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 37f9c1449d5be600ff2b42748cfbef122cf0952c..b40edf5fbb92f6cf86fc7f96b3d99346b61523a6 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -4425,6 +4425,115 @@ class TeamcocoIE(InfoExtractor):
             'thumbnail':   thumbnail,
             'description': description,
         }]
+        
+class XHamsterIE(InfoExtractor):
+    """Information Extractor for xHamster"""
+    _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
+
+    def _real_extract(self,url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('id')
+        mrss_url='http://xhamster.com/movies/%s/.html' % video_id
+        webpage = self._download_webpage(mrss_url, video_id)
+        mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract media URL')
+        if len(mobj.group('server')) == 0:
+            video_url = compat_urllib_parse.unquote(mobj.group('file'))
+        else:
+            video_url = mobj.group('server')+'/key='+mobj.group('file')
+        video_extension = video_url.split('.')[-1]
+
+        mobj = re.search(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract title')
+        video_title = unescapeHTML(mobj.group('title'))
+
+        mobj = re.search(r'<span>Description: </span>(?P<description>[^<]+)', webpage)
+        if mobj is None:
+            video_description = u''
+        else:
+            video_description = unescapeHTML(mobj.group('description'))
+
+        mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract upload date')
+        video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
+
+        mobj = re.search(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^>]+)', webpage)
+        if mobj is None:
+            video_uploader_id = u'anonymous'
+        else:
+            video_uploader_id = mobj.group('uploader_id')
+
+        mobj = re.search(r'\'image\':\'(?P<thumbnail>[^\']+)\'', webpage)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract thumbnail URL')
+        video_thumbnail = mobj.group('thumbnail')
+
+        return [{
+            'id':       video_id,
+            'url':      video_url,
+            'ext':      video_extension,
+            'title':    video_title,
+            'description': video_description,
+            'upload_date': video_upload_date,
+            'uploader_id': video_uploader_id,
+            '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.
@@ -4487,6 +4596,8 @@ def gen_extractors():
         VineIE(),
         FlickrIE(),
         TeamcocoIE(),
+        XHamsterIE(),
+        HypemIE(),
         GenericIE()
     ]