nanocode/playwright-hotspots/scripts/search-tech.js

#!/usr/bin/env node
/**
 * 搜索技术博客
 * 用法: node search-tech.js <关键词> [juejin|cnblogs|all]
 */

const https = require('https');
const fs = require('fs');
const path = require('path');

// 保存结果
function saveResult(platform, data) {
  const timestamp = new Date().toISOString().replace(/[:.]/g, '-');
  const filename = `${platform}_search_${timestamp}.json`;
  const filepath = path.join(__dirname, '../data', filename);
  
  if (!fs.existsSync(path.dirname(filepath))) {
    fs.mkdirSync(path.dirname(filepath), { recursive: true });
  }
  
  fs.writeFileSync(filepath, JSON.stringify(data, null, 2), 'utf-8');
  console.log(`💾 结果已保存: ${filepath}`);
}

// HTTP 请求
function httpGet(url, headers = {}) {
  return new Promise((resolve, reject) => {
    https.get(url, { headers }, (res) => {
      let data = '';
      res.on('data', chunk => data += chunk);
      res.on('end', () => resolve(data));
    }).on('error', reject);
  });
}

// 搜索掘金
async function searchJuejin(keyword) {
  console.log(`\n📱 搜索掘金: "${keyword}"`);
  console.log('-'.repeat(60));
  
  try {
    const url = `https://juejin.cn/search?query=${encodeURIComponent(keyword)}&type=0`;
    const html = await httpGet(url, {
      'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36',
      'Referer': 'https://juejin.cn/',
    });
    
    const items = [];
    const regex = /href="https:\/\/juejin\.cn\/post\/(\d+)"[^>]*>([^<]+)<\/a>/gi;
    let match;
    
    while ((match = regex.exec(html)) !== null && items.length < 10) {
      const title = match[2].trim();
      if (title.length > 5 && !items.find(i => i.title === title)) {
        items.push({
          rank: items.length + 1,
          title: title.substring(0, 80),
          url: `https://juejin.cn/post/${match[1]}`,
        });
      }
    }
    
    if (items.length > 0) {
      items.forEach(i => console.log(`${i.rank}. ${i.title}`));
      saveResult('juejin', { keyword, items });
      console.log(`✅ 找到 ${items.length} 条结果`);
    } else {
      console.log('⚠️ 未找到结果');
    }
    
    return items;
  } catch (e) {
    console.error('❌ 掘金搜索失败:', e.message);
    return [];
  }
}

// 搜索博客园
async function searchCnblogs(keyword) {
  console.log(`\n💻 搜索博客园: "${keyword}"`);
  console.log('-'.repeat(60));
  
  try {
    const url = `https://zzk.cnblogs.com/s?w=${encodeURIComponent(keyword)}`;
    const html = await httpGet(url, {
      'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
    });
    
    const items = [];
    // 匹配搜索结果
    const titleRegex = /<a[^>]*class="searchItemTitle"[^>]*href="([^"]+)"[^>]*>([\s\S]*?)<\/a>/gi;
    let match;
    
    while ((match = titleRegex.exec(html)) !== null && items.length < 10) {
      const url = match[1];
      const title = match[2].replace(/<[^>]+>/g, '').trim();
      
      if (title.length > 5 && !items.find(i => i.title === title)) {
        items.push({
          rank: items.length + 1,
          title: title.substring(0, 80),
          url: url.startsWith('http') ? url : `https:${url}`,
        });
      }
    }
    
    if (items.length > 0) {
      items.forEach(i => console.log(`${i.rank}. ${i.title}`));
      saveResult('cnblogs', { keyword, items });
      console.log(`✅ 找到 ${items.length} 条结果`);
    } else {
      console.log('⚠️ 未找到结果');
    }
    
    return items;
  } catch (e) {
    console.error('❌ 博客园搜索失败:', e.message);
    return [];
  }
}

// 主函数
async function main() {
  const keyword = process.argv[2];
  const platform = process.argv[3] || 'all';
  
  if (!keyword) {
    console.log('用法: node search-tech.js <关键词> [juejin|cnblogs|all]');
    process.exit(1);
  }
  
  console.log('='.repeat(60));
  console.log(`🔍 技术博客搜索: "${keyword}"`);
  console.log('='.repeat(60));
  
  if (platform === 'all' || platform === 'juejin') {
    await searchJuejin(keyword);
  }
  
  if (platform === 'all' || platform === 'cnblogs') {
    await searchCnblogs(keyword);
  }
  
  console.log('\n' + '='.repeat(60));
  console.log('搜索完成');
  console.log('='.repeat(60));
}

main().catch(console.error);