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

✅So if you use pipeline, it would close all other streams and make sure that there are no memory leaks. Working example: const http = require('http'); const { pipeline } = require('stream'); const fs = require('fs'); const file = fs.createWriteStream('./file.jpg'); http.get('http://via.placeholder.com/150/92c952', response => { pipeline( response, file, err => { if (err) console.error('Pipeline failed.', err); else console.log('Pipeline succeeded.'); } ); });

从我的回答“在流上。pipe和。pipeline之间有什么区别”。

其他回答

2022年底编辑:

Node v18及以上版本自带自带的Fetch API支持。使用它。

最初的回答:

对于支持承诺的节点,与其他答案相比,一个简单的(部分)Fetch API的Node shim只需要少量额外的代码:

const fs = require(`fs`);
const http = require(`http`);
const https = require(`https`);

module.exports = function fetch(url) {
  return new Promise((resolve, reject) => {
    const data = [];
    const client = url.startsWith("https") ? https : http;
    client
      .request(url, (res) => {
        res.on(`data`, (chunk) => data.push(chunk));
        res.on(`end`, () => {
          const asBytes = Buffer.concat(data);
          const asString = asBytes.toString(`utf8`);
          resolve({
            arrayBuffer: async () => asBytes,
            json: async () => JSON.parse(asString),
            text: async () => asString,
          });
        });
        res.on(`error`, (e) => reject(e));
      })
      .end();
  });
};

你可以用它来做任何你需要的事情,使用普通的fetch语法:

const fetch = require(`./tiny-fetch.js`);

fetch(`https://placekitten.com/200/300`)
  .then(res => res.arrayBuffer())
  .then(bytes => fs.writeFileSync(`kitten.jpg`, bytes))
  .catch(e => console.error(e));

fetch(`https://jsonplaceholder.typicode.com/todos/1`)
  .then(res => res.json())
  .then(obj => console.log(obj))
  .catch(e => console.error(e));

// etc.

也许node.js已经改变了,但似乎其他解决方案(使用node v8.1.2)有一些问题:

You don't need to call file.close() in the finish event. Per default the fs.createWriteStream is set to autoClose: https://nodejs.org/api/fs.html#fs_fs_createwritestream_path_options file.close() should be called on error. Maybe this is not needed when the file is deleted (unlink()), but normally it is: https://nodejs.org/api/stream.html#stream_readable_pipe_destination_options Temp file is not deleted on statusCode !== 200 fs.unlink() without a callback is deprecated (outputs warning) If dest file exists; it is overridden

下面是一个修改后的解决方案(使用ES6和promises),它可以处理这些问题。

const http = require("http");
const fs = require("fs");

function download(url, dest) {
    return new Promise((resolve, reject) => {
        const file = fs.createWriteStream(dest, { flags: "wx" });

        const request = http.get(url, response => {
            if (response.statusCode === 200) {
                response.pipe(file);
            } else {
                file.close();
                fs.unlink(dest, () => {}); // Delete temp file
                reject(`Server responded with ${response.statusCode}: ${response.statusMessage}`);
            }
        });

        request.on("error", err => {
            file.close();
            fs.unlink(dest, () => {}); // Delete temp file
            reject(err.message);
        });

        file.on("finish", () => {
            resolve();
        });

        file.on("error", err => {
            file.close();

            if (err.code === "EEXIST") {
                reject("File already exists");
            } else {
                fs.unlink(dest, () => {}); // Delete temp file
                reject(err.message);
            }
        });
    });
}

根据上面的其他答案和一些微妙的问题,下面是我的尝试。

Check the file does not exist before hitting the network by using fs.access. Only create the fs.createWriteStream if you get a 200 OK status code. This reduces the amount of fs.unlink commands required to tidy up temporary file handles. Even on a 200 OK we can still possibly reject due to an EEXIST file already exists (imagine another process created the file whilst we were doing network calls). Recursively call download if you get a 301 Moved Permanently or 302 Found (Moved Temporarily) redirect following the link location provided in the header. The issue with some of the other answers recursively calling download was that they called resolve(download) instead of download(...).then(() => resolve()) so the Promise would return before the download actually finished. This way the nested chain of promises resolve in the correct order. It might seem cool to clean up the temp file asynchronously, but I chose to reject only after that completed too so I know that everything start to finish is done when this promise resolves or rejects.

const https = require('https');
const fs = require('fs');

/**
 * Download a resource from `url` to `dest`.
 * @param {string} url - Valid URL to attempt download of resource
 * @param {string} dest - Valid path to save the file.
 * @returns {Promise<void>} - Returns asynchronously when successfully completed download
 */
function download(url, dest) {
  return new Promise((resolve, reject) => {
    // Check file does not exist yet before hitting network
    fs.access(dest, fs.constants.F_OK, (err) => {

        if (err === null) reject('File already exists');

        const request = https.get(url, response => {
            if (response.statusCode === 200) {
       
              const file = fs.createWriteStream(dest, { flags: 'wx' });
              file.on('finish', () => resolve());
              file.on('error', err => {
                file.close();
                if (err.code === 'EEXIST') reject('File already exists');
                else fs.unlink(dest, () => reject(err.message)); // Delete temp file
              });
              response.pipe(file);
            } else if (response.statusCode === 302 || response.statusCode === 301) {
              //Recursively follow redirects, only a 200 will resolve.
              download(response.headers.location, dest).then(() => resolve());
            } else {
              reject(`Server responded with ${response.statusCode}: ${response.statusMessage}`);
            }
          });
      
          request.on('error', err => {
            reject(err.message);
          });
    });
  });
}

我建议你使用res.download,如下:

app.get('/download', function(req, res){
  const file = `${__dirname}/folder/abc.csv`;
  res.download(file); // Set disposition and send it.
});
var fs = require('fs'),
    request = require('request');

var download = function(uri, filename, callback){
    request.head(uri, function(err, res, body){
    console.log('content-type:', res.headers['content-type']);
    console.log('content-length:', res.headers['content-length']);
    request(uri).pipe(fs.createWriteStream(filename)).on('close', callback);

    }); 
};   

download('https://www.cryptocompare.com/media/19684/doge.png', 'icons/taskks12.png', function(){
    console.log('done');
});