GDS: simple Google dorker script

google-dorker.py

import re
import requests
from bs4 import BeautifulSoup
import sys
import webbrowser

global_cookies = None

def the_end():
    print("\r|! end: successfully dumped {} urls from Google search query '{}' to file '{}' (end_page={})".format(len(cached_urls), sys.argv[1], sys.argv[3], pagenm))
    print("-"*15)
    sys.exit()    

def get_(s_query, pagenum, proxy=None):
    global global_cookies
    urls = []
    t_url = "http://www.google.com/search"
    params = {'q': s_query, 'start': pagenum}
    headers = {'User-Agent': "Mozilla/14.0"}
    r = requests.get(t_url, headers=headers, params=params, proxies=proxy)
    if "Our systems have detected unusual traffic from your computer network" in r.text:
        the_end()
        """webbrowser.open(r.url, new=0, autoraise=True)
        raw_input("|! press any key after you solved the captcha")
        global_cookies = r.cookies"""
    soup = BeautifulSoup(r.text, "lxml")
    h3_soup = soup.find_all('h3', class_='r')
    for h3s in h3_soup:
        try:
            urls.append(re.search('url\?q=(.+?)\&sa', h3s.a['href']).group(1))
        except:
            continue
    return urls

def que_thread(query, page, output):
    s_rslt = get_(query, page)
    for url in s_rslt:
        if url in cached_urls: continue
	required_condition = True
	if required_condition:
	        cached_urls.append(url)
	        print("\r|- " + url)
	        f = open(output, "a")
	        f.write(url + "\n")
	        f.close()

def main():
    global running_threads
    print """\
  ________  ____
 / ___/ _ \/ __/  | Google Dorker Script
/ (_ / // /\ \    | Author: P4kL0nc4t
\___/____/___/    | https://github.com/p4kl0nc4t
"""
    if len(sys.argv) != 4:
        print("usage: {} <query> <start_page> <output_file>".format(sys.argv[0]))
        sys.exit()
    query = sys.argv[1]
    output = sys.argv[3]
    global pagenm
    pagenm = int(sys.argv[2])
    max_thread = 5
    global cached_urls
    print("-"*15)
    print("|* begin: started Google dorker with dork='{}', start_page='{}', output='{}'".format(query, pagenm, output))
    cached_urls = []
    while True:
        que_thread(query, pagenm, output)
        pagenm += 1

if __name__ == "__main__":
    try:
        main()
    except KeyboardInterrupt:
        the_end()
    #except Exception:
        #pass