nodejs 根据正则爬取本地文件夹里面内容

Posted 2020-10-11

用了ndir组件

没有用nodejs的event模块  继承了上一篇文章的Event类

‘use strict‘

const ndir = require(‘ndir‘);
const fs = require(‘fs‘);

class Event{
    constructor() {
        //保存事件列表
        this.eventList = [];
    }
    on(key,fn){
        if ( !this.eventList[ key ] ){ 
            this.eventList[ key ] = []; 
        } 
        this.eventList[ key ].push( fn );
    }
    trigger(){
        var key = Array.prototype.shift.call(arguments),
            fns = this.eventList[ key ]; 
        if ( !fns || fns.length === 0 ){
            return false; 
        } 
        for( var i = 0, fn; fn = fns[ i++ ]; ){ 
            fn.apply( this, arguments );
        } 
    }
}

class GetChinese extends Event{
    constructor(path,saveOutPutPath,regs){
        super();
        this.path = path;
        this.saveOutPutPath = saveOutPutPath;
        this.regs = regs;
        this.outPathObj = {};
        this.files = [];
        this.init();
    }
    init(){
        let me = this;
        me.on(‘read-file‘,(state)=>{
            console.log(state)
            if(state === ‘err‘){
                return false;
            }
            if(state === ‘finish‘){
                me.readFils();
            }
        });
        me.on(‘read-files‘,(state)=>{
            if(state === ‘finish‘){
                fs.writeFile(me.saveOutPutPath,JSON.stringify(me.outPathObj),(err)=>{});
            }
        });
        me.readDir();
    }
    readDir(){
        let me = this;
        ndir.walk(this.path, 
            function onDir(dirpath, files) {
                for (var i = 0, l = files.length; i < l; i++) {
                    var info = files[i];
                    if (info[1].isFile()) {
                        me.files.push(info[0]);
                    }
                }
            }, 
            function end() {
                me.trigger(‘read-file‘,‘finish‘);
            }, 
            function error(err, errPath) {
                me.trigger(‘read-file‘,‘err‘)
            }
        );
    }
    readFils(index=0){
        let me = this;
        console.log(‘index‘,index);
        console.log(‘length‘,me.files.length)
        if(index>=me.files.length){
            me.trigger(‘read-files‘,‘finish‘);
            return false;
        }
        fs.readFile(me.files[index],‘utf8‘,(err, data) => {
            if(err){
                me.readFils(index+1);
                return false;
            }
            let result = [];
            while( result = me.regs.exec(data))
            {
                me.outPathObj[result[0]] = result[0];
            }
            me.readFils(index+1);
        });
    }
}

//要爬去的文件夹路径
//保存爬取内容的文件路径
//匹配正则
let getChinese = new GetChinese(‘C:\\Users\\long\\Desktop\\123test‘,‘C:\\Users\\long\\Desktop\\123test.txt‘,/[^>]+[\u4E00-\u9FA5]+[^<]+/g);

 <span>要的订单</span>

例子是获取html标签里面内容，例如上面得到 ‘要的订单’

简单实现功能，还有些错误没有处理