【Python自动化】Selenium WebDriver + OCR 实现网页自动登录

概述

        利用webdriver和PIL库获取验证码图片（解决动态链接），百度OCR识别，实现网页登录

例：

        

网址：登录古诗文网

---

OCR

        网址：百度智能云-登录

        选择产品->文字识别->通用文字识别       

        创建应用

        得到接口信息

---

代码实现

        安装必要库       

pip install selenium
pip3 install pillow
pip install baidu-aip

          有时候会缺chardet库，装下就好

pip install chardet

        login.py

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from aip import AipOcr 
from PIL import Image
import time

def trim_image(l, u, r, d, source, to):
    # 左上右下
    bbox = (l, u, r, d) 
    img = Image.open(source)
    cp_img = img.crop(bbox)
    cp_img.save(to)

def getCode(path):

    #百度OCR接口
    code = ""

    APP_ID = ''
    API_KEY = ''
    SECRET_KEY = ''

    client = AipOcr(APP_ID, API_KEY, SECRET_KEY)

    with open(path ,"rb") as f: 
        img=f.read()

    data=client.basicGeneral(img)

    for da in data["words_result"]:
            code += da["words"]
    code = code.replace(" ", "") 
    return code


# 是否无页面运行 
headless = True;

time.sleep(2) 

options = webdriver.ChromeOptions()
if(headless == True):
    options.add_argument('--headless')

# 忽略ssl证书
options.add_argument('--ignore-ssl-errors=yes')
options.add_argument('--ignore-certificate-errors')
driver = webdriver.Chrome(options=options)

 
driver.set_window_size(1920, 1080); # 设置window大小
driver.get('http://') #网页登陆地址
wait = WebDriverWait(driver, 10)

time.sleep(2)

# 获取DOM元素
username_field = driver.find_element(By.XPATH, '//input[@placeholder="请输入账号"]') #根据html信息替换 
password_field = driver.find_element(By.XPATH, '//input[@placeholder="请输入密码"]')
captcha_field = driver.find_element(By.XPATH, '//input[@placeholder="请输验证码"]') 
login_button = driver.find_element(By.XPATH, '//button[@class="el-button login_confirm_btn el-button--primary el-button--small"]')

screenshot_path = 'C:\\' #截图地址   
driver.save_screenshot(screenshot_path) #页面截图

cropped_path = '' #裁剪地址

#裁剪
if(headless == True): #headless和页面模式图片裁剪参数不一样 
    trim_image(1, 1, 1, 1, screenshot_path, cropped_path) #替换参数
else:
    trim_image(2, 2, 2, 2, screenshot_path, cropped_path) 

# 验证码识别
captcha_text = getCode(cropped_path) 

# 输入
username_field.send_keys('用户名') 
password_field.send_keys('密码')
captcha_field.send_keys(captcha_text)

# 登录
time.sleep(1) 
login_button.click()
time.sleep(4) # 等待页面加载

if(driver.current_url == '目标网址'):
        print("登录成功！")
else:
    print("登录失败!! 验证码错误识别!")

# 退出
time.sleep(5)
driver.quit()

 

---

ps:能力有限，多多包涵~