爬虫爬取网页图片

代码

import urllib.request
import requests
from lxml import etree
url = "https://699pic.com/tupian/fengjing.html"



def schedule(blocknum,blocksize,totalsize):
    per = 100*blocknum*blocksize/totalsize
    if per>100:
        per=100
    print('下载进度：%d'%(per))
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.84 Safari/537.36'}
response = requests.get(url,headers=headers)
if response.status_code==200:
    data = response.text
    with open('.\page\img.html','w',encoding='utf-8') as w:
        w.write(data)
    html = etree.HTML(data)
    img_url = html.xpath('//img/@src')
    if len(img_url)>0:
        for index,img in enumerate(img_url):
            urllib.request.urlretrieve('http:'+img,'./images/img'+str(index)+'.jpg',schedule)
            print('--------->下载第',index,'张图片完毕')

爬取效果

爬取结果