【python markdown 转json、txt文件】

通过python实现指定目录下md文件转换为json或者TXT文件

1.markdown 转txt

```python
import os
import re
import markdown
import html2text


def traverse_dir_files(root_dir, ext=None, is_sorted=True):
    """
    列出文件夹中的文件, 深度遍历
    :param root_dir: 根目录
    :param ext: 后缀名
    :param is_sorted: 是否排序，耗时较长
    :return: [文件路径列表, 文件名称列表]
    """
    names_list = []
    paths_list = []
    for parent, _, fileNames in os.walk(root_dir):
        for name in fileNames:
            if name.startswith('.'):  # 去除隐藏文件
                continue
            if ext:  # 根据后缀名搜索
                if name.endswith(tuple(ext)):
                    names_list.append(name)
                    paths_list.append(os.path.join(parent, name))
            else:
                names_list.append(name)
                paths_list.append(os.path.join(parent, name))
    if not names_list:  # 文件夹为空
        return paths_list, names_list
    # if is_sorted:
    #     paths_list, names_list = sort_two_list(paths_list, names_list)
    print(paths_list)
    return paths_list
def remove_code_blocks(text):
    return re.sub(r'```(.*?)```', '', text, flags=re.DOTALL)
        
def md_to_txt2(md_file, txt_file):
    txt_content = ''
    title = os.path.basename(md_file).replace('.md','').strip()
    # 读取Markdown文件内容
    with open(md_file, 'r', encoding='utf-8') as f:
        markdown_text = f.read()
    
    # 将Markdown转换为HTML
    html_content = markdown.markdown(markdown_text)
    
    # 使用html2text将HTML转换为纯文本
    text_converter = html2text.HTML2Text()
    text_converter.ignore_links = True
    plain_text = text_converter.handle(html_content)
    
    os.makedirs(os.path.dirname(txt_file), exist_ok=True) # 如果目录不存在则创建目录
    with open(os.path.join(txt_file,title+'.txt'), 'w', encoding='utf-8') as f:
        f.write(plain_text)
        print("转换完成：%s" % (md_file))

def readlist(path, txt_dir):
    path_list = traverse_dir_files(root_dir=path, ext='.md')
    res = []
    for path_str in path_list:
        try:
            md_to_txt2(path_str, txt_dir)
        except Exception as e:
            print(path_str + '---------error-----------')
            print(e)



if __name__ == '__main__':
    md_file = 'C:\\Users\\MuMu\\Desktop\\md' # Markdown文件路径
    txt_dir = 'C:\\Users\\MuMu\\Desktop\\TXT' # 转换后的纯文本文件存放的目录路径
    readlist(md_file, txt_dir)

2.markdown 转json

import os
import re
import json
import requests
import base64

# 主程序
md_directory = 'C:\\Users\\MuMu\\Desktop\\md'  # 指定.md文件目录
json_directory = 'C:\\Users\\MuMu\\Desktop\\TXT'  # 指定生成.json文件的根目录

def parse_markdown_file(file_path):
    """解析单个.md文件并生成分页结果"""
    with open(file_path, 'r', encoding='utf-8') as file:
        content = file.read()

    result = []
    pages = content.split('------------------------------------------------------------------')  # 假设用横线分隔页码

    for idx, page in enumerate(pages):
        page_num = f"Page_{str(idx + 1).zfill(3)}"
        page_result = []
        
        # 匹配标题（假设标题格式为 ## 或 # ）
        titles = re.findall(r'##?\s+(.+)', page)
        for title in titles:
            page_result.append({
                "type": "title",
                "text": title.strip()
            })
        
        # 匹配列表
        lists = re.findall(r'^\d+\.\s+(.+)', page, re.MULTILINE)
        for lst in lists:
            page_result.append({
                "type": "list",
                "text": lst.strip()
            })

        # 匹配表格    
        table_pattern = re.compile(r'<table>.*?</table>', re.DOTALL)  
        # 查找所有 <table></table> 标签内容
        tables = table_pattern.findall(content)
        for table in tables:
            page_result.append({
                "type": "table",
                "text": table.strip()
            })

        # 匹配普通文本
        # texts = re.split(r'##?\s+.+', page)
        # for text in texts:
        #     page_result.append({
        #         "type": "text",
        #         "text": text.strip()
        #     })

        # 匹配普通文本，移除图片URL后的内容
        page_no_url = remove_image_urls(page)
        texts = re.split(r'##?\s+.+', page_no_url)
        for text in texts:
            cleaned_text = text.strip()
            if cleaned_text:  # 忽略空白文本
                page_result.append({
                    "type": "text",
                    "text": cleaned_text
                })
        # 添加图片信息
        page_result.extend(extract_image_data(page))

        # 构建分页结果
        result.append({
            "page_num": page_num,
            "result": page_result
        })
    
    return result

def save_json(data, output_file):
    """将数据保存为JSON文件"""
    os.makedirs(os.path.dirname(output_file), exist_ok=True)  # 创建输出目录
    with open(output_file, 'w', encoding='utf-8') as f:
        json.dump(data, f, ensure_ascii=False, indent=4)

def process_md_file(md_file, json_root):
    """处理单个.md文件并生成对应的.json文件"""
    result = {
        "code": 1,
        "message": "操作成功",
        "file_name": os.path.basename(md_file),
        "result": parse_markdown_file(md_file)
    }

    # 生成对应的json文件路径
    relative_path = os.path.relpath(md_file, md_directory)
    json_file = os.path.join(json_root, os.path.splitext(relative_path)[0] + ".json")
    
    # 保存结果到json文件
    save_json(result, json_file)

def process_md_files(directory, json_root):
    """遍历目录下所有.md文件并生成对应的.json文件"""
    for root, _, files in os.walk(directory):
        for file_name in files:
            if file_name.endswith(".md"):
                md_file = os.path.join(root, file_name)
                process_md_file(md_file, json_root)


# 解析目录下的.md文件并生成对应的.json文件
process_md_files(md_directory, json_directory)

print("解析完成，所有结果已保存到对应的json文件中")

2.1.编辑脚本，修改下面内容

md_directory = ‘/opt/markdown/md’ # 指定.md文件目录 json_directory =
‘/data/json/’ # 指定生成.json文件的根目录

2.2.创建导出json目录

mkdir -p /data/json/

2.3.执行脚本

python process_md_to_json.py