[Python从零到壹] 九.网络爬虫之Selenium基础技术万字详解（定位元素、常用方法、鼠标操作）开发者社区

[Python从零到壹] 九.网络爬虫之Selenium基础技术万字详解（定位元素、常用方法、鼠标操作）

C:\selenium\selenium3.4.3> python3 setup.py install

from selenium import webdriver
driver = webdriver.Firefox()
driver.get('http://www.baidu.com/')

import os 
from selenium import webdriver
chromedriver = "C:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe"  
os.environ["webdriver.chrome.driver"] = chromedriver 
browser = webdriver.Chrome(chromedriver)
browser.get('http://www.baidu.com/')

from selenium import webdriver
browser = webdriver.Ie()
browser.get('http://www.baidu.com/')

from selenium import webdriver
driver = webdriver.PhantomJS(executable_path="F:\phantomjs.exe")
driver.get("http://www.baidu.com")
data = driver.title
print(data)

from selenium import webdriver
driver = webdriver.Firefox()
driver.get("http://www.baidu.com")
data = driver.title
driver.save_screenshot('baidu.png')

#-*- coding:utf-8 -*-
#By:Eastmount 2021-05-29
import time
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
#启动驱动
driver = webdriver.Firefox()
driver.get("http://www.baidu.com")
assert "百度" in driver.title
print(driver.title)
#查找元素并输入内容
elem = driver.find_element_by_name("wd")
elem.send_keys("数据分析")
elem.send_keys(Keys.RETURN)
#截图并退出
time.sleep(10)
driver.save_screenshot('baidu.png')
driver.close()
driver.quit()

#-*- coding:utf-8 -*-
#By:Eastmount 2021-05-29
import time
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
#启动驱动
driver = webdriver.Firefox()
driver.get("file://C:/Users/../Desktop/09.selenium/blog09.html")
print(driver.title)
#查找元素并输入内容
test_div = driver.find_elements_by_id('link')
for t in test_div:
    print(t.text)

<div class="other" align="left" name="d1" id="nr">
 <a href="http://test.com/dufu" class="poet" id="link" name="dufu">杜甫</a>
 <a href="http://test.com/lsy" class="poet" id="link" name="lsy">李商隐</a>
 <a href="http://test.com/dumu" class="poet" id="link" name=”dumu”>杜牧</a>

test_poet1 = driver.find_element_by_name('dufu')
test_poet2 = driver.find_element_by_name('lsy')
test_poet3 = driver.find_element_by_name('dumu')

test_div = driver.find_element_by_xpath("/html/body/div[1]")
test_div = driver.find_element_by_xpath("//div[1]")
test_div = driver.find_element_by_xpath("//div[@id='nr']")

username = driver.find_element_by_xpath("//div[a/@name='dumu']")
username = driver.find_element_by_xpath("//div[@id='nr']/a[3]")
username = driver.find_element_by_xpath("//a[@name='dumu']")

<form id="loginForm">
	<input name="continue" type="submit" value="Login" />
	<input name="continue" type="button" value="Clear" />
</form>

clearb = driver.find_element_by_xpath("//input[@name='continue'][@type='button']")
clearb = driver.find_element_by_xpath("//form[@id='loginForm']/input[2]")

<html>
   <div class="other" align="left" name="d1" id="nr">
    <a href="dufu.html" class="poet" id="link" name="dufu">
     Dufu</a>
    <a href="lsy.html" class="poet" id="link" name="lsy">
     LiShangYing</a>
<a href="dumu.html" class="poet" id="link" name=”dumu”>
     DuMu</a>
</body>
</html>

#-*- coding:utf-8 -*-
#By:Eastmount 2021-05-29
import time
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
#启动驱动
driver = webdriver.Firefox()
driver.get("file://C:/Users/../Desktop/09.selenium/blog09_02.html")
print(driver.title)
#分别定位三个超链接
test_poet1 = driver.find_element_by_link_text('Dufu')
print(test_poet1.text)
test_poet2 = driver.find_element_by_link_text('LiShangYing')
print(test_poet2.text)
test_poet3 = driver.find_element_by_link_text('DuMu')
print(test_poet3.text)
#定位超链接部分元素
test_poet4 = driver.find_element_by_partial_link_text('Du')
print(test_poet4.text)
#定位超链接部分元素且定位多个元素
test_poet5 = driver.find_elements_by_partial_link_text('Du')
for t in test_poet5:
    print(t.text)

<html>
  <title>李白简介</title>
</head>
   <h1>静夜思</h1>
   <p class='content'>窗前明月光，疑是地上霜。举头望明月，低头思故乡。</p>
</body>
</html>

name = driver.find_element_by_name("userName")
name.send_keys("admin")  
pwd = driver.find_element_by_name("password")
pwd.send_keys("123456")
pwd.send_keys(Keys.RETURN)

#-*- coding:utf-8 -*-
#By:Eastmount CSDN 2021-05-29
import time
from selenium import webdriver  
from selenium.webdriver.common.keys import Keys  
from selenium.webdriver.common.action_chains import ActionChains
#打开浏览器
driver = webdriver.Firefox()  
driver.get("https://www.baidu.com/")
time.sleep(1)
#点击登录链接
logins = driver.find_elements_by_name("tj_login")
for login in logins:
    print(login.text)
    print(login.get_attribute('href'))
    if login.is_displayed():
        login.click()
time.sleep(1)
#通过二次定位寻找用户名登录按钮
uesrlogins = driver.find_elements_by_xpath("//div[@class='tang-pass-footerBar']/p")
for uesrlogin in uesrlogins:
    print(uesrlogin.text)
    if uesrlogin.is_displayed():
        uesrlogin.click()
#输入密码并登陆
name = driver.find_element_by_name("userName")
name.clear
name.send_keys("Eastmount")     
pwd = driver.find_element_by_name("password")
pwd.clear
pwd.send_keys("12345678")
#暂停输入验证码 按回车键登录
time.sleep(5)
pwd.send_keys(Keys.RETURN)
driver.close()

#-*- coding:utf-8 -*-
#By:Eastmount CSDN 2021-05-29
import time
from selenium import webdriver  
from selenium.webdriver.common.keys import Keys 
driver = webdriver.Firefox()  
driver.get("https://www.baidu.com/")
print(driver.title)
print(driver.current_url)
# 百度一下，你就知道
# https://www.baidu.com/
news = driver.find_element_by_xpath("//div[@id='u1']/a[1]")
print(news.text)
print(news.get_attribute('href'))
print(news.location)
# http://news.baidu.com/
# {'y': 19.0, 'x': 456.0}

#-*- coding:utf-8 -*-
#By:Eastmount CSDN 2021-05-29
from selenium import webdriver  
from selenium.webdriver.common.keys import Keys 
driver = webdriver.Firefox()  
driver.get("https://www.baidu.com/")
elem = driver.find_element_by_id("kw")
elem.send_keys("Python")
elem.send_keys(Keys.RETURN)

from selenium.webdriver.support.ui import Select
name = driver.find_element_by_name('name')
select = Select(name)
select.select_by_index(index)
select.select_by_visible_text("text")
select.select_by_value(value)

from selenium.webdriver.support.ui import Select
name = driver.find_element_by_name('name')
select = Select(name)
all_selected_options = select.all_selected_options

for handle in driver.window_handles:
    driver.switch_to_window(handle)

#获取当前窗口句柄
now_handle = driver.current_window_handle 
print(now_handle)
#获取所有窗口句柄
all_handles = driver.window_handles 
for handle in all_handles:
    if handle!=now_handle:
        #输出待选择的窗口句柄
        print(handle)
        driver.switch_to_window(handle)
        time.sleep(1)
        #具体操作
        elem_bt = driver.find_element_by_xpath("...")

[Python从零到壹] 九.网络爬虫之Selenium基础技术万字详解（定位元素、常用方法、鼠标操作）

[Python从零到壹] 九.网络爬虫之Selenium基础技术万字详解（定位元素、常用方法、鼠标操作）

一.初识Selenium

1.安装Selenium

2.安装浏览器驱动

3.Phantomjs

二.快速开始Selenium解析

三.定位元素

1.通过ID定位元素

2.通过Name定位元素

3.通过XPath定位元素

4.通过连接文本定位超链接

5.通过标签名定位元素

6.通过类名定位元素

7.通过CSS选择器定位元素

四.常用方法和属性

1.操作元素方法

2.WebElement常用属性

五.键盘和鼠标自动化操作

1.键盘操作

2.鼠标操作

六.导航控制

1.下拉菜单交互操作

2.Window和Frame间对话框移动