昵图网图片无名字加数字爬虫，存文档

最新推荐文章于 2022-03-15 10:05:12 发布

daerwenke

最新推荐文章于 2022-03-15 10:05:12 发布

阅读量369

点赞数

本文链接：https://blog.csdn.net/daerwenke/article/details/118021546

版权

import requests
from lxml import etree
src_url=[]
for i in range(5):
    headers={'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.106 Safari/537.36'}
    url='https://www.ivsky.com/tupian/huoche_t657/index_{}.html'.format(str(i+1))
    data=requests.get(url,headers).text
    # print(data)
    html=etree.HTML(data)
    pic=html.xpath("/html/body/div[3]/div[2]/ul/li/div/a/img/@src")
    src_url.extend(pic)

print("开始下载!")
for i in range(len(src_url)):
    with open("D:\\pictures\\{}.jpg".format(str(i+1)),"wb")as f:
        imgs = requests.get(url='http:' + src_url[i], headers=headers).content
        f.write(imgs)
print('下载成功!')