from selenium import webdriver import time from PIL import Image import pytesseract import re dr = webdriver.Chrome() dr.get('http://172.16.1.9/IPINwebDEV/login.html') dr.maximize_window() n = dr.find_elements_by_class_name('login_type_li')[2] n.click() name = dr.find_element_by_xpath('/html/body/div[3]/div/div/div[2]/input[1]') name.send_keys('wiwi') password = dr.find_element_by_xpath('/html/body/div[3]/div/div/div[2]/input[2]') password.send_keys('Aa123456') # 整個頁面截圖 dr.save_screenshot('.\\printscreen.png') # 獲取驗證碼的位置坐標 imgelement = dr.find_element_by_xpath('/html/body/div[3]/div/div/div[2]/img') location = imgelement.location size = imgelement.size rangle = ( int(location['x']), int(location['y']), int(location['x'] + size['width']), int(location['y'] + size['height'])) # 打開截圖 i = Image.open(".\\printscreen.png") # 根據坐標裁剪圖片 frame4 = i.crop(rangle) # 保存為圖片 frame4.save('.\\save.tif') # 转化为灰度 imgry = frame4.convert('L') # 保存下來 imgry.save(".\\imgry1.tif") # 獲取圖片驗證碼的內容 text = pytesseract.image_to_string(Image.open(r".\\imgry1.tif")) # 打印出來查看，發現內容有特殊字符空格 print(text) # 去除特殊字符，剩下數字英文中文，導入re包 sub_str = re.sub(u"([^\u4e00-\u9fa5\u0030-\u0039\u0041-\u005a\u0061-\u007a])", "", text) # 輸入驗證碼 c = dr.find_element_by_xpath('/html/body/div[3]/div/div/div[2]/input[3]') c.send_keys(sub_str) time.sleep(2) # 點擊登錄按鈕 login = dr.find_element_by_id('login_btn') login.click()
