memory-infrastructure-palace/code/utils/organize-pokemon-resources.js

/**
 * Organize Pokémon Resources
 *
 * Creates folder structure and renames files based on the order
 * they appear on the pokemon.com resources page
 *
 * Usage:
 *   node code/utils/organize-pokemon-resources.js
 *   npm run organize:pokemon
 */
import puppeteer from 'puppeteer-extra';
import StealthPlugin from 'puppeteer-extra-plugin-stealth';
import fs from 'fs';
import path from 'path';
import { fileURLToPath } from 'url';

puppeteer.use(StealthPlugin());

const __filename = fileURLToPath(import.meta.url);
const __dirname = path.dirname(__filename);

const BASE_URL =
  'https://www.pokemon.com/us/play-pokemon/about/tournaments-rules-and-resources';
const RESOURCES_DIR = path.resolve(
  __dirname,
  '../../docs/projects/pokemon-professor/Pokemon Rules & Resources'
);

/**
 * Clean filename for filesystem
 */
function sanitizeFilename(name) {
  return name
    .replace(/[<>:"/\\|?*]/g, '-')
    .replace(/\s+/g, ' ')
    .trim();
}

/**
 * Main organization function
 */
async function organizeResources() {
  console.log('🚀 Starting Pokémon Resources Organization');
  console.log(`📁 Resources directory: ${RESOURCES_DIR}\n`);

  const browser = await puppeteer.launch({
    headless: true,
    args: [
      '--no-sandbox',
      '--disable-setuid-sandbox',
      '--disable-blink-features=AutomationControlled'
    ]
  });

  try {
    const page = await browser.newPage();
    await page.setViewport({ width: 1920, height: 1080 });
    await page.setUserAgent(
      'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
    );

    console.log('🌐 Loading main page to extract structure...');
    await page.goto(BASE_URL, { waitUntil: 'networkidle0', timeout: 90000 });
    await new Promise(resolve => setTimeout(resolve, 3000));

    // Extract the page structure: sections and their resources
    const structure = await page.evaluate(() => {
      const sections = [];

      // Get the main content area
      const mainContent =
        document.querySelector('main, .main-content, article, #content') ||
        document.body;

      // Look for all text nodes and elements that might be section headers
      // The page likely uses specific patterns for section titles
      const allElements = Array.from(mainContent.querySelectorAll('*'));

      for (let i = 0; i < allElements.length; i++) {
        const element = allElements[i];
        const text = element.innerText?.trim() || '';

        // Check if this looks like a section header
        // Pattern: ends with "Rules & Resources" or "Training Videos" or similar
        const isSectionHeader =
          (text.includes('Rules & Resources') ||
            text.includes('Training Videos') ||
            text === 'Further Resources for Players') &&
          text.length < 100 &&
          !text.includes('\n') &&
          element.children.length < 3;

        if (!isSectionHeader) continue;

        const sectionTitle = text;
        const links = [];

        // Look ahead to find links belonging to this section
        // Stop when we hit another section header
        for (let j = i + 1; j < allElements.length && j < i + 50; j++) {
          const nextEl = allElements[j];
          const nextText = nextEl.innerText?.trim() || '';

          // Stop if we hit another section header
          if (
            (nextText.includes('Rules & Resources') ||
              nextText.includes('Training Videos') ||
              nextText === 'Further Resources for Players') &&
            nextText.length < 100 &&
            !nextText.includes('\n') &&
            nextEl.children.length < 3 &&
            nextText !== sectionTitle
          ) {
            break;
          }

          // Look for links in this element
          if (nextEl.tagName === 'A' && nextEl.href) {
            const linkText = nextEl.innerText.trim();
            if (
              linkText &&
              !nextEl.href.includes('javascript:') &&
              !nextEl.href.includes('#')
            ) {
              links.push({ text: linkText, href: nextEl.href });
            }
          }

          // Also check child links
          const childLinks = nextEl.querySelectorAll('a[href]');
          childLinks.forEach(a => {
            const linkText = a.innerText.trim();
            if (
              linkText &&
              !a.href.includes('javascript:') &&
              !a.href.includes('#') &&
              a.href.startsWith('http')
            ) {
              links.push({ text: linkText, href: a.href });
            }
          });
        }

        if (links.length > 0) {
          // Deduplicate links
          const uniqueLinks = [];
          const seen = new Set();
          links.forEach(link => {
            if (!seen.has(link.text)) {
              seen.add(link.text);
              uniqueLinks.push(link);
            }
          });

          sections.push({
            title: sectionTitle,
            links: uniqueLinks
          });
        }
      }

      return sections;
    });

    console.log(`\n📋 Found ${structure.length} sections\n`);

    // Deduplicate sections by title
    const uniqueSections = [];
    const seenTitles = new Set();
    structure.forEach(section => {
      if (!seenTitles.has(section.title)) {
        seenTitles.add(section.title);
        // Skip the main "Play! Pokémon Rules & Resources" section header
        // as it's just a page title, not a content section
        if (section.title !== 'Play! Pokémon Rules & Resources') {
          uniqueSections.push(section);
        }
      }
    });

    console.log(
      `📋 After deduplication: ${uniqueSections.length} unique sections\n`
    );

    // Get list of existing files
    const existingFiles = fs
      .readdirSync(RESOURCES_DIR)
      .filter(
        f =>
          !f.startsWith('.') &&
          !f.startsWith('debug') &&
          (f.endsWith('.pdf') || f.endsWith('.txt'))
      );

    console.log(`📦 Found ${existingFiles.length} files to organize\n`);

    let totalMoved = 0;
    let sectionIndex = 1;

    // Process each section
    for (const section of uniqueSections) {
      const sectionName = sanitizeFilename(section.title);
      const folderName = `${sectionIndex.toString().padStart(2, '0')}-${sectionName}`;
      const folderPath = path.join(RESOURCES_DIR, folderName);

      // Create section folder
      if (!fs.existsSync(folderPath)) {
        fs.mkdirSync(folderPath, { recursive: true });
      }

      console.log(`📂 Section ${sectionIndex}: ${section.title}`);
      console.log(`   Folder: ${folderName}`);
      console.log(`   Resources: ${section.links.length}\n`);

      let resourceIndex = 1;

      // Process each resource in this section
      for (const link of section.links) {
        const resourceName = sanitizeFilename(link.text);

        // Find matching file
        const matchingFile = existingFiles.find(f => {
          const baseName = f.replace(/\.(pdf|txt)$/, '');
          return (
            baseName === resourceName ||
            baseName.includes(resourceName) ||
            resourceName.includes(baseName)
          );
        });

        if (matchingFile) {
          const oldPath = path.join(RESOURCES_DIR, matchingFile);
          const extension = path.extname(matchingFile);
          const newName = `${sectionIndex.toString().padStart(2, '0')}-${resourceIndex.toString().padStart(2, '0')}-${resourceName}${extension}`;
          const newPath = path.join(folderPath, newName);

          // Move and rename file
          if (fs.existsSync(oldPath)) {
            fs.renameSync(oldPath, newPath);
            console.log(`   ✅ ${resourceIndex}. ${resourceName}${extension}`);
            totalMoved++;
          }
        } else {
          console.log(`   ⚠️  ${resourceIndex}. ${resourceName} (not found)`);
        }

        resourceIndex++;
      }

      console.log('');
      sectionIndex++;
    }

    // Move any remaining files to an "Other" folder
    const remainingFiles = fs
      .readdirSync(RESOURCES_DIR)
      .filter(
        f =>
          !f.startsWith('.') &&
          !fs.statSync(path.join(RESOURCES_DIR, f)).isDirectory() &&
          (f.endsWith('.pdf') || f.endsWith('.txt'))
      );

    if (remainingFiles.length > 0) {
      const otherFolder = path.join(RESOURCES_DIR, '99-Other');
      if (!fs.existsSync(otherFolder)) {
        fs.mkdirSync(otherFolder, { recursive: true });
      }

      console.log(
        `📂 Moving ${remainingFiles.length} unmatched files to Other folder\n`
      );

      remainingFiles.forEach((file, index) => {
        const oldPath = path.join(RESOURCES_DIR, file);
        const newName = `99-${(index + 1).toString().padStart(2, '0')}-${file}`;
        const newPath = path.join(otherFolder, newName);
        fs.renameSync(oldPath, newPath);
        console.log(`   ✅ ${file}`);
      });
    }

    console.log(`\n🎉 Organization complete!`);
    console.log(`📊 Statistics:`);
    console.log(`   Sections created: ${sectionIndex - 1}`);
    console.log(`   Files organized: ${totalMoved}`);
    console.log(`   Files in Other: ${remainingFiles.length}`);
  } catch (error) {
    console.error('❌ Error:', error.message);
    process.exit(1);
  } finally {
    await browser.close();
  }
}

organizeResources();