Python爬虫（2）-Selenium控制浏览器

Selenium中提供了不少的方法来操作浏览器

1.打开浏览器

使用driver.get(‘网址’)的方式来打开浏览器

from selenium import webdriver
from selenium.webdriver import Chrome, ChromeOptions
from selenium.webdriver.common.by import By
opt = ChromeOptions()            # 创建Chrome参数对象
opt.headless = True              # 把Chrome设置成可视化无界面模式，windows/Linux 皆可
driver = webdriver.Chrome()# Chrome浏览器
driver.get("网址")

2.打开浏览器后可以控制浏览器前进和后退就使用

driver.back()#后退
driver.forward()#前进

3.浏览器刷新

driver.refresh()

4.浏览器切换网页窗口

浏览器切换标签的方法就是,

driver.current_window_handle

用selenium点击新打开了一个网页，需要告知selenium目前这个窗口是新的窗口，那么它才能早新的页面进行操作不然的话就无法操作。

from selenium import webdriver
from selenium.webdriver import Chrome, ChromeOptions
from selenium.webdriver.common.by import By
from selenium.webdriver.support import wait, expected_conditions
from selenium import webdriver

driver = webdriver.Chrome()

driver.get("https://so.csdn.net/so/search?spm=1000.2115.3001.7499&q=%E6%95%B0%E6%8D%AE%E5%BA%93%E8%AF%BE%E7%A8%8B%E8%AE%BE%E8%AE%A1&t=&u=")
driver.refresh()
driver.implicitly_wait(5)
driver.find_element(By.XPATH,'//*[@id="search"]').click()
driver.switch_to.window(driver.window_handles[-1])#表示新的窗口
f1=driver.find_element(By.CSS_SELECTOR,'div.item-hd em').text
print(f1)

如果只是在页面进行标签操作的话可以用tab切换到新的标签页而不用切换窗口
# 打开新标签页并切换到新标签页
driver.switch_to.new_window(‘tab’)

5.关闭页面和退出浏览器

操作完毕退出页面是

driver.close()

操作完毕退出浏览器是

driver.quit()

6.设置窗口大小

driver.set_window_size(1920,1080)

7.获取窗口位置

x = driver.get_window_position().get(‘x’)
y = driver.get_window_position().get(‘y’)

from selenium import webdriver

driver = webdriver.Chrome()

driver.get("https://so.csdn.net/so/search?spm=1000.2115.3001.7499&q=%E6%95%B0%E6%8D%AE%E5%BA%93%E8%AF%BE%E7%A8%8B%E8%AE%BE%E8%AE%A1&t=&u=")
    # 分别获取每个尺寸
x = driver.get_window_position().get('x')
y = driver.get_window_position().get('y')
print(x,y)

8.最大化窗口

driver.maximize_window()

9.最小化窗口

driver.minimize_window()

11.无窗口运行

opt = ChromeOptions() # 创建Chrome参数对象
opt.headless = True # 把Chrome设置成可视化无界面模式，windows/Linux 皆可
driver = Chrome(options=opt) # 创建Chrome无界面对象

from selenium import webdriver
from selenium.webdriver import Chrome, ChromeOptions
from selenium.webdriver.common.by import By
from selenium.webdriver.support import wait, expected_conditions
from selenium import webdriver
opt = ChromeOptions()            # 创建Chrome参数对象
opt.headless = True              # 把Chrome设置成可视化无界面模式，windows/Linux 皆可
driver = Chrome(options=opt)     # 创建Chrome无界面对象

driver.get("https://so.csdn.net/so/search?spm=1000.2115.3001.7499&q=%E6%95%B0%E6%8D%AE%E5%BA%93%E8%AF%BE%E7%A8%8B%E8%AE%BE%E8%AE%A1&t=&u=")
driver.refresh()
driver.implicitly_wait(5)
fx=driver.window_handles
print(fx)
driver.find_element(By.XPATH,'//*[@id="search"]').click()
driver.switch_to.window(driver.window_handles[-1])
f1=driver.find_element(By.CSS_SELECTOR,'div.item-hd em').text
print(f1)

10.全屏

driver.fullscreen_window()

11.屏幕截图

driver.save_screenshot(‘./1.png’)

from selenium import webdriver
from selenium.webdriver import Chrome, ChromeOptions
from selenium.webdriver.common.by import By
from selenium.webdriver.support import wait, expected_conditions
from selenium import webdriver
driver = webdriver.Chrome()

driver.get("https://so.csdn.net/so/search?spm=1000.2115.3001.7499&q=%E6%95%B0%E6%8D%AE%E5%BA%93%E8%AF%BE%E7%A8%8B%E8%AE%BE%E8%AE%A1&t=&u=")
driver.refresh()
driver.implicitly_wait(5)
driver.find_element(By.XPATH,'//*[@id="search"]').click()
driver.switch_to.window(driver.window_handles[-1])
f1=driver.find_element(By.CSS_SELECTOR,'div.item-hd em').text
driver.save_screenshot('./1.png')
print(f1)

12.元素截图

元素截图只是针对这个元素进行截图，但是这种截图只能是一个大概的范围精准度就不太太好。

f1.screenshot(‘./2.png’)

from selenium.webdriver.common.by import By
from selenium import webdriver
driver = webdriver.Chrome()

driver.get("https://so.csdn.net/so/search?spm=1001.2101.3001.4498&q=XPATH%E5%AE%9A%E4%BD%8D&t=&u=&s=hot")
f1=driver.find_element(By.CSS_SELECTOR,'div.search-box')
f1.screenshot('./2.png')
driver.quit()