CCCPaste

ac67925ad0932

# To run this, download the BeautifulSoup zip file
# http://www.py4e.com/code3/bs4.zip
# or pip install beautifulsoup4 to ensure you have the latest version
# and unzip it in the same directory as this file

import urllib.request, urllib.parse, urllib.error
from bs4 import BeautifulSoup
import ssl # defauts to certicate verification and most secure protocol (now TLS)

# Ignore SSL/TLS certificate errors
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE

url = input('Enter - ')
html = urllib.request.urlopen(url, context=ctx).read()
soup = BeautifulSoup(html, 'html.parser')
#Follow link at below position
count=17
#Follow link this many times
times=6
# Retrieve all of the anchor tags
tags = soup('a')
lst = list()

for tag in tags:
    #print(tag.get('href', None))
    lst.append(tag.get('href', None))
print(lst[count])

for i in range(times):
    url = lst[count]
    html = urllib.request.urlopen(url, context=ctx).read()
    soup = BeautifulSoup(html, 'html.parser')
    
# Retrieve all of the anchor tags
    tags = soup('a')
    lst = list()
    
    for tag in tags:
    #print(tag.get('href', None))
        lst.append(tag.get('href', None))
    print(lst[count])