title': data.get('name'),
 142             'description': data.get('description'),
 143         }