Add tests to MySpass

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 086aa5da3eeae202caf7fa743029b6863c969048..fe9bd97d0070dfbbee5b0b6904d048ab1935a5b2 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -3967,7 +3967,7 @@ class KeekIE(InfoExtractor):
                 'uploader': uploader
         }
         return [info]
-        
+
 class TEDIE(InfoExtractor):
     _VALID_URL=r'http://www.ted.com/talks/(?P<videoName>\w+)'
     def _real_extract(self, url):
@@ -3992,6 +3992,62 @@ class TEDIE(InfoExtractor):
         }
         return [info]
 
+class MySpassIE(InfoExtractor):
+    _VALID_URL = r'http://www.myspass.de/.*'
+    
+    def _real_extract(self, url):
+        META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
+
+        # video id is the last path element of the URL
+        # usually there is a trailing slash, so also try the second but last
+        url_path = compat_urllib_parse_urlparse(url).path
+        url_parent_path, video_id = os.path.split(url_path)
+        if not video_id:
+            _, video_id = os.path.split(url_parent_path)
+        
+        # get metadata
+        metadata_url = META_DATA_URL_TEMPLATE % video_id
+        metadata_text = self._download_webpage(metadata_url, video_id)
+        metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8'))
+        
+        # extract values from metadata
+        url_flv_el = metadata.find('url_flv')
+        if url_flv_el is None:
+            self._downloader.trouble(u'ERROR: unable to extract download url')
+            return
+        video_url = url_flv_el.text
+        extension = os.path.splitext(video_url)[1][1:]
+        title_el = metadata.find('title')
+        if title_el is None:
+            self._downloader.trouble(u'ERROR: unable to extract title')
+            return
+        title = title_el.text
+        format_id_el = metadata.find('format_id')
+        if format_id_el is None:
+            format = ext
+        else:
+            format = format_id_el.text
+        description_el = metadata.find('description')
+        if description_el is not None:
+            description = description_el.text
+        else:
+            description = None
+        imagePreview_el = metadata.find('imagePreview')
+        if imagePreview_el is not None:
+            thumbnail = imagePreview_el.text
+        else:
+            thumbnail = None
+        info = {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'ext': extension,
+            'format': format,
+            'thumbnail': thumbnail,
+            'description': description
+        }
+        return [info]
+
 def gen_extractors():
     """ Return a list of an instance of every supported extractor.
     The order does matter; the first extractor matched is the one handling the URL.
@@ -4040,6 +4096,7 @@ def gen_extractors():
         EightTracksIE(),
         KeekIE(),
         TEDIE(),
+        MySpassIE(),
         GenericIE()
     ]