Search_Source¶

import sys
from colorama import Fore, Back, Style, init
import requests
from bs4 import BeautifulSoup
import os

results_counter = 0

def crawl_over_every_thing(url, max_depth):

    global results_counter

    response = requests.get(url)
    soup = BeautifulSoup(response.content, "html.parser")

    if max_depth >= 0:
        if 'pico' in response.text:
            fil = open(str(results_counter)+'.txt', 'w')
            fil.write(response.text)

            os.system('grep pico ' + str(results_counter)+'.txt')
            results_counter += 1

    if max_depth == 0:
        return

    links_list = soup.select('link[href]')
    for found_url in links_list:
        new_url = url + found_url['href']

        if 'http' in found_url['href']:
            new_url = found_url['href']

        print(Fore.WHITE + '[+] ' + Style.RESET_ALL, end='')
        print(Fore.GREEN + 'Searching through ' + Fore.BLUE + new_url + Style.RESET_ALL)

        crawl_over_every_thing(new_url, max_depth - 1)

if __name__ == '__main__':

    init(autoreset=True)


    for url in sys.argv :
        if url == 'crawler.py':
            continue
        print(Fore.WHITE + '[+] ' + Style.RESET_ALL, end='')
        print(Fore.GREEN + 'Searching through ' + Fore.BLUE + url + Style.RESET_ALL)
        crawl_over_every_thing(url, 10)