phishing kit finding script

from urllib.request import urlopen

from urllib.request import urlretrieve

import re

import sys

import os

filepath = 'urls.txt'

with open(filepath) as fp:

 theurl = fp.readline()

 while theurl:

  if(not theurl.startswith('http')):

   if(":443" in theurl):

    theurl = 'https://' + theurl.strip()

   else:

    theurl = 'http://' + theurl.strip()

  theurl = theurl.strip()

  if(theurl.endswith("/") or theurl.endswith("\\")):

   theurl = theurl[:-1]

  stopnow = 0

  while stopnow == 0:

   try:

    domain = theurl.split("//")[-1].split("/")[0]

    currentfolder = theurl.split("/")[-1]

    try:

     if not theurl.endswith(".zip") and (len(theurl.split("//")[-1].split("/")) > 1):

      zipfile = domain + "___" + currentfolder + ".zip"

      phishkit = theurl + ".zip"

      urlretrieve(phishkit, zipfile)

      print("phishkit," + phishkit)

    except Exception as e:

     print("failedphishkit," + phishkit + "(" + str(e) + ")")

    html = urlopen(theurl, timeout=3)

    val = html.read()

    titles = re.findall(r'(?i)<title>(.*?)</title>',str(val))

    if len(titles) > 0:

     if titles[0].startswith('Index of'):

      print("opendir," + theurl + "(" + titles[0] + ")")

      zipfiles = re.findall(r'(?i)href\=\"[^\"]+\.zip\"\>',str(val))

      if len(zipfiles) > 0:

       for zipfile in zipfiles:

        zipfile = zipfile.replace('\"', '').replace('href=', '').replace('>','').replace("&amp;", "&")

        if theurl.endswith('/'):

         phishkit = theurl + zipfile

        else:

         phishkit = theurl + "/" + zipfile

        try:

         zipfile = domain + "___" + zipfile

         urlretrieve(phishkit, zipfile)

         print("phishkit," + phishkit)

        except Exception as e:

         print("failedphishkit," + phishkit + "(" + str(e) + ")")

      exefiles = re.findall(r'(?i)href\=\"[^\"]+\.exe\"\>',str(val))

      if len(exefiles) > 0:

       for exefile in exefiles:

        exefile = exefile.replace('\"', '').replace('href=', '').replace('>','').replace("&amp;", "&")

        if theurl.endswith('/'):

         malware = theurl + exefile

        else:

         malware = theurl + "/" + exefile

        try:

         urlretrieve(malware, exefile)

         print("malware," + malware)

        except Exception as e:

         print("failedmalware," + malware + "(" + str(e) + ")")

      panels = re.findall(r'(?i)href\=\"(panel|webpanel|fre\.php)\"\>',str(val))

      if len(panels) > 0:

       for panel in panels:

        panel = panel.replace('\"', '').replace('href=' ,'').replace('>', '').replace("&amp;", "&")

        if theurl.endswith('/'):

         panelurl = theurl + panel

        else:

         panelurl = theurl + "/" + panel

        print("panel," + panelurl)

     else:

      print("webpage," + theurl + "(" + titles[0] + ")")

    theurl = re.sub(r'\/[^\/]*$', '', theurl)

    if theurl.endswith('http:/') or theurl.endswith('https:/'):

     stopnow = 1

   except Exception as e:

    if "no host given" in str(e):

     stopnow = 1

    else:

     print("failedurl," + theurl + "(" + str(e) + ")")

     theurl = re.sub(r'\/[^\/]*$', '', theurl)

  theurl = fp.readline()