youtube_dl/extractor/eighttracks.py

   1 import json
   2 import random
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8 )
   9
  10
  11 class EightTracksIE(InfoExtractor):
  12     IE_NAME = '8tracks'
  13     _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
  14     _TEST = {
  15         u"name": u"EightTracks",
  16         u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
  17         u"playlist": [
  18             {
  19                 u"file": u"11885610.m4a",
  20                 u"md5": u"96ce57f24389fc8734ce47f4c1abcc55",
  21                 u"info_dict": {
  22                     u"title": u"youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
  23                     u"uploader_id": u"ytdl"
  24                 }
  25             },
  26             {
  27                 u"file": u"11885608.m4a",
  28                 u"md5": u"4ab26f05c1f7291ea460a3920be8021f",
  29                 u"info_dict": {
  30                     u"title": u"youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
  31                     u"uploader_id": u"ytdl"
  32                 }
  33             },
  34             {
  35                 u"file": u"11885679.m4a",
  36                 u"md5": u"d30b5b5f74217410f4689605c35d1fd7",
  37                 u"info_dict": {
  38                     u"title": u"youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
  39                     u"uploader_id": u"ytdl"
  40                 }
  41             },
  42             {
  43                 u"file": u"11885680.m4a",
  44                 u"md5": u"4eb0a669317cd725f6bbd336a29f923a",
  45                 u"info_dict": {
  46                     u"title": u"youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
  47                     u"uploader_id": u"ytdl"
  48                 }
  49             },
  50             {
  51                 u"file": u"11885682.m4a",
  52                 u"md5": u"1893e872e263a2705558d1d319ad19e8",
  53                 u"info_dict": {
  54                     u"title": u"PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
  55                     u"uploader_id": u"ytdl"
  56                 }
  57             },
  58             {
  59                 u"file": u"11885683.m4a",
  60                 u"md5": u"b673c46f47a216ab1741ae8836af5899",
  61                 u"info_dict": {
  62                     u"title": u"PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
  63                     u"uploader_id": u"ytdl"
  64                 }
  65             },
  66             {
  67                 u"file": u"11885684.m4a",
  68                 u"md5": u"1d74534e95df54986da7f5abf7d842b7",
  69                 u"info_dict": {
  70                     u"title": u"phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
  71                     u"uploader_id": u"ytdl"
  72                 }
  73             },
  74             {
  75                 u"file": u"11885685.m4a",
  76                 u"md5": u"f081f47af8f6ae782ed131d38b9cd1c0",
  77                 u"info_dict": {
  78                     u"title": u"phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
  79                     u"uploader_id": u"ytdl"
  80                 }
  81             }
  82         ]
  83     }
  84
  85
  86     def _real_extract(self, url):
  87         mobj = re.match(self._VALID_URL, url)
  88         if mobj is None:
  89             raise ExtractorError(u'Invalid URL: %s' % url)
  90         playlist_id = mobj.group('id')
  91
  92         webpage = self._download_webpage(url, playlist_id)
  93
  94         json_like = self._search_regex(r"PAGE.mix = (.*?);\n", webpage, u'trax information', flags=re.DOTALL)
  95         data = json.loads(json_like)
  96
  97         session = str(random.randint(0, 1000000000))
  98         mix_id = data['id']
  99         track_count = data['tracks_count']
 100         first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
 101         next_url = first_url
 102         res = []
 103         for i in range(track_count):
 104             api_json = self._download_webpage(next_url, playlist_id,
 105                 note=u'Downloading song information %s/%s' % (str(i+1), track_count),
 106                 errnote=u'Failed to download song information')
 107             api_data = json.loads(api_json)
 108             track_data = api_data[u'set']['track']
 109             info = {
 110                 'id': track_data['id'],
 111                 'url': track_data['track_file_stream_url'],
 112                 'title': track_data['performer'] + u' - ' + track_data['name'],
 113                 'raw_title': track_data['name'],
 114                 'uploader_id': data['user']['login'],
 115                 'ext': 'm4a',
 116             }
 117             res.append(info)
 118             next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id'])
 119         return res