src/lib/crawler/engine.ts

// hf-space/src/lib/crawler/engine.ts

import puppeteer from 'puppeteer';
import { extractTapTap } from './sites/taptap';
import { extractSteam } from './sites/steam';
import { extractGeneric } from './sites/generic';
import type { ExtractedContent } from './extractor';
import * as crypto from 'crypto';

export interface CrawlResult {
  url: string;
  title: string;
  content: string;
  contentHash: string;
  success: boolean;
  error?: string;
}

function getSiteName(url: string): string {
  if (url.includes('taptap.cn') || url.includes('taptap.io')) return 'taptap';
  if (url.includes('store.steampowered.com')) return 'steam';
  return 'generic';
}

function createHash(content: string): string {
  return crypto.createHash('sha256').update(content).digest('hex');
}

export async function crawlPage(url: string): Promise<CrawlResult> {
  const browser = await puppeteer.launch({
    headless: true,
    args: ['--no-sandbox', '--disable-setuid-sandbox', '--disable-dev-shm-usage'],
  });

  try {
    const page = await browser.newPage();
    await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36');

    await page.goto(url, { waitUntil: 'networkidle2', timeout: 30000 });

    // 等待内容渲染
    await new Promise<void>((r) => setTimeout(r, 2000));

    const html = await page.content();
    const siteName = getSiteName(url);

    let extracted: ExtractedContent;
    switch (siteName) {
      case 'taptap':
        extracted = extractTapTap(html, url);
        break;
      case 'steam':
        extracted = extractSteam(html, url);
        break;
      default:
        extracted = extractGeneric(html, url);
    }

    if (!extracted.content || extracted.content.length < 100) {
      return { url, title: extracted.title, content: '', contentHash: '', success: false, error: 'Content too short' };
    }

    return {
      url,
      title: extracted.title,
      content: extracted.content,
      contentHash: createHash(extracted.content),
      success: true,
    };
  } catch (err) {
    return { url, title: '', content: '', contentHash: '', success: false, error: String(err) };
  } finally {
    await browser.close();
  }
}