in web-qa.py [0:0]
def get_hyperlinks(url):
# Try to open the URL and read the HTML
try:
# Open the URL and read the HTML
with urllib.request.urlopen(url) as response:
# If the response is not HTML, return an empty list
if not response.info().get('Content-Type').startswith("text/html"):
return []
# Decode the HTML
html = response.read().decode('utf-8')
except Exception as e:
print(e)
return []
# Create the HTML Parser and then Parse the HTML to get hyperlinks
parser = HyperlinkParser()
parser.feed(html)
return parser.hyperlinks