def magic_probe(start_url, timeout=None, config=None):
form_url = url_with_slash = url_without_slash = None
resp = urllib2.urlopen(start_url, timeout=timeout)
url = resp.geturl()
for link in _link_re.findall(resp.read()):
if link[0] in "\"'":
link = link[1:-1]
link = urlparse.urljoin(url, link)
if urlparse.urlsplit(link).netloc == urlparse.urlsplit(url).netloc:
if url_with_slash is None and link.endswith("/") and link != url:
url_with_slash = link
elif url_without_slash is None and not link.endswith("/"):
url_without_slash = link
if form_url is None:
try:
form_resp = urllib.urlopen(link).read()
if "<form" in form_resp:
form_url = link
except IOError:
pass
return url, probe_website(url, form_url, url_with_slash, url_without_slash, timeout, config)
def magic_probe(start_url, timeout=None, config=None):
form_url = url_with_slash = url_without_slash = None
resp = urllib2.urlopen(start_url, timeout=timeout)
url = resp.geturl()
for link in _link_re.findall(resp.read()):
if link[0] in '"\'':
link = link[1:-1]
link = urlparse.urljoin(url, link)
if urlparse.urlsplit(link).netloc == urlparse.urlsplit(url).netloc:
if url_with_slash is None and link.endswith('/') and link != url:
url_with_slash = link
elif url_without_slash is None and not link.endswith('/'):
url_without_slash = link
if form_url is None:
try:
form_resp = urllib.urlopen(link).read()
if '<form' in form_resp:
form_url = link
except IOError:
pass
return url, probe_website(url, form_url, url_with_slash, url_without_slash,
timeout, config)
def runtest(caption, url, *args, **kwargs):
print_results(caption, url, probe_website(url, *args, **kwargs))
def runtest(caption, url, *args, **kwargs):
print_results(caption, url, probe_website(url, *args, **kwargs))
