style and error handling edits to HypemIE

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index a6294e1e1823bb3c47a8860f6986c7a09f57c92f..b40edf5fbb92f6cf86fc7f96b3d99346b61523a6 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -4483,6 +4483,58 @@ class XHamsterIE(InfoExtractor):
             'thumbnail': video_thumbnail
         }]
 
+class HypemIE(InfoExtractor):
+    """Information Extractor for hypem"""
+    _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+        track_id = mobj.group(1)
+
+        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, u'Downloading webpage with the url')
+        cookie = urlh.headers.get('Set-Cookie', '')
+
+        self.report_extraction(track_id)
+        mobj = re.search(r'<script type="application/json" id="displayList-data">(.*?)</script>', response, flags=re.MULTILINE|re.DOTALL)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extrack tracks')
+        html_tracks = mobj.group(1).strip()
+        try:
+            track_list = json.loads(html_tracks)
+            track = track_list[u'tracks'][0]
+        except ValueError:
+            raise ExtractorError(u'Hypemachine contained invalid JSON.')
+
+        key = track[u"key"]
+        track_id = track[u"id"]
+        artist = track[u"artist"]
+        title = track[u"song"]
+
+        serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key))
+        request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'})
+        request.add_header('cookie', cookie)
+        song_data_json = self._download_webpage(request, track_id, u'Downloading metadata')
+        try:
+            song_data = json.loads(song_data_json)
+        except ValueError:
+            raise ExtractorError(u'Hypemachine contained invalid JSON.')
+        final_url = song_data[u"url"]
+
+        return [{
+            'id':       track_id,
+            'url':      final_url,
+            'ext':      "mp3",
+            'title':    title,
+            'artist':   artist,
+        }]
+
+
 def gen_extractors():
     """ Return a list of an instance of every supported extractor.
     The order does matter; the first extractor matched is the one handling the URL.
@@ -4545,6 +4597,7 @@ def gen_extractors():
         FlickrIE(),
         TeamcocoIE(),
         XHamsterIE(),
+        HypemIE(),
         GenericIE()
     ]