python selenium UI自動化解決驗證碼的4種方法

#coding=utf-8

import os
import subprocess
import traceback
import logging

from PIL import Image # 來源于Pillow庫

TESSERACT = 'tesseract' # 調(diào)用的本地命令名稱
TEMP_IMAGE_NAME = "temp.bmp" # 轉(zhuǎn)換后的臨時文件
TEMP_RESULT_NAME = "temp" # 保存識別文字臨時文件
CLEANUP_TEMP_FLAG = True # 清理臨時文件的標(biāo)識
INCOMPATIBLE = True # 兼容性標(biāo)識

def image_to_scratch(image, TEMP_IMAGE_NAME):
  # 將圖片處理為兼容格式
  image.save(TEMP_IMAGE_NAME, dpi=(200,200))

def retrieve_text(TEMP_RESULT_NAME):
  # 讀取識別內(nèi)容
  inf = open(TEMP_RESULT_NAME + '.txt','r')
  text = inf.read()
  inf.close()
  return text

def perform_cleanup(TEMP_IMAGE_NAME, TEMP_RESULT_NAME):
  # 清理臨時文件
  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):
  # 調(diào)用tesseract.exe，將識讀結(jié)果寫入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):
  # 假如圖片是不兼容的格式并且incompatible = True，先轉(zhuǎn)換圖片為兼容格式（本程序?qū)D片轉(zhuǎn)換為.bmp格式），然后獲取識讀結(jié)果;如果cleanup=True,操作之后刪除臨時文件。
  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' # 要測試的鏈接
    self.title = '某管理平臺' # 測試網(wǎng)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') # 截取當(dāng)前網(wǎng)頁，該網(wǎng)頁有我們需要的驗證碼
    imgelement = driver.find_element_by_class_name('kaptchaImage')
    location = imgelement.location # 獲取驗證碼x,y軸坐標(biāo)
    size = imgelement.size # 獲取驗證碼的長寬
    rangle = (int(location['x']),int(location['y']),int(location['x']+size['width']),int(location['y']+size['height'])) # 寫成我們需要截取的位置坐標(biāo)
    i = Image.open("All.png") # 打開截圖
    result = i.crop(rangle) # 使用Image的crop函數(shù)，從截圖中再次截取我們需要的區(qū)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') # 用戶名
    driver.find_element_by_id(u'password').clear()
    driver.find_element_by_id(u'password').send_keys('XXXXXX') # 密碼
    #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/") # 要登陸的網(wǎng)站

driver.add_cookie(cook) # 這里添加cookie，有時cookie可能會有多條，需要添加多次
time.sleep(3) 

# 刷新下頁面就可以看到登陸成功了
driver.refresh()