Raphaël G. Git Repositories - youtubedl/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         mobj = re.match(self._VALID_URL, url)
 107         playlist_id = mobj.group('id')
 108
 109         webpage = self._download_webpage(url, playlist_id)
 110
 111         json_like = self._search_regex(
 112             r"(?s)PAGE.mix = (.*?);\n", webpage, 'trax information')
 113         data = json.loads(json_like)
 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         first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
 121         next_url = first_url
 122         entries = []
 123
 124         for i in range(track_count):
 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                         self._sleep(avg_song_duration, playlist_id)
 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'] + ' - ' + 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         }