google_vision.py

def ocr_by_goole_vision(input_file='captcha.png',draw_text=False):
    
    with io.open(input_file, 'rb') as image_file:
        content = image_file.read()

    response = client.text_detection(image=vision.Image(content=content))

    if response.error.message:
        raise Exception(
            '{}\nFor more info on error messages, check: '
            'https://cloud.google.com/apis/design/errors'.format(
                response.error.message))

    print('chptcha decode:')
    texts=response.text_annotations
    #print(texts[0].description.split())
    
    for text in response.text_annotations[1::]:
        ocr_text = text.description
        print(ocr_text)
    
    if draw_text:
        bound=text.bounding_poly
        draw_text_on_image(input_file,ocr_text,bound)
        
    return  ocr_text

session.get.py

# -*- coding: utf-8 -*-
"""
Created on Sat Nov 18 20:30:29 2023

@author: joseph@艾鍗學院

(1) mimic the behavior of browser

(2)session = requests.Session()
send a cookie containing the session identifier.
The Flask-Session extension will then associate the request
with the correct session.

"""

import requests
from bs4 import BeautifulSoup
import random
import string

def generate_captcha_text(length=5):
    #return ''.join(random.choices(string.ascii_uppercase + string.digits, k=length))
    return ''.join(random.choices(string.digits, k=length))



server='http://localhost:5000/'  # end with '/'
url = server+"test2"




# Send an HTTP GET request to the URL
# Create a session to maintain cookies
session = requests.Session()
response =session.get(url)

# Check if the request was successful (status code 200)
if response.status_code == 200:
    # Parse the HTML content
    soup = BeautifulSoup(response.text, 'html.parser')

    # Find the img tag containing the CAPTCHA image
    img_tag = soup.find('img', attrs={'alt': 'CAPTCHA'})  # Replace 'CAPTCHA' with the actual alt text of the image
    
    if img_tag:
        # Extract the URL of the image
        captcha_image_url = img_tag['src']

        # You now have the URL of the CAPTCHA image
        print("CAPTCHA Image URL:", captcha_image_url)
        captcha_image_url=server+captcha_image_url
        # You can use this URL to download the image using the 'requests' library

        captcha_image_response = session.get(captcha_image_url)

        # Check if the request was successful (status code 200)
        
        if captcha_image_response.status_code == 200:
            #Save the image to a file
            with open('captcha.png', 'wb') as f:
                f.write(captcha_image_response.content)
            print("CAPTCHA Image downloaded successfully as 'captcha.png'")
      
            form = soup.find('form') #, {'id': 'your_form_id'})
            form_action = server+ form['action']
            form_fields = {}
            # for input_element in form.find_all('input'):
            #     print(input_element)
            #     field_name = input_element.get('name')
            #     print(field_name)
            #     if field_name: #place the text on the value attribute
            #         form_fields[field_name] = input_element.get('value', '1234')    
           
            # #print(form_fields)
            
            for _ in range(5):
                
                form_fields['captcha']=generate_captcha_text()
                print(form_fields)
                # Send an HTTP POST request to submit the form data
                response = session.post(form_action, data=form_fields)
                # Check if the request was successful (status code 200)
                if response.status_code == 200:
                    
                    # Process the response from the server as needed
                    print("Form submitted successfully")
                    print(response.text)
                else:
                    print("Failed to submit the form")
                    break
    
                
            
        else:
            print("Failed to download CAPTCHA image")
    else:
        print("CAPTCHA image not found on the page")
else:
    print("Failed to retrieve the webpage")