Merge tag 'upstream/2013.12.23'

[youtubedl] / youtube_dl / extractor / escapist.py

diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py
index 86b145bca9d9da95024525be3f4b5cf441b36b58..b1242f6bc457a41a9c8413eb851671acd05cc8c0 100644 (file)
--- a/youtube_dl/extractor/escapist.py
+++ b/youtube_dl/extractor/escapist.py
@@ -11,58 +11,74 @@ from ..utils import (
 
 
 class EscapistIE(InfoExtractor):
 
 
 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'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", 
+            u"title": u"Breaking Down Baldur's Gate"
+        }
+    }

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     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)
 
         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)
 
             webpage, u'description', fatal=False)
 

-        imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
-            webpage, u'thumbnail', fatal=False)
-
-        playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
-            webpage, u'player url')
+        playerUrl = self._og_search_video_url(webpage, name=u'player URL')

 
 

-        title = self._html_search_regex('<meta name="title" content="([^"]*)"',
-            webpage, u'player url').split(' : ')[-1]
+        title = self._html_search_regex(
+            r'<meta name="title" content="([^"]*)"',
+            webpage, u'title').split(' : ')[-1]

 
 

-        configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
+        configUrl = self._search_regex('config=(.*)$', playerUrl, u'config URL')

         configUrl = compat_urllib_parse.unquote(configUrl)
 
         configUrl = compat_urllib_parse.unquote(configUrl)
 

-        configJSON = self._download_webpage(configUrl, videoId,
-                                            u'Downloading configuration',
-                                            u'unable to download configuration')
-
-        # Technically, it's JavaScript, not JSON
-        configJSON = configJSON.replace("'", '"')
-
+        formats = []
+
+        def _add_format(name, cfgurl):
+            configJSON = self._download_webpage(
+                cfgurl, videoId,
+                u'Downloading ' + name + ' configuration',
+                u'Unable to download ' + name + ' configuration')
+
+            # Technically, it's JavaScript, not JSON
+            configJSON = configJSON.replace("'", '"')
+
+            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,
+            })
+
+        _add_format(u'normal', configUrl)
+        hq_url = (configUrl +
+                  ('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))

         try:
         try:

-            config = json.loads(configJSON)
-        except (ValueError,) as err:
-            raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
-
-        playlist = config['playlist']
-        videoUrl = playlist[1]['url']
+            _add_format(u'hq', hq_url)
+        except ExtractorError:
+            pass  # That's fine, we'll just use normal quality

 
 

-        info = {
+        return {

             'id': videoId,
             'id': videoId,

-            'url': videoUrl,
+            'formats': formats,

             'uploader': showName,
             'uploader': showName,

-            'upload_date': None,

             'title': title,
             'title': title,

-            'ext': 'mp4',
-            'thumbnail': imgUrl,
+            'thumbnail': self._og_search_thumbnail(webpage),

             'description': videoDesc,
             'player_url': playerUrl,
         }
             'description': videoDesc,
             'player_url': playerUrl,
         }

-
-        return [info]