使用selenium实现站长素材图片采集

Posted 2021-11-27 wangtaobiu

from selenium import webdriver
import requests,os
from lxml import etree
from selenium.webdriver.chrome.options import Options
from urllib import request

chrome_options = Options()
chrome_options.add_argument(‘--headless‘)
chrome_options.add_argument(‘--disable-gpu‘)

pro = webdriver.Chrome(executable_path=‘./chromedriver.exe‘,options=chrome_options)

url = "http://sc.chinaz.com/tupian/haiyangshengwutupian.html"
pro.get(url)
js = ‘window.scrollTo(0,document.body.scrollHeight)‘
pro.execute_script(js)
page_text = pro.page_source

tree = etree.HTML(page_text)
url_img = tree.xpath(‘//div[@id="container"]/div[@class="box picblock col3 masonry-brick"]/div/a/img/@src‘)  #获取图片url列表
names = tree.xpath(‘//div[@id="container"]/div[@class="box picblock col3 masonry-brick"]/div/a/@alt‘)   #图片名称列表

if not os.path.exists(‘./img‘):  #生成文件夹
    os.mkdir(‘./img‘)    
for index,url in enumerate(url_img):
    img_path = ‘./img/‘ + names[index]+‘.jpg‘  #提取图片名称
    request.urlretrieve(url,img_path)