python Selenium 库的使用技巧

 from selenium import webdriver path = "C:/Users/LyShark/AppData/Local/Google/Chrome/Application/chromedriver.exe" driver = webdriver.Chrome(executable_path=path) url = "https://www.baidu.com" driver.get(url) print(driver.page_source)

 # -*- coding:utf-8 -*- from selenium import webdriver WebPath = "C:/Users/LyShark/AppData/Local/Google/Chrome/Application/chromedriver.exe" driver = webdriver.Chrome(executable_path=WebPath) driver.set_window_size(1000,500) url = "https://www.baidu.com" driver.get(url) print(driver.find_element_by_id("kw"))

    
 新闻我的博客GitHub
 
用户: 
密码: 
 hello lyshark p1
 hello lyshark p2

 # 驱动下载地址: http://chromedriver.storage.googleapis.com/index.html from selenium import webdriver WebPath = "C:/Users/LyShark/AppData/Local/Google/Chrome/Application/chromedriver.exe" driver = webdriver.Chrome(executable_path=WebPath) driver.set_window_size(1024,768) # 常用的定位变量参数如下所示. driver.get("http://lyshark.com") print("当前URL: {}".format(driver.current_url)) print("当前标题: {}".format(driver.title)) print("网页代码: {}".format(driver.page_source)) # 基本的 find_element 标签查找定位方式 print(driver.find_element_by_id("user"))     # 通过ID来查找元素 print(driver.find_element_by_name("p1").text)   # 通过name属性来定位 print(driver.find_element_by_class_name("s_ipt")) # 通过类名来定位 # 通过xpath定位,xpath定位有N种写法,这里列几个常用写法 print(driver.find_element_by_xpath("//form[@class='fms']//input[@id='user']")) print(driver.find_element_by_xpath("//p[@name='p1']")) print(driver.find_element_by_xpath("//html/body/form/p/input")) print(driver.find_elements_by_css_selector(".fms #user")) # 定位a标签中的关键字. print(driver.find_element_by_link_text("新闻")) print(driver.find_element_by_partial_link_text("我"))

 from selenium import webdriver WebPath = "C:/Users/LyShark/AppData/Local/Google/Chrome/Application/chromedriver.exe" driver = webdriver.Chrome(executable_path=WebPath) driver.set_window_size(1024,768) driver.get("http://lyshark.com") # 通过xpath语法定位到用户名的标签上并且自动输入lyshark这个用户名 driver.find_element_by_xpath("//form[@class='fms']/p//input[@id='user']").send_keys("lyshark") # 通过xpath语法定位到密码的标签上清空默认值,然后输入123123密码 driver.find_element_by_xpath("//form[@class='fms']/p//input[@id='pass']").clear() driver.find_element_by_xpath("//form[@class='fms']/p//input[@id='pass']").send_keys("123123") # 提交这个请求,默认有两种提交方式一种是 click() 一种是submit() driver.find_element_by_xpath("//form[@class='fms']/input[@type='submit']").click()

 from selenium import webdriver from selenium.webdriver import ActionChains from selenium.webdriver.common.keys import Keys WebPath = "C:/Users/LyShark/AppData/Local/Google/Chrome/Application/chromedriver.exe" driver = webdriver.Chrome(executable_path=WebPath) driver.set_window_size(1024,768) driver.get("https://www.baidu.com") # ------------------------------------------------------------------------ # ActionChains 类提供了鼠标操作的常用方法，鼠标事件的常用函数说明 # perform()：    鼠标悬浮于标签 # context_click()： 右击 # double_click()：  双击 # drag_and_drop()： 拖动 # move_to_element()：鼠标悬停 # 定位到要悬停的元素 above = driver.find_element_by_link_text("更多产品") # 对定位到的元素执行鼠标悬停操作 ActionChains(driver).move_to_element(above).perform() # ------------------------------------------------------------------------ # webdriver.common.keys 类提供了键盘事件的操作,以下为常用的键盘操作： # send_keys(Keys.BACK_SPACE) 删除键（BackSpace） # send_keys(Keys.SPACE) 空格键(Space) # send_keys(Keys.TAB) 制表键(Tab) # send_keys(Keys.ESCAPE) 回退键（Esc） # send_keys(Keys.ENTER) 回车键（Enter） # send_keys(Keys.CONTROL,'a') 全选（Ctrl+A） # send_keys(Keys.CONTROL,'c') 复制（Ctrl+C） # send_keys(Keys.CONTROL,'x') 剪切（Ctrl+X） # send_keys(Keys.CONTROL,'v') 粘贴（Ctrl+V） # send_keys(Keys.F1) 键盘 F1 # 输入框输入内容 driver.find_element_by_id("kw").send_keys("seleniumm") # 删除多输入的一个 m driver.find_element_by_id("kw").send_keys(Keys.BACK_SPACE) # 输入空格键+从入门到入土 driver.find_element_by_id("kw").send_keys(Keys.SPACE) driver.find_element_by_id("kw").send_keys("从入门到入土") # ctrl+a 全选输入框内容 driver.find_element_by_id("kw").send_keys(Keys.CONTROL, 'a') # ctrl+x 剪切输入框内容 driver.find_element_by_id("kw").send_keys(Keys.CONTROL, 'x') # ctrl+v 粘贴内容到输入框 driver.find_element_by_id("kw").send_keys(Keys.CONTROL, 'v') # 通过回车键来代替单击操作 driver.find_element_by_id("su").send_keys(Keys.ENTER)

 # -*- coding:utf-8 -*- from selenium import webdriver import time WebPath = "C:/Users/LyShark/AppData/Local/Google/Chrome/Application/chromedriver.exe" driver = webdriver.Chrome(executable_path=WebPath) driver.set_window_size(1024,768) driver.get("https://www.baidu.com") driver.find_element_by_id("kw").send_keys("lyshark") # 发送给id=kw的编辑框,搜索关键字 lyshark driver.find_element_by_id("su").click()        # 点击搜索按钮,百度一下的ID是su time.sleep(1) # xpath 语法 寻找 div id是1里面的 a标签取出标签中的 contains text() driver.find_element_by_xpath("//div[@id='1']//a[contains(text(),'-')]").click() time.sleep(1) handle = driver.current_window_handle  # 获取当前窗口句柄 handle_all = driver.window_handles   # 获取当前所有开启窗口的句柄 print(handle_all) driver.switch_to.window(handle_all[0])  # 切换到第一个窗口中 time.sleep(1) driver.find_element_by_id("kw").clear() # 接着清空搜索框中的内容

 from selenium import webdriver from bs4 import BeautifulSoup from queue import Queue import requests,os,re,lxml # driver: http://chromedriver.storage.googleapis.com/index.html?path=79.0.3945.36/ head = {"User-Agent":"Mozilla/5.0 (iPhone; U; CPU like Mac OS X) AppleWebKit/420.1 (KHTML, like Gecko) Version/3.0 Mobile/4A93 Safari/419.3"} WebPath = "C:/Users/LyShark/AppData/Local/Google/Chrome/Application/chromedriver.exe" driver = webdriver.Chrome(executable_path=WebPath) queue = Queue() for item in range(0,1000,10): queue.put('https://www.baidu.com/s?wd={}&pn={}'.format("lyshark",str(item))) for item in queue.queue: driver.get(item) ret = str(driver.page_source) try: soup = BeautifulSoup(ret,'lxml') urls = soup.find_all(name='a',attrs={'data-click':re.compile(('.')),'class':None}) for item in urls: get_url = requests.get(url=item['href'],headers=head,timeout=5) if get_url.status_code == 200: print(get_url.url) except Exception: pass

 from selenium import webdriver driver=webdriver.Chrome() driver.get('https://www.taobao.com/') wait=WebDriverWait(driver,3) #设置监听driver等待时间3秒 input=wait.until(EC.presence_of_element_located((By.ID,'q'))) #设置等待条件为id为q的元素加载完成 button=wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'.btn-search'))) #设置等待条件为class名为btn-search的元素加载完成 print(input,button) driver = webdriver.Firefox() driver.implicitly_wait(10) #隐式等待设置为10等待时间 driver.get("http://somedomain/url_that_delays_loading") myDynamicElement = driver.find_element_by_id("myDynamicElement")

 element=driver.find_element_by_id('search') #获取输入框 element.send_keys('selenium') #搜索selenium包 element.send_keys(Keys.ENTER) #按回车键 element_a=driver.find_element_by_link_text('selenium') #定位selenium包链接 ActionChains(driver).move_to_element(element_a).click(element_a).perform() #按左键点击链接执行 element_down=driver.find_element_by_link_text('Download files') #定位下载链接 ActionChains(driver).move_to_element(element_down).click(element_down).perform() #按左键点击链接 element_selenium=driver.find_element_by_link_text('selenium-3.13.0.tar.gz') #定位元素selenium下载包链接 data=element_selenium.get_attribute('href')  #获取链接地址 with open('selenium-3.13.0.tar.gz','wb') as f: source=requests.get(data).content  #请求下载链接地址获取二进制包数据 f.write(source) #写入数据 f.close() driver.quit() menu = driver.find_element_by_css_selector(".nav") #获取element对象 hidden_submenu = driver.find_element_by_css_selector(".nav #submenu1") #获取点击对象 #创建鼠标对象 actions = ActionChains(driver) #移动鼠标到对象 actions.move_to_element(menu) #点击对象 actions.click(hidden_submenu) #执行操作 actions.perform()