node.js爬虫数据库创建

npm install express mongoose axios cheerio

const mongoose = require('mongoose');

mongoose.connect('mongodb://localhost:27017/mydatabase', {
  useNewUrlParser: true,
  useUnifiedTopology: true,
});

const db = mongoose.connection;
db.on('error', console.error.bind(console, 'connection error:'));
db.once('open', () => {
  console.log('Database connected');
});

const Schema = mongoose.Schema;

const itemSchema = new Schema({
  title: String,
  link: String,
  description: String,
});

const Item = mongoose.model('Item', itemSchema);

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

async function scrapeData() {
  try {
    const response = await axios.get('https://example.com');
    const $ = cheerio.load(response.data);

    $('div.item').each((index, element) => {
      const title = $(element).find('h2').text();
      const link = $(element).find('a').attr('href');
      const description = $(element).find('p').text();

      const newItem = new Item({ title, link, description });
      newItem.save((err) => {
        if (err) return console.error(err);
        console.log('Item saved');
      });
    });
  } catch (error) {
    console.error('Error scraping data:', error);
  }
}

scrapeData();