http.py 文件源码

def _is_safe_url(url, host):
    # Chrome considers any URL with more than two slashes to be absolute, but
    # urlparse is not so flexible. Treat any url with three slashes as unsafe.
    if url.startswith('///'):
        return False
    url_info = urlparse(url)
    # Forbid URLs like http:///example.com - with a scheme, but without a hostname.
    # In that URL, example.com is not the hostname but, a path component. However,
    # Chrome will still consider example.com to be the hostname, so we must not
    # allow this syntax.
    if not url_info.netloc and url_info.scheme:
        return False
    # Forbid URLs that start with control characters. Some browsers (like
    # Chrome) ignore quite a few control characters at the start of a
    # URL and might consider the URL as scheme relative.
    if unicodedata.category(url[0])[0] == 'C':
        return False
    return ((not url_info.netloc or url_info.netloc == host) and
            (not url_info.scheme or url_info.scheme in ['http', 'https']))