Support for The Escapist
authorPhilipp Hagemeister <phihag@phihag.de>
Wed, 14 Sep 2011 20:26:53 +0000 (22:26 +0200)
committerPhilipp Hagemeister <phihag@phihag.de>
Wed, 14 Sep 2011 20:26:53 +0000 (22:26 +0200)
youtube-dl

index 5aff9c08c1aab97a14909e76a0cb042f78345d6a..719edeb9b557caf4bf345cea0dc3066acfc64e39 100755 (executable)
@@ -23,6 +23,7 @@ import cookielib
 import datetime
 import gzip
 import htmlentitydefs
+import HTMLParser
 import httplib
 import locale
 import math
@@ -3189,6 +3190,93 @@ class ComedyCentralIE(InfoExtractor):
                                continue
 
 
+class EscapistIE(InfoExtractor):
+       """Information extractor for The Escapist """
+
+       _VALID_URL = r'^(https?://)?(www\.)escapistmagazine.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?].*$'
+
+       @staticmethod
+       def suitable(url):
+               return (re.match(EscapistIE._VALID_URL, url) is not None)
+
+       def report_extraction(self, showName):
+               self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
+
+       def report_config_download(self, showName):
+               self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
+
+       def _simplify_title(self, title):
+               res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+               res = res.strip(ur'_')
+               return res
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+               showName = mobj.group('showname')
+               videoId = mobj.group('episode')
+
+               self.report_extraction(showName)
+               try:
+                       webPage = urllib2.urlopen(url).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
+                       return
+
+               descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
+               description = htmlParser.unescape(descMatch.group(1))
+               imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
+               imgUrl = htmlParser.unescape(imgMatch.group(1))
+               playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
+               playerUrl = htmlParser.unescape(playerUrlMatch.group(1))
+               configUrlMatch = re.search('config=(.*)$', playerUrl)
+               configUrl = urllib2.unquote(configUrlMatch.group(1))
+
+               self.report_config_download(showName)
+               try:
+                       configJSON = urllib2.urlopen(configUrl).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download configuration: ' + unicode(err))
+                       return
+
+               # Technically, it's JavaScript, not JSON
+               configJSON = configJSON.replace("'", '"')
+
+               try:
+                       config = json.loads(configJSON)
+               except (ValueError,), err:
+                       self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + unicode(err))
+                       return
+
+               playlist = config['playlist']
+               videoUrl = playlist[1]['url']
+
+               self._downloader.increment_downloads()
+               info = {
+                       'id': videoId,
+                       'url': videoUrl,
+                       'uploader': showName,
+                       'upload_date': None,
+                       'title': showName,
+                       'stitle': self._simplify_title(showName),
+                       'ext': 'flv',
+                       'format': 'flv',
+                       'thumbnail': imgUrl,
+                       'description': description,
+                       'player_url': playerUrl,
+               }
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download ' + videoId)
+
+
+
 class PostProcessor(object):
        """Post Processor class.
 
@@ -3611,6 +3699,7 @@ def main():
                VimeoIE(),
                MyVideoIE(),
                ComedyCentralIE(),
+               EscapistIE(),
 
                GenericIE()
        ]