node.js爬虫 极客学院

const axios = require('axios');
const cheerio = require('cheerio');

async function fetchPage(url) {
    try {
        const response = await axios.get(url, { timeout: 5000 });
        const $ = cheerio.load(response.data);
        // 处理页面数据...
    } catch (error) {
        console.error('Error fetching page:', error);
    }
}

// 使用 setInterval 控制请求频率
setInterval(() => {
    fetchPage('http://example.com');
}, 10000); // 每 10 秒发送一次请求

const puppeteer = require('puppeteer');

(async () => {
    const browser = await puppeteer.launch();
    const page = await browser.newPage();
    await page.goto('http://example.com');
    const content = await page.content();
    const $ = cheerio.load(content);
    // 处理页面数据...
    await browser.close();
})();

async function fetchData() {
    try {
        const data = await someAsyncOperation();
        // 处理数据...
    } catch (error) {
        console.error('Error:', error);
    }
}