以这个网站为例,爬取美女写真。
代码如下:
from selenium import webdriver
from time import sleep
from lxml import etree
import requests
import os
# 浏览器自动化
headers = {
"User-Agent": "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/108.0.0.0 Mobile Safari/537.36 Edg/108.0.1462.54 "
}
dirName = '0107beautifulgirl' # 新建文件夹
if not os.path.exists(dirName):
os.mkdir(dirName)
# 基于浏览器的驱动程序实例化一个浏览器对象
# 下载谷歌驱动,网址:http://chromediver.storage.googleapis.com/index.html
bro = webdriver.Chrome(executable_path=r'C:\Program Files\Google\Chrome\Application\chromedriver.exe')
# 对目的网站发起请求
bro.get('https://www.yalayi.com/gallery/')
sleep(1