youtube-dl

commit 94c1255782414cdcda565717e31c91734ec00990
parent 476e1095fac398b648f953a826ed3b191ce8d5d7
Author: Sergey M․ <dstftw@gmail.com>
Date:   Tue, 14 Apr 2015 17:50:53 +0600

[brightcove] Handle non well-formed XMLs (#5421)

Diffstat:
M
youtube_dl/extractor/brightcove.py
 | 
7
+++++--

1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py
@@ -117,7 +117,10 @@ class BrightcoveIE(InfoExtractor):
         object_str = re.sub(r'(<object[^>]*)(xmlns=".*?")', r'\1', object_str)
         object_str = fix_xml_ampersands(object_str)
 
-        object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
+        try:
+            object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
+        except xml.etree.ElementTree.ParseError:
+            return
 
         fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
         if fv_el is not None:
@@ -185,7 +188,7 @@ class BrightcoveIE(InfoExtractor):
                 [^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
             ).+?>\s*</object>''',
             webpage)
-        return [cls._build_brighcove_url(m) for m in matches]
+        return filter(None, [cls._build_brighcove_url(m) for m in matches])
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})