minnan-website/scripts/ExportToAi/ich.ts

import { writeFile } from 'fs/promises';
import { GetContentListParams, type GetContentDetailItem, type GetContentListItem } from '~/api/CommonContent';
import ProjectsContent from '~/api/inheritor/ProjectsContent';

const data = [] as Array<GetContentListItem & { detail?: GetContentDetailItem }>;

const markdownText = ref('');

// HTML转Markdown的简单实现
function htmlToMarkdown(html: string): string {
  if (!html) return '';
  
  // 处理标题
  html = html.replace(/<h1[^>]*>(.*?)<\/h1>/gi, '# $1\n\n');
  html = html.replace(/<h2[^>]*>(.*?)<\/h2>/gi, '## $1\n\n');
  html = html.replace(/<h3[^>]*>(.*?)<\/h3>/gi, '### $1\n\n');
  
  // 处理段落
  html = html.replace(/<p[^>]*>(.*?)<\/p>/gi, '$1\n\n');
  
  // 处理加粗
  html = html.replace(/<strong[^>]*>(.*?)<\/strong>/gi, '**$1**');
  html = html.replace(/<b[^>]*>(.*?)<\/b>/gi, '**$1**');
  
  // 处理斜体
  html = html.replace(/<em[^>]*>(.*?)<\/em>/gi, '*$1*');
  html = html.replace(/<i[^>]*>(.*?)<\/i>/gi, '*$1*');
  
  // 处理列表
  html = html.replace(/<ul[^>]*>([\s\S]*?)<\/ul>/gi, (match, content) => {
    return content.replace(/<li[^>]*>(.*?)<\/li>/gi, '- $1\n') + '\n';
  });
  
  html = html.replace(/<ol[^>]*>([\s\S]*?)<\/ol>/gi, (match, content, index) => {
    let count = 1;
    return content.replace(/<li[^>]*>(.*?)<\/li>/gi, () => {
      return `${count++}. $1\n`;
    }) + '\n';
  });
  
  // 处理图片
  html = html.replace(/<img[^>]*src="([^"]*)"[^>]*alt="([^"]*)"[^>]*>/gi, '![$2]($1)');
  
  // 处理链接
  html = html.replace(/<a[^>]*href="([^"]*)"[^>]*>(.*?)<\/a>/gi, '[$2]($1)');
  
  // 处理换行
  html = html.replace(/<br[^>]*>/gi, '\n');
  
  // 去除所有HTML标签
  html = html.replace(/<[^>]*>/g, '');
  
  // 处理多余的换行
  html = html.replace(/\n\s*\n/g, '\n\n');
  
  return html.trim();
}
// 生成Markdown文本
function generateMarkdown(): string {
  let md = '';
  
  data.forEach((item, index) => {
    if (index > 0) {
      md += '\n\n---\n\n';
    }
    
    // 基本信息
    md += `# ${item.title}\n\n`;
    md += `${item.desc || '无描述'}\n\n`;
    md += `## 基本信息\n\n`;
    md += `- 非遗级别: ${item.levelText || '无'}\n`;
    md += `- 非遗类别: ${item.ichTypeText || '无'}\n`;
    md += `- 地区: ${item.district || '无'}\n`;
    md += `- 批次: ${item.batchText || '无'}\n`;
    md += `- 保护单位: ${item.unit || '无'}\n\n`;
    
    // 图片
    if (item.images && item.images.length > 0) {
      md += `## 图片\n\n`;
      item.images.forEach(image => {
        md += `![${item.title}图片](${image})\n\n`;
      });
    }
    
    // 详细信息
    if (item.detail) {
      // 简介
      if (item.detail.intro) {
        md += `## 简介\n\n`;
        md += htmlToMarkdown(item.detail.intro) + '\n\n';
      }
      
      // 传承人
      if (item.detail.inheritorsList && item.detail.inheritorsList.length > 0) {
        md += `## 相关传承人\n\n`;
        if (item.detail.inheritor) {
          md += htmlToMarkdown(item.detail.inheritor) + '\n\n';
        }
        
        item.detail.inheritorsList.forEach(inheritor => {
          md += `### ${inheritor.title}\n\n`;
          md += `级别：${inheritor.levelLext || '无'}\n\n`;
          if (inheritor.image) {
            md += `![传承人头像](${inheritor.image})\n\n`;
          }
        });
      }
      
      // 传习所
      if (item.detail.ichSitesList && item.detail.ichSitesList.length > 0) {
        md += `## 相关传习所\n\n`;
        item.detail.ichSitesList.forEach(site => {
          md += `### ${site.title}\n\n`;
          md += `级别：${site.levelLext || '无'}\n\n`;
          md += `地址：${site.address || '无'}\n\n`;
          if (site.image) {
            md += `![传习所图片](${site.image})\n\n`;
          }
        });
      }
    }
  });
  
  return md;
}

(await ProjectsContent.getContentList(new GetContentListParams(), 1, 1000)).list.forEach(item => {
  data.push(item);
});
for (const item of data) {
  item.detail = (await ProjectsContent.getContentDetail(item.id)) as GetContentDetailItem;
}
// 生成Markdown文本
markdownText.value = generateMarkdown();
await writeFile('非遗项目数据.md', markdownText.value);