如何在不使用第三方库的情况下使用Node.js下载文件?

我不需要什么特别的东西。我只想从给定的URL下载文件,然后将其保存到给定的目录。


当前回答

现代版本(ES6, Promise, Node 12。X +)适用于https/http。它还支持重定向302和301。我决定不使用第三方库,因为它可以很容易地使用标准Node.js库。

// download.js
import fs from 'fs'
import https from 'https'
import http from 'http'
import { basename } from 'path'
import { URL } from 'url'

const TIMEOUT = 10000

function download (url, dest) {
  const uri = new URL(url)
  if (!dest) {
    dest = basename(uri.pathname)
  }
  const pkg = url.toLowerCase().startsWith('https:') ? https : http

  return new Promise((resolve, reject) => {
    const request = pkg.get(uri.href).on('response', (res) => {
      if (res.statusCode === 200) {
        const file = fs.createWriteStream(dest, { flags: 'wx' })
        res
          .on('end', () => {
            file.end()
            // console.log(`${uri.pathname} downloaded to: ${path}`)
            resolve()
          })
          .on('error', (err) => {
            file.destroy()
            fs.unlink(dest, () => reject(err))
          }).pipe(file)
      } else if (res.statusCode === 302 || res.statusCode === 301) {
        // Recursively follow redirects, only a 200 will resolve.
        download(res.headers.location, dest).then(() => resolve())
      } else {
        reject(new Error(`Download request failed, response status: ${res.statusCode} ${res.statusMessage}`))
      }
    })
    request.setTimeout(TIMEOUT, function () {
      request.abort()
      reject(new Error(`Request timeout after ${TIMEOUT / 1000.0}s`))
    })
  })
}

export default download

感谢安德烈·特卡琴科,我修改了他的要点

将其包含在另一个文件中并使用

const download = require('./download.js')
const url = 'https://raw.githubusercontent.com/replace-this-with-your-remote-file'
console.log('Downloading ' + url)

async function run() {
  console.log('Downloading file')
  try {
    await download(url, 'server')
    console.log('Download done')
  } catch (e) {
    console.log('Download failed')
    console.log(e.message)
  }
}

run()

其他回答

超时解决方案,防止内存泄漏:

下面的代码是基于Brandon Tilley的回答:

var http = require('http'),
    fs = require('fs');

var request = http.get("http://example12345.com/yourfile.html", function(response) {
    if (response.statusCode === 200) {
        var file = fs.createWriteStream("copy.html");
        response.pipe(file);
    }
    // Add timeout.
    request.setTimeout(12000, function () {
        request.abort();
    });
});

当您得到一个错误时,不要创建文件,并倾向于使用超时在X秒后关闭您的请求。

你可以使用https://github.com/douzi8/ajax-request#download

request.download('http://res.m.ctrip.com/html5/Content/images/57.png', 
  function(err, res, body) {}
);
var requestModule=require("request");

requestModule(filePath).pipe(fs.createWriteStream('abc.zip'));
function download(url, dest, cb) {

  var request = http.get(url, function (response) {

    const settings = {
      flags: 'w',
      encoding: 'utf8',
      fd: null,
      mode: 0o666,
      autoClose: true
    };

    // response.pipe(fs.createWriteStream(dest, settings));
    var file = fs.createWriteStream(dest, settings);
    response.pipe(file);

    file.on('finish', function () {
      let okMsg = {
        text: `File downloaded successfully`
      }
      cb(okMsg);
      file.end(); 
    });
  }).on('error', function (err) { // Handle errors
    fs.unlink(dest); // Delete the file async. (But we don't check the result)
    let errorMsg = {
      text: `Error in file downloadin: ${err.message}`
    }
    if (cb) cb(errorMsg);
  });
};

你好,我认为你可以使用child_process模块和curl命令。

const cp = require('child_process');

let download = async function(uri, filename){
    let command = `curl -o ${filename}  '${uri}'`;
    let result = cp.execSync(command);
};


async function test() {
    await download('http://zhangwenning.top/20181221001417.png', './20181221001417.png')
}

test()

另外,当你想下载较大、多个文件时,你可以使用集群模块来使用更多的cpu内核。