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

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5 import time
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     compat_urllib_parse,
  10     compat_urllib_request,
  11
  12     ExtractorError,
  13 )
  14
  15
  16 class HypemIE(InfoExtractor):
  17     _VALID_URL = r'http://(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
  18     _TEST = {
  19         'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
  20         'md5': 'b9cc91b5af8995e9f0c1cee04c575828',
  21         'info_dict': {
  22             'id': '1v6ga',
  23             'ext': 'mp3',
  24             'title': 'Tame',
  25             'uploader': 'BODYWORK',
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         track_id = mobj.group(1)
  32
  33         data = {'ax': 1, 'ts': time.time()}
  34         data_encoded = compat_urllib_parse.urlencode(data)
  35         complete_url = url + "?" + data_encoded
  36         request = compat_urllib_request.Request(complete_url)
  37         response, urlh = self._download_webpage_handle(
  38             request, track_id, 'Downloading webpage with the url')
  39         cookie = urlh.headers.get('Set-Cookie', '')
  40
  41         html_tracks = self._html_search_regex(
  42             r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>',
  43             response, 'tracks')
  44         try:
  45             track_list = json.loads(html_tracks)
  46             track = track_list['tracks'][0]
  47         except ValueError:
  48             raise ExtractorError('Hypemachine contained invalid JSON.')
  49
  50         key = track['key']
  51         track_id = track['id']
  52         artist = track['artist']
  53         title = track['song']
  54
  55         serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key)
  56         request = compat_urllib_request.Request(
  57             serve_url, '', {'Content-Type': 'application/json'})
  58         request.add_header('cookie', cookie)
  59         song_data = self._download_json(request, track_id, 'Downloading metadata')
  60         final_url = song_data["url"]
  61
  62         return {
  63             'id': track_id,
  64             'url': final_url,
  65             'ext': 'mp3',
  66             'title': title,
  67             'uploader': artist,
  68         }