The python script is continuously running

Question

I am trying to build a web crawler to extract all the links on a webpage. I have created 2 python files. (class: scanner.py and object: vulnerability-scanner.py). When I run the script, it is continuously running without stopping. I am unable to find the error. Help me to solve this.

Here is my source code:

scanner.py

import requests
from urllib.parse import urlparse, urljoin
from bs4 import BeautifulSoup
import colorama

class Scanner:

    colorama.init()

    def __init__(self, url):
        self.target_url = url
        self.target_links = []

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

    def get_all_website_links(self, url):

        GREEN = colorama.Fore.GREEN
        WHITE = colorama.Fore.WHITE
        RESET = colorama.Fore.RESET

        urls = set()
        internal_urls = set()
        external_urls = set()
        domain_name = urlparse(url).netloc
        response = requests.get(url)
        soup = BeautifulSoup(response.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)
            href = parsed_href.scheme + "://" + parsed_href.netloc + parsed_href.path

            if not self.is_valid(href):
                continue
            if href in internal_urls:
                continue
            if domain_name not in href:
                if href not in external_urls:
                    print(f"{WHITE}[*] External link: {href}{RESET}")
                    external_urls.add(href)
                continue
            print(f"{GREEN}[*] Internal link: {href}{RESET}")
            urls.add(href)
            internal_urls.add(href)
        return urls

    def crawl(self, url):
        href_links = self.get_all_website_links(url)
        for link in href_links:
            print(link)
            self.crawl(link)

vulnerability-scanner.py

import argu

target_url = "https://hack.me/"
vul_scanner = argu.Scanner(target_url)
vul_scanner.crawl(target_url)

Answer 1

The following part is (almost) an infinite recursion:

for link in href_links:
    print(link)
    self.crawl(link)

I believe you added this on the notion of crawling the links in the page. But you didn't put a stopping condition. (Although currently, it seems like your only stopping condition is if there is a crawled page with no links at all).

One stopping condition might be to set a predefined number of "max" levels to crawl.

Something like this in your init function:

def __init__(self, url):
    self.target_url = url
    self.target_links = []
    self.max_parse_levels = 5 #you can go a step further and make this as an input to the constructore (i.e. __init__ function)
    self.cur_parse_levels = 0
.
.
.

def crawl(url):
    if self.cur_parse_levels > self.max_parse_levels:
        return
    for link in href_links:
        print(link)
        self.crawl(link)