简介
硬性要求

python >= 3.8

安装

pip install ddddocr

ddddocr1.2多版本的使用

import ddddocr
import requests

def get_code(path):
    ocr = ddddocr.DdddOcr()
    with open(path, 'rb') as f:
        img_bytes = f.read()
    res = ocr.classification(img_bytes)
    print('识别出的验证码为：' + res)
    return res

# captcha_image = requests.get("https://scsso.zhjpec.edu.cn/authserver/app/validate/genCode?code=0.8384928333969981")
# with open('captcha.png', 'wb') as f:
#     f.write(captcha_image.content)
# get_code('captcha.png')

ddddocr1.5.5版本的使用

import ddddocr
import requests

def get_code(path):
    ocr = ddddocr.DdddOcr(show_ad=False)  # Added argument to suppress ads
    with open(path, 'rb') as f:
        img_bytes = f.read()
    res = ocr.classification(img_bytes)
    print('识别出的验证码为：' + res)
    return res

# To save and classify captcha image from the URL
def fetch_and_get_code(url, save_path):
    captcha_image = requests.get(url)
    with open(save_path, 'wb') as f:
        f.write(captcha_image.content)
    return get_code(save_path)

# Usage example
print(get_code("E:\\Daily_Work\\search\\JS\\JS_end\\captcha.png"))
# Or fetch and classify directly
# print(fetch_and_get_code("https://scsso.zhjpec.edu.cn/authserver/app/validate/genCode?code=0.8384928333969981", "captcha.png"))

爬虫中的使用

#pip install beautifulsoup4
#pip install requests

import requests
from bs4 import BeautifulSoup
from code import get_code

# Define the login URL and payload
login_url = 'https://scsso.zhjpec.edu.cn/authserver/login?'
payload = {
    'username': 'your_username',
    'password': 'your_password',
    'captcha': 'captcha_code'
}

headers = {
    'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36"
}

# Send a GET request to the login page to obtain the captcha image
login_page = requests.get(login_url,headers=headers)
soup = BeautifulSoup(login_page.content, 'html.parser')
captcha_image_url = "https://scsso.zhjpec.edu.cn" + soup.find('img', {'class': 'mvLoginForm-bottom-img'})['src']
# Use a library like pytesseract to extract the captcha code from the image
captcha_image = requests.get(captcha_image_url)
with open('captcha.png', 'wb') as f:
    f.write(captcha_image.content)
captcha_code = get_code('captcha.png')
print('dd', captcha_code)
# Add the captcha code to the payload and send a POST request to the login page
payload['captcha'] = captcha_code

response = requests.post(login_url, data=payload)

# Check if the login was successful
if 'Welcome' in response.text:
    print('Login successful!')
else:
    print('Login failed. Please check your credentials and try again.')

GitHub
文档地址