python批量处理URL并提取内容且按序保存到本地

import re

# 打开HTML文件
with open('html.txt', 'r') as file:
    html_content = file.read()

# 使用正则表达式提取URL
pattern = r'<img\s+data-src="([^"]+\.png)"'
urls = re.findall(pattern, html_content)

# 将URL保存到http.txt文件中
with open('HTTP.txt', 'w') as file:
    for url in urls:
        file.write(url + '\n')

import requests

# 创建一个计数器
count = 1

# 打开网址文件
with open('HTTP.txt', 'r') as file:
    # 逐行读取网址
    for line in file:
        url = line.strip()  # 去除行尾的换行符和空格

        # 下载图片并保存到本地
        response = requests.get(url)
        if response.status_code == 200:
            # 生成图片文件名
            filename = f'{count}.jpg'

            # 保存到桌面文件夹
            save_path = f'F:/桌面文件夹/tupian/{filename}'
            with open(save_path, 'wb') as image_file:
                image_file.write(response.content)
            print(f'Saved image: {save_path}')

            # 增加计数器
            count += 1
        else:
            print(f'Failed to download image from {url}')