Python爬虫实战：使用requests和BeautifulSoup批量下载图片

import requests
from bs4 import BeautifulSoup
import os

def download(url):
    '''下载图片并保存到本地。'''
    res = requests.get(url)
    img_data = res.content
    filename = os.path.join('img1', url.split('/')[-1])
    if not os.path.exists(filename):
        with open(filename, 'wb') as f:
            f.write(img_data)

def get_html():
    '''获取网页内容并解析图片链接。'''
    for i in range(3, 20):  # 获取第2到19页的图片
        url = f'http://www.netbian.com/index_{i}.htm'
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'}
        res = requests.get(url, headers=headers)
        res.encoding = 'gbk'
        if res.status_code == 200:
            html = res.text
            soup = BeautifulSoup(html, 'lxml')
            all_list = soup.find(class_ = 'list')
            all_imgs = all_list.find_all('img')
            if not os.path.exists('img1'):
                os.makedirs('img1')
            for img in all_imgs:
                src = img['src']
                download(src)

if __name__ == '__main__':
    get_html()