python爬虫--selenium模块

selenium模块

selenium基本概念

selenium优势

• 便捷的获取网站中动态加载的数据
• 便捷实现模拟登陆

selenium使用流程：

1.环境安装：

pip install selenium

2.下载一个浏览器的驱动程序（谷歌浏览器）

3.实例化一个浏览器对象

基本使用

代码

from selenium import webdriver
from lxml import etree
from time import sleep

if __name__ == '__main__':

    bro = webdriver.Chrome(r"E:\google\Chrome\Application\chromedriver.exe")
    bro.get(url='http://scxk.nmpa.gov.cn:81/xk/')

    page_text = bro.page_source
    tree = etree.HTML(page_text)
    li_list = tree.xpath('//*[@id="gzlist"]/li')
    for li in li_list:
        name = li.xpath('./dl/@title')[0]
        print(name)
    sleep(5)
    bro.quit()

基于浏览器自动化的操作代码

#编写基于浏览器自动化的操作代码

- 发起请求: get(url)

- 标签定位: find系列的方法

- 标签交互: send_ keys( 'xxx' )

- 执行js程序: excute_script('jsCod')

- 前进，后退: back(),forward( )

- 关闭浏览器: quit()

代码

https://www.taobao.com/

from selenium import webdriver
from time import sleep

bro = webdriver.Chrome(executable_path=r"E:\google\Chrome\Application\chromedriver.exe")

bro.get(url='https://www.taobao.com/')

#标签定位
search_input = bro.find_element_by_id('q')
sleep(2)
#执行一组js代码，使得滚轮向下滑动
bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(2)
#标签交互
search_input.send_keys('女装')
button = bro.find_element_by_class_name('btn-search')
button.click()

bro.get('https://www.baidu.com')
sleep(2)
bro.back()
sleep(2)
bro.forward()
sleep(5)
bro.quit()

selenium处理iframe：

- 如果定位的标签存在于iframe标签之中，则必须使用switch_to.frame(id)

- 动作链(拖动) : from selenium. webdriver import ActionChains
	- 实例化一个动作链对象: action = ActionChains (bro)
	- click_and_hold(div) :长按且点击操作
	- move_by_offset(x,y)
	- perform( )让动作链立即执行
	- action.release( )释放动作链对象

代码

https://www.runoob.com/try/try.php?filename=jqueryui-api-droppable

from selenium import webdriver
from time import sleep
from selenium.webdriver import ActionChains
bro = webdriver.Chrome(executable_path=r"E:\google\Chrome\Application\chromedriver.exe")

bro.get('https://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')

bro.switch_to.frame('iframeResult')

div = bro.find_element_by_id('draggable')

#动作链
action = ActionChains(bro)
action.click_and_hold(div)

for i in range(5):
    action.move_by_offset(17,0).perform()
    sleep(0.3)

#释放动作链
action.release()

bro.quit()

selenium模拟登陆QQ空间

代码

https://qzone.qq.com/

from selenium import webdriver
from time import sleep


bro = webdriver.Chrome(executable_path=r"E:\google\Chrome\Application\chromedriver.exe")
bro.get('https://qzone.qq.com/')
bro.switch_to.frame("login_frame")

switcher = bro.find_element_by_id('switcher_plogin')
switcher.click()

user_tag = bro.find_element_by_id('u')
password_tag = bro.find_element_by_id('p')
user_tag.send_keys('1234455')
password_tag.send_keys('qwer123')
sleep(1)

but = bro.find_element_by_id('login_button')
but.click()

无头浏览器和规避检测

代码

from  selenium import webdriver
from time import sleep
#实现无可视化界面
from selenium.webdriver.chrome.options import Options
#实现规避检测
from selenium.webdriver import ChromeOptions

#实现无可视化界面
chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
#实现规避检测
option = ChromeOptions()
option.add_experimental_option('excludeSwitches',['enable-automation'])

bro = webdriver.Chrome(executable_path=r"E:\google\Chrome\Application\chromedriver.exe",chrome_options=chrome_options,options=option)

bro.get('https://www.baidu.com')
print(bro.page_source)
sleep(2)
bro.quit()