cronicas-periodisticas-wp-download-full/generate-epub.ts

import { readFile } from 'fs/promises';
import Epub from 'epub-gen';
import { parseHTML } from 'linkedom';

interface BlogPost {
  title: string;
  author: string;
  content: string;
  url: string;
}

async function generateEpub() {
  // Read the scraped posts
  const postsData = await readFile('posts.json', 'utf-8');
  const posts: BlogPost[] = JSON.parse(postsData);

  if (posts.length === 0) {
    console.error('No posts found in posts.json');
    return;
  }

  // Prepare ePub options
  const options = {
    title: 'Crónicas Periodísticas',
    author: posts[0].author, // Using first post's author as main author
    output: 'cronicas-periodisticas.epub',
    content: [],
    appendChapterTitles: true,
    verbose: true
  };

  // Convert each post to ePub chapter format
  for (const post of posts) {
    // Parse the content HTML and extract text nodes
    const { document } = parseHTML(`<div>${post.content}</div>`);
    
    // Get all text content from paragraphs and other text containers
    const paragraphs = [...document.querySelectorAll('p, div, span')]
      .map(el => el.textContent?.trim())
      .filter(Boolean)
      .join('\n\n');

    options.content.push({
      title: post.title,
      author: post.author,
      data: `
        <h1>${post.title}</h1>
        <p><em>Por ${post.author}</em></p>
        ${paragraphs || 'No content available'}
        <p><a href="${post.url}">Publicación original</a></p>
      `
    });
  }

  // Generate the ePub
  console.log(`Generating ePub with ${posts.length} posts...`);
  await new Epub(options).promise;
  console.log('ePub generated successfully!');
}

generateEpub().catch(console.error);