使用 Python 脚本下载指定网页的图片文件

import os
import requests
import re
import random

def download_images(url, save_folder):
    # 确保保存目录存在
    if not os.path.exists(save_folder):
        os.makedirs(save_folder)

    # 发送HTTP请求获取网页内容
    response = requests.get(url)
    if response.status_code != 200:
        print(f"Failed to retrieve the webpage. Status code: {response.status_code}")
        return

    # 使用正则表达式查找所有的图片URL
    image_urls = re.findall(r'<img[^>]+src=["\'](.*?)["\']', response.text)

    for img_url in image_urls:
        # 处理相对路径的URL
        if not img_url.startswith(('http://', 'https://')):
            img_url = os.path.join(url, img_url)

        # 下载图片
        img_response = requests.get(img_url)
        if img_response.status_code == 200:
            # 生成随机文件名
            random_filename = f"{random.randint(10000, 99999)}.jpg"
            save_path = os.path.join(save_folder, random_filename)

            # 保存图片
            with open(save_path, 'wb') as f:
                f.write(img_response.content)
            print(f"Downloaded and saved {img_url} as {save_path}")
        else:
            print(f"Failed to download {img_url}. Status code: {img_response.status_code}")

# 读取网址列表文件
def read_urls_from_file(file_path):
    with open(file_path, 'r') as file:
        urls = file.readlines()
    return [url.strip() for url in urls]

# 示例调用
if __name__ == "__main__":
    urls_file = 'f:\\代码\\urls.txt'  # 包含网址的文件路径
    save_folder = 'f:\\代码\\images'  # 保存图片的目录路径

    urls = read_urls_from_file(urls_file)
    for url in urls:
        download_images(url, save_folder)