Merge pull request #6428 from dstftw/improve-generic-smil-support

[youtube-dl] / youtube_dl / extractor / common.py

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index f9578b8380cfcaa1d63a7688307ef231d5691d75..def6caa0d1eb320a091ecaecc50db58b82d4f28d 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -638,7 +638,7 @@ class InfoExtractor(object):
     @staticmethod
     def _meta_regex(prop):
         return r'''(?isx)<meta
-                    (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
+                    (?=[^>]+(?:itemprop|name|property|id)=(["\']?)%s\1)
                     [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(prop)
 
     def _og_search_property(self, prop, html, name=None, **kargs):
@@ -999,8 +999,7 @@ class InfoExtractor(object):
             assert not fatal
             return []
 
-        namespace = self._search_regex(
-            r'{([^}]+)?}smil', smil.tag, 'namespace', default=None)
+        namespace = self._parse_smil_namespace(smil)
 
         return self._parse_smil_formats(
             smil, smil_url, video_id, namespace=namespace, f4m_params=f4m_params)
@@ -1017,8 +1016,7 @@ class InfoExtractor(object):
             'Unable to download SMIL file', fatal=fatal)
 
     def _parse_smil(self, smil, smil_url, video_id, f4m_params=None):
-        namespace = self._search_regex(
-            r'{([^}]+)?}smil', smil.tag, 'namespace', default=None)
+        namespace = self._parse_smil_namespace(smil)
 
         formats = self._parse_smil_formats(
             smil, smil_url, video_id, namespace=namespace, f4m_params=f4m_params)
@@ -1045,6 +1043,10 @@ class InfoExtractor(object):
             'subtitles': subtitles,
         }
 
+    def _parse_smil_namespace(self, smil):
+        return self._search_regex(
+            r'(?i)^{([^}]+)?}smil$', smil.tag, 'namespace', default=None)
+
     def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None):
         base = smil_url
         for meta in smil.findall(self._xpath_ns('./head/meta', namespace)):
@@ -1101,7 +1103,7 @@ class InfoExtractor(object):
                         'plugin': 'flowplayer-3.2.0.1',
                     }
                 f4m_url += '&' if '?' in f4m_url else '?'
-                f4m_url += compat_urllib_parse.urlencode(f4m_params).encode('utf-8')
+                f4m_url += compat_urllib_parse.urlencode(f4m_params)
                 formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds'))
                 continue