selenium框架的使用

selenium是浏览器自动化测试框架，使用前可直接pip install selenium安装

需要选择与当前使用浏览器匹配的驱动下载调用。本次采用Chrome 74版，Chrome驱动下载地址：http://chromedriver.storage.googleapis.com/index.html

使用小案例：

from selenium import webdriver
from time import sleep

bower=webdriver.Chrome(executable_path=r'C:UsersasaxhDesktopchromedriver.exe')

bower.get(url='https://www.hao123.com/')        #指定导航栏URL
sleep(2)

text_input=bower.find_element_by_name('word')
text_input.send_keys('胡歌')                     #要搜素的内容
sleep(2)

bower.find_element_by_class_name('submitInput').click() #点击搜素
sleep(3)

bower.quit()        #关闭浏览器并退出

 使用普通Chrome有界面浏览器，执行鼠标拖动事件：

from selenium import webdriver
from time import sleep
url='https://www.hao123.com/'
bower=webdriver.Chrome(executable_path=r'C:UsersasaxhDesktopchromedriver.exe')
bower.get(url)

sleep(5)
bower.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(5)
bower.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(5)
bower.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(5)
bower.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(5)
bower.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(5)
bower.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(5)
page_html=bower.page_source

with open('./hao123.html','w',encoding='utf-8')as f:
    f.write(page_html)
sleep(3)
bower.quit()

推荐使用Chrome的无界面浏览器：

from selenium.webdriver.chrome.options import Options
from selenium import webdriver
from time import sleep

chrome_options=Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')        #关闭浏览器界面

url='https://www.hao123.com/'
bower=webdriver.Chrome(executable_path=r'C:UsersasaxhDesktopchromedriver.exe',chrome_options=chrome_options)
bower.get(url)

sleep(5)
bower.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(5)
bower.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(5)
bower.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(5)
bower.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(5)
bower.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(5)
bower.execute_script('window.scrollTo(0,document.body.scrollHeight)')
sleep(5)
page_html=bower.page_source

with open('./hao123.html','w',encoding='utf-8')as f:
    f.write(page_html)
sleep(3)
print('ok')
bower.quit()

 实现QQ的模拟登录：

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

web=webdriver.Chrome(executable_path=r'C:UsersasaxhDesktopchromedriver.exe')
url='https://qzone.qq.com/'
web.get(url)
sleep(2)
web.switch_to.frame('login_frame')　　　　　　#空间采取的是iframe控件式页面 要先找到控件
web.find_element_by_id('switcher_plogin').click()
sleep(3)
web.find_element_by_id('u').send_keys("1159402553")
web.find_element_by_id('p').send_keys('1159402553')
web.find_element_by_id('login_button').click()
sleep(3)            #延迟3秒确保登录后的信息全部加载完成
q_page=web.page_source

tree=etree.HTML(q_page)
src_img=tree.xpath('//ul[@id="feed_friend_list"]/li//div[@class="user-pto"]/a/img/@src')
for src in src_img:

    with open('./q.txt','a',encoding='utf-8')as f:
        f.write(src+'
')       #简单的获取控件好友图像链接

#
# with open('./q.html','w',encoding='utf-8')as f:
#     f.write(q_page)           #个人主页持久化存储

sleep(2)
web.quit()