Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/mixcloud.py

   1 import json
   2 import re
   3 import socket
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_http_client,
   8     compat_str,
   9     compat_urllib_error,
  10     compat_urllib_request,
  11
  12     ExtractorError,
  13 )
  14
  15
  16 class MixcloudIE(InfoExtractor):
  17     _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/
  18     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
  19     IE_NAME = u'mixcloud'
  20
  21     def report_download_json(self, file_id):
  22         """Report JSON download."""
  23         self.to_screen(u'Downloading json')
  24
  25     def get_urls(self, jsonData, fmt, bitrate='best'):
  26         """Get urls from 'audio_formats' section in json"""
  27         try:
  28             bitrate_list = jsonData[fmt]
  29             if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
  30                 bitrate = max(bitrate_list) # select highest
  31
  32             url_list = jsonData[fmt][bitrate]
  33         except TypeError: # we have no bitrate info.
  34             url_list = jsonData[fmt]
  35         return url_list
  36
  37     def check_urls(self, url_list):
  38         """Returns 1st active url from list"""
  39         for url in url_list:
  40             try:
  41                 compat_urllib_request.urlopen(url)
  42                 return url
  43             except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error):
  44                 url = None
  45
  46         return None
  47
  48     def _print_formats(self, formats):
  49         print('Available formats:')
  50         for fmt in formats.keys():
  51             for b in formats[fmt]:
  52                 try:
  53                     ext = formats[fmt][b][0]
  54                     print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]))
  55                 except TypeError: # we have no bitrate info
  56                     ext = formats[fmt][0]
  57                     print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]))
  58                     break
  59
  60     def _real_extract(self, url):
  61         mobj = re.match(self._VALID_URL, url)
  62         if mobj is None:
  63             raise ExtractorError(u'Invalid URL: %s' % url)
  64         # extract uploader & filename from url
  65         uploader = mobj.group(1).decode('utf-8')
  66         file_id = uploader + "-" + mobj.group(2).decode('utf-8')
  67
  68         # construct API request
  69         file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
  70         # retrieve .json file with links to files
  71         request = compat_urllib_request.Request(file_url)
  72         try:
  73             self.report_download_json(file_url)
  74             jsonData = compat_urllib_request.urlopen(request).read()
  75         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
  76             raise ExtractorError(u'Unable to retrieve file: %s' % compat_str(err))
  77
  78         # parse JSON
  79         json_data = json.loads(jsonData)
  80         player_url = json_data['player_swf_url']
  81         formats = dict(json_data['audio_formats'])
  82
  83         req_format = self._downloader.params.get('format', None)
  84
  85         if self._downloader.params.get('listformats', None):
  86             self._print_formats(formats)
  87             return
  88
  89         if req_format is None or req_format == 'best':
  90             for format_param in formats.keys():
  91                 url_list = self.get_urls(formats, format_param)
  92                 # check urls
  93                 file_url = self.check_urls(url_list)
  94                 if file_url is not None:
  95                     break # got it!
  96         else:
  97             if req_format not in formats:
  98                 raise ExtractorError(u'Format is not available')
  99
 100             url_list = self.get_urls(formats, req_format)
 101             file_url = self.check_urls(url_list)
 102             format_param = req_format
 103
 104         return [{
 105             'id': file_id.decode('utf-8'),
 106             'url': file_url.decode('utf-8'),
 107             'uploader': uploader.decode('utf-8'),
 108             'upload_date': None,
 109             'title': json_data['name'],
 110             'ext': file_url.split('.')[-1].decode('utf-8'),
 111             'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
 112             'thumbnail': json_data['thumbnail_url'],
 113             'description': json_data['description'],
 114             'player_url': player_url.decode('utf-8'),
 115         }]