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:
"""Return a list of all Brightcove URLs from the webpage """
url_m = re.search(
- r'<meta\s+property="og:video"\s+content="(https?://(?:secure|c)\.brightcove.com/[^"]+)"',
+ r'<meta\s+property=[\'"]og:video[\'"]\s+content=[\'"](https?://(?:secure|c)\.brightcove.com/[^\'"]+)[\'"]',
webpage)
if url_m:
url = unescapeHTML(url_m.group(1))
[^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
).+?>\s*</object>''',
webpage)
- return [cls._build_brighcove_url(m) for m in matches]
+ return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})