Python Ethical Hacking - VULNERABILITY SCANNER(4)

Extracting & Submitting Forms Automatically

Target website:http://10.0.0.45/dvwa/vulnerabilities/xss_r/

Class Scanner.

#!/usr/bin/env python

import requests
import re
from bs4 import BeautifulSoup
from urllib.parse import urljoin


class Scanner:
    def __init__(self, url, ignore_links):
        self.session = requests.Session()
        self.target_url = url
        self.target_links = []
        self.links_to_ignore = ignore_links

    def extract_links_from(self, url):
        response = self.session.get(url)
        return re.findall('(?:href=")(.*?)"', response.content.decode(errors='ignore'))

    def crawl(self, url=None):
        if url == None:
            url = self.target_url
        href_links = self.extract_links_from(url)
        for link in href_links:
            link = urljoin(url, link)

            if "#" in link:
                link = link.split("#")[0]

            if self.target_url in link and link not in self.target_links and link not in self.links_to_ignore:
                self.target_links.append(link)
                print(link)
                self.crawl(link)

    def extract_forms(self, url):
        response = self.session.get(url)
        parsed_html = BeautifulSoup(response.content.decode(), features="lxml")
        return parsed_html.findAll("form")

    def submit_form(self, form, value, url):
        action = form.get("action")
        post_url = urljoin(url, action)
        method = form.get("method")

        inputs_list = form.findAll("input")
        post_data = {}
        for input in inputs_list:
            input_name = input.get("name")
            input_type = input.get("type")
            input_value = input.get("value")
            if input_type == "text":
                input_value = value

            post_data[input_name] = input_value
        if method == "post":
            return requests.post(post_url, data=post_data)
        return self.session.get(post_url, params=post_data)

Vulnerability scanner.

#!/usr/bin/env python

import scanner

target_url = "http://10.0.0.45/dvwa/"
links_to_ignore = "http://10.0.0.45/dvwa/logout.php"

data_dict = {"username": "admin", "password": "password", "Login": "submit"}

vuln_scanner = scanner.Scanner(target_url, links_to_ignore)
vuln_scanner.session.post("http://10.0.0.45/dvwa/login.php", data=data_dict)

# vuln_scanner.crawl()
forms = vuln_scanner.extract_forms("http://10.0.0.45/dvwa/vulnerabilities/xss_r/")
print(forms)
response = vuln_scanner.submit_form(forms[0], "testtest", "http://10.0.0.45/dvwa/vulnerabilities/xss_r/")
print(response.content.decode())

The program runs fine.

Polish the Class Scanner to a generic scanner.

#!/usr/bin/env python

import requests
import re
from bs4 import BeautifulSoup
from urllib.parse import urljoin


class Scanner:
    def __init__(self, url, ignore_links):
        self.session = requests.Session()
        self.target_url = url
        self.target_links = []
        self.links_to_ignore = ignore_links

    def extract_links_from(self, url):
        response = self.session.get(url)
        return re.findall('(?:href=")(.*?)"', response.content.decode(errors='ignore'))

    def crawl(self, url=None):
        if url == None:
            url = self.target_url
        href_links = self.extract_links_from(url)
        for link in href_links:
            link = urljoin(url, link)

            if "#" in link:
                link = link.split("#")[0]

            if self.target_url in link and link not in self.target_links and link not in self.links_to_ignore:
                self.target_links.append(link)
                print(link)
                self.crawl(link)

    def extract_forms(self, url):
        response = self.session.get(url)
        parsed_html = BeautifulSoup(response.content.decode(), features="lxml")
        return parsed_html.findAll("form")

    def submit_form(self, form, value, url):
        action = form.get("action")
        post_url = urljoin(url, action)
        method = form.get("method")

        inputs_list = form.findAll("input")
        post_data = {}
        for input in inputs_list:
            input_name = input.get("name")
            input_type = input.get("type")
            input_value = input.get("value")
            if input_type == "text":
                input_value = value

            post_data[input_name] = input_value
        if method == "post":
            return requests.post(post_url, data=post_data)
        return self.session.get(post_url, params=post_data)

    def run_scanner(self):
        for link in self.target_links:
            forms = self.extract_forms(link)
            for form in forms:
                print("[+] Testing form in " + link)

            if "=" in link:
                print("[+] Testing " + link)