python3图片验证码识别种类最多第三方模块-MuggleOCR

官网下载地址

https://pypi.org/project/muggle-ocr/
pip install muggle_ocr
pip install muggle_ocr -i http://pypi.douban.com/simple --trusted-host pypi.douban.com

案例1

导入包

import time

# 1. 导入包
import muggle_ocr

"""
使用预置模型，预置模型包含了[ModelType.OCR, ModelType.Captcha] 两种
其中 ModelType.OCR 用于识别普通印刷文本, ModelType.Captcha 用于识别4-6位简单英数验证码

"""

# 打开印刷文本图片
with open(r"test1.png", "rb") as f:
    ocr_bytes = f.read()

# 打开验证码图片
with open(r"test2.jpg", "rb") as f:
    captcha_bytes = f.read()

# 2. 初始化；model_type 可选: [ModelType.OCR, ModelType.Captcha]
sdk = muggle_ocr.SDK(model_type=muggle_ocr.ModelType.OCR)

# ModelType.Captcha 可识别光学印刷文本
for i in range(5):
    st = time.time()
    # 3. 调用预测函数
    text = sdk.predict(image_bytes=ocr_bytes)
    print(text, time.time() - st)

# ModelType.Captcha 可识别4-6位验证码
sdk = muggle_ocr.SDK(model_type=muggle_ocr.ModelType.Captcha)
for i in range(5):
    st = time.time()
    # 3. 调用预测函数
    text = sdk.predict(image_bytes=captcha_bytes)
    print(text, time.time() - st)

"""
使用自定义模型
支持基于 https://github.com/kerlomz/captcha_trainer 框架训练的模型
训练完成后，进入导出编译模型的[out]路径下, 把[graph]路径下的pb模型和[model]下的yaml配置文件放到同一路径下。
将 conf_path 参数指定为 yaml配置文件 的绝对或项目相对路径即可，其他步骤一致，如下示例：
"""
with open(r"test3.jpg", "rb") as f:
    b = f.read()
sdk = muggle_ocr.SDK(conf_path="./ocr.yaml")
text = sdk.predict(image_bytes=b)

案例2

import time
import muggle_ocr
import os
sdk = muggle_ocr.SDK(model_type=muggle_ocr.ModelType.OCR)
root_dir = r"./imgs"
for i in os.listdir(root_dir):
n = os.path.join(root_dir, i)
with open(n, "rb") as f:
b = f.read()
st = time.time()
text = sdk.predict(image_bytes=b)
print(i, text, time.time() - st)

案例3

import datetime
import time
import requests
import json
import base64
import muggle_ocr
import random
import warnings

warnings.filterwarnings("ignore")

def login_qufenqi():
    sdk = muggle_ocr.SDK(model_type=muggle_ocr.ModelType.Captcha)
    # sdk = muggle_ocr.SDK(model_type=muggle_ocr.ModelType.OCR)
    # num_str = ''.join(str(random.choice(range(10))) for _ in range(7))
    # 获取图片
    url = "https://passport.qufenqi.com/verify/getimg?r=0.05915737242270325"
    headers = {
        "authority": "passport.qufenqi.com",
        "method": "GET",
        "path": "/verify/getimg?r=0.05915737242270325",
        "scheme": "https",
        "accept": "image/webp,image/apng,image/*,*/*;q=0.8",
        "accept-encoding": "gzip, deflate, br",
        "accept-language": "zh-CN,zh;q=0.9,en;q=0.8",
        "referer": "https://passport.qufenqi.com/i/resetloginpass",
        "sec-fetch-dest": "image",
        "sec-fetch-mode": "no-cors",
        "sec-fetch-site": "same-origin",
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36",
    }

    response = requests.get(url, headers=headers, verify=False, timeout=10)
    print("图片验证码",response.content)
    with open('a.jpg', 'wb') as fw:
        fw.write(response.content)
    # 验证号码
    code = sdk.predict(response.content)
    print(code)

    url = "https://passport.qufenqi.com/i/resetloginpass/setaccount"
    headers = {
            "authority":"passport.qufenqi.com",
            "method":"POST",
            "path":"/i/resetloginpass/setaccount",
            "scheme":"https",
            "accept":"*/*",
            "accept-encoding":"gzip, deflate, br",
            "accept-language":"zh-CN,zh;q=0.9,en;q=0.8",
            "content-length":"31",
            "content-type":"application/x-www-form-urlencoded; charset=UTF-8",
            "origin":"https://passport.qufenqi.com",
            "referer":"https://passport.qufenqi.com/i/resetloginpass",
            "sec-fetch-dest":"empty",
            "sec-fetch-mode":"cors",
            "sec-fetch-site":"same-origin",
            "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36",
            "x-requested-with":"XMLHttpRequest",
    }
    time.sleep(1)
    data = {"mobile": "13918238777","imgcode": code} # input("输入验证码:")
    print(data)
    response = requests.post(url, headers=headers, data=data, verify=False, timeout=10)
    print(json.loads(response.text))



if __name__ == '__main__':
    # while True:
    # time.sleep(1)
    login_qufenqi()