xxxxxxxxxx
# Search for link values within URL input
import urllib.request, urllib.parse, urllib.error
import re
import ssl
# Ignore SSL certificate errors
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
url = "https://docs.python.org"
html = urllib.request.urlopen(url, context=ctx).read()
links = re.findall(b'href="(http[s]?://.*?)"', html)
for link in links:
print(link.decode())
xxxxxxxxxx
import requests
from bs4 import BeautifulSoup
vgm_url = 'https://www.vgmusic.com/music/console/nintendo/nes/'
html_text = requests.get(vgm_url).text
soup = BeautifulSoup(html_text, 'html.parser')