python基础语法+爬虫+图像处理+NumpyPandas数据处理(12天速成，第7天下-爬取图书封面图片)

# 非文本爬取
    # 图片、音频、视频、文档等
    # 实现批量自动化下载

#1、获取资源的路径url
#2、访问地址，得到数据（字节序列）
#3、本地存储（写文件）

import requests
from bs4 import BeautifulSoup as BS

hds = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36'}

urls=[] # 存图片的url

for i in range(5):
    url = 'https://book.douban.com/tag/%E5%B0%8F%E8%AF%B4?start={}&type=T'.format(i*20)
    resp = requests.get(url,headers=hds);
    ct = resp.content.decode("utf-8");
    html=BS(ct,'lxml'); # 封装成bs对象
    imgs = html.select('.subject-item .pic img'); # 图片标签数组
    # print(len(imgs))
    for img in imgs:
        urls.append(img['src'])
print(len(urls))

100

i = 1;
for url in urls:
    resp = requests.get(url,headers = hds);
    ct = resp.content
    f = open(r'D:\books\{}{}'.format(i,'.jpg'),'wb');
    f.write(ct);
    f.close();
    i = i+1;
    print('下载完毕:',i)