try:
content_type = headers["Content-Type"]
try:
- content_type, charset = content_type.split(';')
+ content_type, charset = content_type.split(';', 1)
content_type = content_type.strip()
charset = charset.split('=')[1].strip()
self.log(" HTTP charset : %s" % charset)
except (ValueError, IndexError):
charset = None
self.log(" no charset in Content-Type header")
- if content_type == "text/html":
+ if content_type in ("text/html", "application/xhtml+xml"):
parser = parse_html(fname, charset, self.log)
bookmark.real_title = parser.title
if parser.refresh: