def GetLinks(page_url):
html_string = ''
try:
response = urlopen(page_url)
if 'text/html' in response.getheader('Content-Type'):
html_bytes = response.read()
html_string = html_bytes.decode("utf-8")
finder = LinkFinder(spider.base_url, page_url)
finder.feed(html_string)
except Exception as e:
print(str(e))
return set()
return finder.getLinks()
