使用 Node.js 开发资讯爬虫流程

三、定时任务

cron 每天跑一跑
function job () {
 let cronJob = new cron.CronJob({
 cronTime: cronConfig.cronTime,
 onTick: () => {
  spider()
 },
 start: false
 })
 cronJob.start()
}

四、数据持久化

数据持久化理论上应该不属于爬虫关心的范围，用 mongoose ，创建Model

import mongoose from 'mongoose'
const Schema = mongoose.Schema
const NewsSchema = new Schema(
 {
 title: { type: 'String', required: true },
 url: { type: 'String', required: true },
 summary: String,
 recommend: { type: Boolean, default: false },
 source: { type: Number, required: true, default: 0 },
 status: { type: Number, required: true, default: 0 },
 createdTime: { type: Date, default: Date.now }
 },
 {
 collection: 'news'
 }
)
export default mongoose.model('news', NewsSchema)

基本操作

import { OBJ_STATUS } from '../../Constants'
class BaseService {
 constructor (ObjModel) {
 this.ObjModel = ObjModel
 }
 saveObject (objData) {
 return new Promise((resolve, reject) => {
  this.ObjModel(objData).save((err, result) => {
  if (err) {
   return reject(err)
  }
  return resolve(result)
  })
 })
 }
}
export default BaseService

资讯

import BaseService from './BaseService'
import News from '../models/News'
class NewsService extends BaseService {}
export default new NewsService(News)

愉快地保存数据

await newsService.batchSave(newsListTem)

更多内容到Github把项目clone下来看就好了。

总结