selenium UI自动化解决验证码的五种方法

TesseractPy3.py

#coding=utf-8

import os
import subprocess
import traceback
import logging

from PIL import Image # 来源于Pillow库

TESSERACT = 'tesseract' # 调用的本地命令名称
TEMP_IMAGE_NAME = "temp.bmp" # 转换后的临时文件
TEMP_RESULT_NAME = "temp" # 保存识别文字临时文件
CLEANUP_TEMP_FLAG = True # 清理临时文件的标识
INCOMPATIBLE = True # 兼容性标识

def image_to_scratch(image, TEMP_IMAGE_NAME):
  # 将图片处理为兼容格式
  image.save(TEMP_IMAGE_NAME, dpi=(200,200))

def retrieve_text(TEMP_RESULT_NAME):
  # 读取识别内容
  inf = open(TEMP_RESULT_NAME + '.txt','r')
  text = inf.read()
  inf.close()
  return text

def perform_cleanup(TEMP_IMAGE_NAME, TEMP_RESULT_NAME):
  # 清理临时文件
  for name in (TEMP_IMAGE_NAME, TEMP_RESULT_NAME + '.txt', "tesseract.log"):
    try:
      os.remove(name)
    except OSError:
      pass

def call_tesseract(image, result, lang):
  # 调用tesseract.exe，将识读结果写入output_filename中
  args = [TESSERACT, image, result, '-l', lang]
  proc = subprocess.Popen(args)
  retcode = proc.communicate()

def image_to_string(image, lang, cleanup = CLEANUP_TEMP_FLAG, incompatible = INCOMPATIBLE):
  # 假如图片是不兼容的格式并且incompatible = True，先转换图片为兼容格式（本程序将图片转换为.bmp格式），然后获取识读结果;如果cleanup=True,操作之后删除临时文件。
  logging.basicConfig(filename='tesseract.log')
  try:
    try:
      call_tesseract(image, TEMP_RESULT_NAME, lang)
      text = retrieve_text(TEMP_RESULT_NAME)
    except Exception:
      if incompatible:
        image = Image.open(image)
        image_to_scratch(image, TEMP_IMAGE_NAME)
        call_tesseract(TEMP_IMAGE_NAME, TEMP_RESULT_NAME, lang)
        text = retrieve_text(TEMP_RESULT_NAME)
      else:
        raise
    return text
  except:
    s=traceback.format_exc()
    logging.error(s)
  finally:
    if cleanup:
      perform_cleanup(TEMP_IMAGE_NAME, TEMP_RESULT_NAME)

#coding=utf-8

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import Select
from selenium.common.exceptions import NoSuchElementException
from selenium.common.exceptions import NoAlertPresentException
from PIL import Image
import unittest, time, re
from TesseractPy3 import *

class lgoin(unittest.TestCase):
  def setUp(self):
    self.driver = webdriver.Ie()
    self.driver.implicitly_wait(30)
    self.base_url = 'http://127.0.0.1:8080/test' # 要测试的链接
    self.title = '某管理平台' # 测试网站的Title
    self.verificationErrors = []
    self.accept_next_alert = True

  def test_lgoin(self):
    driver = self.driver
    driver.get(self.base_url)
    driver.maximize_window()
    driver.save_screenshot('All.png') # 截取当前网页，该网页有我们需要的验证码
    imgelement = driver.find_element_by_class_name('kaptchaImage')
    location = imgelement.location # 获取验证码x,y轴坐标
    size = imgelement.size # 获取验证码的长宽
    rangle = (int(location['x']),int(location['y']),int(location['x']+size['width']),int(location['y']+size['height'])) # 写成我们需要截取的位置坐标
    i = Image.open("All.png") # 打开截图
    result = i.crop(rangle) # 使用Image的crop函数，从截图中再次截取我们需要的区域
    result.save('result.jpg')
    text = image_to_string('result.jpg', 'eng').strip()

    assert self.title in driver.title

    driver.find_element_by_id(u'userCode').clear()
    driver.find_element_by_id(u'userCode').send_keys('XXXXXX') # 用户名
    driver.find_element_by_id(u'password').clear()
    driver.find_element_by_id(u'password').send_keys('XXXXXX') # 密码
    #driver.find_element_by_name('verifyCode').clear()
    driver.find_element_by_name('verifyCode').send_keys(text)
    driver.find_element_by_name('submit').submit()

  def is_element_present(self, how, what):
    try: self.driver.find_element(by=how, value=what)
    except NoSuchElementException as e: return False
    return True

  def is_alert_present(self):
    try: self.driver.switch_to_alert()
    except NoAlertPresentException as e: return False
    return True

  def close_alert_and_get_its_text(self):
    try:
      alert = self.driver.switch_to_alert()
      alert_text = alert.text
      if self.accept_next_alert:
         alert.accept()
      else:
        alert.dismiss()
      return alert_text
    finally: self.accept_next_alert = True

  def tearDown(self):
    #self.driver.quit()
    self.assertEqual([], self.verificationErrors)

if __name__ == "__main__":
  unittest.main()

# coding=utf-8

from selenium import webdriver
import time 

driver = webdriver.Firefox()
driver.get("http://www.xxxxxx.com/") # 要登陆的网站

driver.add_cookie(cook) # 这里添加cookie，有时cookie可能会有多条，需要添加多次
time.sleep(3) 

# 刷新下页面就可以看到登陆成功了
driver.refresh() 

BufferedReader reader = new BufferedReader(new InputStreamReader(
                new FileInputStream("/Users/pangyongjuan/IdeaProjects/Zmbx/src/test/java/code.txt")));
​
        String code = null;
​
        while((code = reader.readLine()) != null){
            System.out.println("验证码是：---->"+ code);
            driver.findElement(By.id("pin")).sendKeys(code);
        }