网址转Markdown

网址转Markdown

依赖package

requirements.txt

beautifulsoup4
markdownify
requests

main程序

main.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2025-03-10 08:36
# @Author  : Jack
# @File    : main

"""
main
"""
import os
import requests
from bs4 import BeautifulSoup
from markdownify import markdownify as md
from urllib.parse import urljoin, urlparse

# 获取网页内容
url = 'https://nstudy.org/p2025/99/d97d89.html'
response = requests.get(url)

# 图片下载保存路径
download_folder = 'images'
os.makedirs(download_folder, exist_ok=True)

# 如果请求成功
if response.status_code == 200:
    html_content = response.text

    # 使用 BeautifulSoup 解析 HTML，获取所有图片标签
    soup = BeautifulSoup(html_content, 'html.parser')
    images = soup.find_all('img')

    # 下载图片并保存
    for img in images:
        img_url = img.get('src')
        if not img_url:
            continue

        print(url, img_url)
        img_url = urljoin(url, img_url)
        print(url, img_url)

        # 获取图片文件名（从 URL 中提取）
        img_name = os.path.basename(urlparse(img_url).path)
        img_path = os.path.join(download_folder, img_name)

        # 下载图片并保存
        try:
            img_response = requests.get(img_url)
            with open(img_path, 'wb') as img_file:
                img_file.write(img_response.content)
            print(f"图片已下载: {img_path}")

            # 更新 HTML 中的图片链接为本地路径
            img['src'] = os.path.join(download_folder, img_name)
        except Exception as e:
            print(f"下载图片失败: {img_url}，错误: {e}")

    # 转换 HTML 为 Markdown
    markdown_content = md(str(soup))

    # 输出或保存到文件
    with open('output.md', 'w', encoding='utf-8') as f:
        f.write(markdown_content)

    print("转换完成，Markdown 文件已保存为 output.md")
else:
    print(f"网页请求失败，状态码：{response.status_code}")

运行步骤

• 安装依赖包 pip install -r requirements.txt
• 运行main.py python main.py
• 微调code来满足自己的需求

其他情况

本程序运行在 python 3.11.7