selenium自动化JS滚动条获取动态加载的元素
昨天的滚动条是在非动态的页面加载,但是购物网站,比如京东页面,他的元素是动态加载的,
动态加载就是页面滑动到页面的可是区域才会被加载,
一、先滑动一下,等待新元素加载出来,再寻找元素,没有则继续滚动,只到元素出现
2、获取当前窗口的可视区域大小
3、获取整个HTML的body高度
4、循环判断只要整个HTML页面的高度和现在的高度是否一致,不一致就循环接着找,
from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.common.keys import Keys from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait driver = webdriver.Chrome() driver.get('http://www.baidu.com') driver.implicitly_wait(5) driver.maximize_window() # 输入京东,按回车 ele = driver.find_element_by_id('kw') ele.send_keys("京东商城", Keys.ENTER) # 找到京东商城,点击进入 loc = (By.XPATH, '//a[contains(text(),"正品低价、品质保障")]') WebDriverWait(driver, 20).until(EC.visibility_of_element_located(loc)) driver.find_element(*loc).click() # 其他换到新页面,京东 win = driver.window_handles driver.switch_to.window(win[-1])
# 获取当前窗口的内容可视区域 inner_height = driver.execute_script("var a = window.innerHeight;return a;") print("当前窗口的内容可视区域-高度:", inner_height) # 获取当前整个html页面的body高度。 body_height = driver.execute_script("var a = document.body.scrollHeight;return a;") print("当前整个html页面的body-高度:", body_height) # 京东页面的内容 - 滚动多少,加载多少。所要操作的内容,并不知道大概要滚动多少。
# 查找的元素定位 lo = (By.XPATH, '//*[@id="J_top"]/div[1]/a/h3') scrolled_height = 0 new_body_height = body_height # 当前整个html页面的body高度 old_body_height = 0 break_flag = False while new_body_height != old_body_height: distance = int((new_body_height - scrolled_height) / (inner_height * 0.5)) + 1 for i in range(distance): # 滚动距离为 窗口内容可视区域的百分之50.可灵活配置哦!
# window.innerHeight:返回窗口的文档显示区的高度。 window.scrollBy():会使元素从当前的滚动条位置向下滚动 driver.execute_script("var a = window.innerHeight;window.scrollBy(0,a*0.5);") # 滚动一次,页面内容会更新一部分。在滚动之后,查找当前页面是否包含了它。如果没有,继续滚动。如果有,退出。 try: WebDriverWait(driver, 10).until(EC.visibility_of_element_located(lo)) except: pass else: print("找到啦!!!") driver.find_element(*lo).click() break_flag = True # 终止for循环 break if break_flag is True: # 终止While循环 break # time.sleep(3) # 更新滚动 old_body_height = new_body_height scrolled_height = new_body_height new_body_height = driver.execute_script("var a = document.body.scrollHeight;return a;") print("老 - 当前整个html页面的body-高度:", old_body_height) print("新 - 当前整个html页面的body-高度:", new_body_height)
简易版 :搬运 动态加载元素可以这样获取
from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.common.keys import Keys from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.wait import WebDriverWait driver = webdriver.Chrome() driver.get('http://www.baidu.com') driver.implicitly_wait(5) driver.maximize_window() ele = driver.find_element_by_id('kw') ele.send_keys("京东商城", Keys.ENTER) loc = (By.XPATH, '//a[contains(text(),"正品低价、品质保障")]') WebDriverWait(driver, 20).until(EC.visibility_of_element_located(loc)) driver.find_element(*loc).click() win = driver.window_handles driver.switch_to.window(win[-1]) lo = (By.XPATH, '//h3[text()="逛好店"]') while True: js = """ var a = window.innerHeight; window.scrollBy(0, a*0.5); """ driver.execute_script(js) try: WebDriverWait(driver, 3, 0.5).until(EC.visibility_of_element_located(lo)) driver.find_element(*lo).click() except: pass else: break