[auengine] Modernize

youtube_dl/extractor/auengine.py

@@ -11,22 +11,24 @@
 
 
 class AUEngineIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?auengine\.com/embed\.php\?.*?file=(?P<id>[^&]+).*?'
+
     _TEST = {
         'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
-        'file': 'lfvlytY6.mp4',
         'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
         'info_dict': {
+            'id': 'lfvlytY6',
+            'ext': 'mp4',
             'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
         }
     }
-    _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?'
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')
+
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
+        title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title')
-                webpage, 'title')
         title = title.strip()
         links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
         links = map(compat_urllib_parse.unquote, links)
@@ -39,7 +41,7 @@ def _real_extract(self, url):
             elif '/videos/' in link:
                 video_url = link
         if not video_url:
-            raise ExtractorError(u'Could not find video URL')
+            raise ExtractorError('Could not find video URL')
         ext = '.' + determine_ext(video_url)
         if ext == title[-len(ext):]:
             title = title[:-len(ext)]

youtube_dl/extractor/cspan.py

@@ -56,16 +56,61 @@ def _real_extract(self, url):
 
         url = unescapeHTML(data['video']['files'][0]['path']['#text'])
 
-        doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
+        doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id + '&version=2014-01-23',
             video_id)
 
-        def find_string(s):
+        formats = [
-            return find_xpath_attr(doc, './/string', 'name', s).text
+            {
+                'url': url,
+            }
+        ]
+
+        def find_string(node, s):
+            return find_xpath_attr(node, './/string', 'name', s).text
+
+        def find_number(node, s):
+            return int(find_xpath_attr(node, './/number', 'name', s).text)
+
+        def find_array(node, s):
+            return find_xpath_attr(node, './/array', 'name', s)
+
+        def process_files(files, url, formats):
+            for file in files:
+                path = find_string(file, 'path')
+                #duration = find_number(file, './number', 'name', 'length')
+                hd = find_number(file, 'hd')
+                formats.append({
+                    'url': url,
+                    'play_path': path,
+                    'ext': 'flv',
+                    'quality': hd,
+                })
+
+        def process_node(node, formats):
+            url = find_xpath_attr(node, './string', 'name', 'url')
+            if url is None:
+                url = find_xpath_attr(node, './string', 'name', 'URL')
+                if url is None:
+                    return
+            url = url.text.replace('$(protocol)', 'rtmp').replace('$(port)', '1935')
+            files = find_array(node, 'files')
+            if files is None:
+                return
+            process_files(files, url, formats)
+
+        process_node(doc.find('./media-link'), formats)
+
+        streams = find_array(doc, 'streams')
+        if streams is not None:
+            for stream in streams:
+                if find_string(stream, 'name') != 'vod':
+                    continue
+                process_node(stream, formats)
 
         return {
             'id': video_id,
-            'title': find_string('title'),
+            'title': find_string(doc, 'title'),
-            'url': url,
             'description': description,
-            'thumbnail': find_string('poster'),
+            'thumbnail': find_string(doc, 'poster'),
+            'formats': formats,
         }