]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/hypem.py
Prepare to upload
[youtubedl] / youtube_dl / extractor / hypem.py
index 6d0d847c6d3461a02c6eab71b24848247e9678ab..9ca28d632eb2199b770159cfd3d6a60fd2db5db1 100644 (file)
@@ -1,20 +1,11 @@
 from __future__ import unicode_literals
 
-import json
-import re
-import time
-
 from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse,
-    compat_urllib_request,
-
-    ExtractorError,
-)
+from ..utils import int_or_none
 
 
 class HypemIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?hypem\.com/track/(?P<id>[0-9a-z]{5})'
     _TEST = {
         'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
         'md5': 'b9cc91b5af8995e9f0c1cee04c575828',
@@ -23,46 +14,36 @@ class HypemIE(InfoExtractor):
             'ext': 'mp3',
             'title': 'Tame',
             'uploader': 'BODYWORK',
+            'timestamp': 1371810457,
+            'upload_date': '20130621',
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        track_id = mobj.group(1)
+        track_id = self._match_id(url)
 
-        data = {'ax': 1, 'ts': time.time()}
-        data_encoded = compat_urllib_parse.urlencode(data)
-        complete_url = url + "?" + data_encoded
-        request = compat_urllib_request.Request(complete_url)
-        response, urlh = self._download_webpage_handle(
-            request, track_id, 'Downloading webpage with the url')
-        cookie = urlh.headers.get('Set-Cookie', '')
+        response = self._download_webpage(url, track_id)
 
-        html_tracks = self._html_search_regex(
-            r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>',
-            response, 'tracks')
-        try:
-            track_list = json.loads(html_tracks)
-            track = track_list['tracks'][0]
-        except ValueError:
-            raise ExtractorError('Hypemachine contained invalid JSON.')
+        track = self._parse_json(self._html_search_regex(
+            r'(?s)<script\s+type="application/json"\s+id="displayList-data">(.+?)</script>',
+            response, 'tracks'), track_id)['tracks'][0]
 
-        key = track['key']
         track_id = track['id']
-        artist = track['artist']
         title = track['song']
 
-        serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key)
-        request = compat_urllib_request.Request(
-            serve_url, '', {'Content-Type': 'application/json'})
-        request.add_header('cookie', cookie)
-        song_data = self._download_json(request, track_id, 'Downloading metadata')
-        final_url = song_data["url"]
+        final_url = self._download_json(
+            'http://hypem.com/serve/source/%s/%s' % (track_id, track['key']),
+            track_id, 'Downloading metadata', headers={
+                'Content-Type': 'application/json'
+            })['url']
 
         return {
             'id': track_id,
             'url': final_url,
             'ext': 'mp3',
             'title': title,
-            'uploader': artist,
+            'uploader': track.get('artist'),
+            'duration': int_or_none(track.get('time')),
+            'timestamp': int_or_none(track.get('ts')),
+            'track': title,
         }