教你用十行node.js代码读取docx的文本

const fs = require("fs");
const AdmZip = require('adm-zip'); //引入查看zip文件的包
const zip = new AdmZip(filePath); //filePath为文件路径
let contentXml = zip.readAsText("word/document.xml");//将document.xml读取为text内容；
let str = "";
contentXml .match(/<w:t>[\s\S]*?<\/w:t>/ig).forEach((item)=>{
str += item.slice(5,-6)});
fs.writeFile("./2.txt",str,(err)=>{//将./2.txt替换为你要输出的文件路径
if(err)throw err;
});

//原代码
//str += item.replace("<w:t>","").replace("</w:t>","");
//更新代码
str += item.slice(5,-6)

var str = "<w:t>sdfjpasif aefnmasd;lf asdfsdf</w:t>";
var arr = [];
for(var i=0;i<50000;i++){
 arr.push(str);
}
console.time("replactest");
arr.forEach((item)=>{
 item.replace(/<w:t>/,"").replace(/<\/w:t>/,"");
});
console.timeEnd("replactest");
//replactest: 20.560ms

console.time("replactest2");
arr.forEach((item)=>{
 item.replace(/<\/*w:t>/g,"");
});
console.timeEnd("replactest2");
//replactest2: 14.926ms

console.time("replactest3");
arr.forEach((item)=>{
 item.replace(/(^<w:t>)|(<\/w:t>$)/g,"");
});
console.timeEnd("replactest3");
//replactest3: 14.402ms

console.time("slice");
arr.forEach((item)=>{
 item.slice(5,-6);
});
console.timeEnd("slice");
//slice: 1.718ms