selenium+验证码识别

ddddocr实现验证登录

🕐镜像安装：pip install ddddocr -i https://pypi.tuna.tsinghua.edu.cn/simple
或 pip install ddddocr -i https://mirrors.aliyun.com/pypi/simple/
🕐有的环境可能需要 numpy 更新：
pip install --upgrade numpy -i https://mirrors.aliyun.com/pypi/simple/

from selenium import webdriver
from selenium.webdriver.common.by import By
import ddddocr
import time


# 识别图片，返回字母
def recognizeCode(filename):
    ocr = ddddocr.DdddOcr()
    with open(filename, 'rb') as f:
        img_bytes = f.read()
    res = ocr.classification(img_bytes)
    return res


driver = webdriver.Edge()
driver.get('https://www.ptpress.com.cn/login')
flag = True
while flag:# 如果验证失败，则一直尝试登录
    window1 = driver.get_cookies()
    driver.find_element(by=By.NAME, value="username").send_keys("18839105371")
    driver.find_element(by=By.NAME, value="password").send_keys("qjy@12345")
    img = driver.find_element(by=By.CLASS_NAME, value="verCodeImg")
    img.screenshot("ok.png")  # 返回image函数对象
    veriCode = recognizeCode("ok.png")
    driver.find_element(by=By.NAME, value='verifyCode').send_keys(veriCode)
    driver.find_element(by=By.ID, value='loginBtn').click()
    window2 = driver.get_cookies()
    if window1 != window2:
        flag = False
    else:
        driver.refresh()  # 刷新网页
        time.sleep(3)
driver.close()

超级鹰实现验证登录

利用超级鹰识别验证码时需要导入相关模块，可在官网https://www.chaojiying.com下载，注册登陆后转到当前页面

下载对应的压缩包

之后将压缩包中的chaojiying.py移入项目的合适位置，再进行调用

import ddddocr
from selenium import webdriver
from selenium.webdriver.common.by import By
from chaojiying import Chaojiying_Client
import time

web = webdriver.Chrome()
web.get('http://www.chaojiying.com/user/login/')
# # 将页面img截图，并传给img变量
img = web.find_element(by=By.XPATH, value='/html/body/div[3]/div/div[3]/div[1]/form/div/img').screenshot_as_png
chaojiying = Chaojiying_Client('qjy123', 'qjy123', '947723')
dic = chaojiying.PostPic(img, 1902)
print(dic)
# # dic为识别的图片信息，包括
# {'err_no': 0, 'err_str': 'OK', 'pic_id': '', 'pic_str': '', 'md5': ''}
verfy_code = dic['pic_str']
print(verfy_code)

# 输入信息
web.find_element(by=By.XPATH, value='/html/body/div[3]/div/div[3]/div[1]/form/p[1]/input').send_keys('qjy123')
web.find_element(by=By.XPATH, value='/html/body/div[3]/div/div[3]/div[1]/form/p[2]/input').send_keys('qjy123')
web.find_element(by=By.XPATH, value='/html/body/div[3]/div/div[3]/div[1]/form/p[3]/input').send_keys(verfy_code)
time.sleep(5)
# 点击登录
web.find_element(by=By.XPATH, value='/html/body/div[3]/div/div[3]/div[1]/form/p[4]/input').click()

print('登录成功')
# 打印当前剩余积分

jifen = web.find_element(by=By.XPATH, value='/html/body/div[3]/div[2]/div[1]/div[1]/span').text
print(jifen)