Quick and dirty IE for xvideos.com.
authorRogério Brito <rbrito@ime.usp.br>
Thu, 13 Oct 2011 19:44:20 +0000 (16:44 -0300)
committerRogério Brito <rbrito@ime.usp.br>
Thu, 13 Oct 2011 19:44:20 +0000 (16:44 -0300)
youtube-dl

index 38ad999e59dbbd69f7239d80096b889bb90770ef..450da8ebdbeb8f2e8030bcd9be70f6c1149ff6a5 100755 (executable)
@@ -3383,6 +3383,92 @@ class CollegeHumorIE(InfoExtractor):
                        self._downloader.trouble(u'\nERROR: unable to download video')
 
 
+class XVideosIE(InfoExtractor):
+       """Information extractor for xvideos.com"""
+
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
+       IE_NAME = u'xvideos'
+
+       def report_webpage(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+       def _simplify_title(self, title):
+               res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+               res = res.strip(ur'_')
+               return res
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+               video_id = mobj.group(1).decode('utf-8')
+
+               self.report_webpage(video_id)
+
+               request = urllib2.Request(url)
+               try:
+                       webpage = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+                       return
+
+               self.report_extraction(video_id)
+
+
+               # Extract video URL
+               mobj = re.search(r'flv_url=(.+?)&', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video title')
+                       return
+               video_url = urllib2.unquote(mobj.group(1).decode('utf-8'))
+
+
+               # Extract title
+               mobj = re.search(r'<title>(.*?)</title>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video title')
+                       return
+               video_title = mobj.group(1).decode('utf-8')
+
+
+               # Extract video thumbnail
+               mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+                       return
+               video_thumbnail = mobj.group(1).decode('utf-8')
+
+
+
+               self._downloader.increment_downloads()
+               info = {
+                       'id': video_id,
+                       'url': video_url,
+                       'uploader': None,
+                       'upload_date': None,
+                       'title': video_title,
+                       'stitle': self._simplify_title(video_title),
+                       'ext': 'flv',
+                       'format': 'flv',
+                       'thumbnail': video_thumbnail,
+                       'description': None,
+                       'player_url': None,
+               }
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
+
+
 class PostProcessor(object):
        """Post Processor class.
 
@@ -3778,6 +3864,7 @@ def gen_extractors():
                ComedyCentralIE(),
                EscapistIE(),
                CollegeHumorIE(),
+               XVideosIE(),
 
                GenericIE()
        ]