Web Scraping with BeautifulSoup

scrapurl.py

#!/usr/bin/python
# -*- coding: utf-8 -*-

# Codelatte Team
# https://codelatte.org/
# Usage: python3 scrapurl.py https://yoursite.com/

import sys
import requests
from urllib.request import urlparse, urljoin
from bs4 import BeautifulSoup
import colorama

colorama.init()
GREEN = colorama.Fore.GREEN
RESET = colorama.Fore.RESET

internal_urls = set()
external_urls = set()

def is_valid(url):
    parsed = urlparse(url)
    return bool(parsed.netloc) and bool(parsed.scheme)

def get_all_website_links(url):
    urls = set()
    domain_name = urlparse(url).netloc
    soup = BeautifulSoup(requests.get(url).content, "html.parser")

    for a_tag in soup.findAll("a"):
        href = a_tag.attrs.get("href")
        if href == "" or href is None:
            continue
        href = urljoin(url, href)
        parsed_href = urlparse(href)
        if not is_valid(href):
            continue
        if href in internal_urls:
            continue
        if domain_name not in href:
            if href not in external_urls:
                print(f"{RESET}[!] External link: {href}")
                external_urls.add(href)
            continue
        print(f"{GREEN}[*] Internal link: {href}{RESET}")
        urls.add(href)
        internal_urls.add(href)
    return urls

total_urls_visited = 0

def crawl(url, max_urls=50):
    global total_urls_visited
    total_urls_visited += 1
    links = get_all_website_links(url)
    for link in links:
        if total_urls_visited > max_urls:
            break
        crawl(link, max_urls=max_urls)

if __name__ == "__main__":
    crawl(sys.argv[1])
    print("[+] Total External links:", len(external_urls))
    print("[+] Total Internal links:", len(internal_urls))
    print("[+] Total:", len(external_urls) + len(internal_urls))