[escapist] Add support for HD format (Closes #1755)
authorPhilipp Hagemeister <phihag@phihag.de>
Wed, 20 Nov 2013 05:47:50 +0000 (06:47 +0100)
committerPhilipp Hagemeister <phihag@phihag.de>
Wed, 20 Nov 2013 05:52:08 +0000 (06:52 +0100)
youtube_dl/extractor/escapist.py

index 3aa2da52c0117bc9926df9c250eeb70da6cc2299..f9681fd436944ec7fa937d96e57a1d30ed63aefc 100644 (file)
@@ -11,11 +11,11 @@ from ..utils import (
 
 
 class EscapistIE(InfoExtractor):
-    _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+    _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
     _TEST = {
         u'url': u'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
         u'file': u'6618-Breaking-Down-Baldurs-Gate.mp4',
-        u'md5': u'c6793dbda81388f4264c1ba18684a74d',
+        u'md5': u'ab3a706c681efca53f0a35f1415cf0d1',
         u'info_dict': {
             u"description": u"Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.", 
             u"uploader": u"the-escapist-presents", 
@@ -25,50 +25,61 @@ class EscapistIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         showName = mobj.group('showname')
         videoId = mobj.group('episode')
 
         self.report_extraction(videoId)
         webpage = self._download_webpage(url, videoId)
 
-        videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
+        videoDesc = self._html_search_regex(
+            r'<meta name="description" content="([^"]*)"',
             webpage, u'description', fatal=False)
 
         playerUrl = self._og_search_video_url(webpage, name='player url')
 
-        title = self._html_search_regex('<meta name="title" content="([^"]*)"',
+        title = self._html_search_regex(
+            'r<meta name="title" content="([^"]*)"',
             webpage, u'player url').split(' : ')[-1]
 
         configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
         configUrl = compat_urllib_parse.unquote(configUrl)
 
-        configJSON = self._download_webpage(configUrl, videoId,
-                                            u'Downloading configuration',
-                                            u'unable to download configuration')
+        formats = []
 
-        # Technically, it's JavaScript, not JSON
-        configJSON = configJSON.replace("'", '"')
+        def _add_format(name, cfgurl):
+            configJSON = self._download_webpage(
+                cfgurl, videoId,
+                u'Downloading ' + name + ' configuration',
+                u'Unable to download ' + name + ' configuration')
 
-        try:
-            config = json.loads(configJSON)
-        except (ValueError,) as err:
-            raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
+            # Technically, it's JavaScript, not JSON
+            configJSON = configJSON.replace("'", '"')
 
-        playlist = config['playlist']
-        videoUrl = playlist[1]['url']
+            try:
+                config = json.loads(configJSON)
+            except (ValueError,) as err:
+                raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
+            playlist = config['playlist']
+            formats.append({
+                'url': playlist[1]['url'],
+                'format_id': name,
+            })
 
-        info = {
+        _add_format(u'normal', configUrl)
+        try:
+            hq_url = (configUrl +
+                      ('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))
+            try:
+                _add_format(u'hq', hq_url)
+            except ExtractorError:
+                pass  # That's fine, we'll just use normal quality
+
+        return {
             'id': videoId,
-            'url': videoUrl,
+            'formats': formats,
             'uploader': showName,
-            'upload_date': None,
             'title': title,
-            'ext': 'mp4',
             'thumbnail': self._og_search_thumbnail(webpage),
             'description': videoDesc,
             'player_url': playerUrl,
         }
-
-        return [info]