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

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.

其他回答

使用http2模块

我看到了使用http、https和request模块的答案。我想添加一个使用另一个本地NodeJS模块,支持http或https协议:

解决方案

我已经参考了官方的NodeJS API,以及关于这个问题的一些其他答案。下面是我编写的测试,它可以按照预期工作:

import * as fs from 'fs';
import * as _path from 'path';
import * as http2 from 'http2';

/* ... */

async function download( host, query, destination )
{
    return new Promise
    (
        ( resolve, reject ) =>
        {
            // Connect to client:
            const client = http2.connect( host );
            client.on( 'error', error => reject( error ) );

            // Prepare a write stream:
            const fullPath = _path.join( fs.realPathSync( '.' ), destination );
            const file = fs.createWriteStream( fullPath, { flags: "wx" } );
            file.on( 'error', error => reject( error ) );

            // Create a request:
            const request = client.request( { [':path']: query } );

            // On initial response handle non-success (!== 200) status error:
            request.on
            (
                'response',
                ( headers/*, flags*/ ) =>
                {
                    if( headers[':status'] !== 200 )
                    {
                        file.close();
                        fs.unlink( fullPath, () => {} );
                        reject( new Error( `Server responded with ${headers[':status']}` ) );
                    }
                }
            );

            // Set encoding for the payload:
            request.setEncoding( 'utf8' );

            // Write the payload to file:
            request.on( 'data', chunk => file.write( chunk ) );

            // Handle ending the request
            request.on
            (
                'end',
                () =>
                {
                    file.close();
                    client.close();
                    resolve( { result: true } );
                }
            );

            /* 
                You can use request.setTimeout( 12000, () => {} ) for aborting
                after period of inactivity
            */

            // Fire off [flush] the request:
            request.end();
        }
    );
}

然后,例如:

/* ... */

let downloaded = await download( 'https://gitlab.com', '/api/v4/...', 'tmp/tmpFile' );

if( downloaded.result )
{
    // Success!
}

// ...

外部引用

https://nodejs.org/api/http2.html#http2_client_side_example https://nodejs.org/api/http2.html#http2_clienthttp2session_request_headers_options

编辑信息

解决方案是为typescript编写的,函数是一个类方法——但是没有注意到这一点,如果没有正确使用函数声明,这个解决方案将无法为假定的javascript用户工作,这是我们的贡献者迅速添加的。谢谢!

这里还有另一种方法来处理它没有第三方依赖,也搜索重定向:

        var download = function(url, dest, cb) {
            var file = fs.createWriteStream(dest);
            https.get(url, function(response) {
                if ([301,302].indexOf(response.statusCode) !== -1) {
                    body = [];
                    download(response.headers.location, dest, cb);
                  }
              response.pipe(file);
              file.on('finish', function() {
                file.close(cb);  // close() is async, call cb after close completes.
              });
            });
          }

我更喜欢request(),因为你可以同时使用http和https。

request('http://i3.ytimg.com/vi/J---aiyznGQ/mqdefault.jpg')
  .pipe(fs.createWriteStream('cat.jpg'))

说到处理错误,监听请求错误甚至更好。我甚至会通过检查响应代码来验证。这里认为只有200个响应代码成功,但其他代码可能很好。

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

const download = (url, dest, cb) => {
    const file = fs.createWriteStream(dest);

    const request = http.get(url, (response) => {
        // check if response is success
        if (response.statusCode !== 200) {
            return cb('Response status was ' + response.statusCode);
        }

        response.pipe(file);
    });

    // close() is async, call cb after close completes
    file.on('finish', () => file.close(cb));

    // check for request error too
    request.on('error', (err) => {
        fs.unlink(dest, () => cb(err.message)); // delete the (partial) file and then return the error
    });

    file.on('error', (err) => { // Handle errors
        fs.unlink(dest, () => cb(err.message)); // delete the (partial) file and then return the error
    });
};

尽管这段代码相对简单,但我建议使用request模块,因为它处理更多http不支持的协议(你好,HTTPS!)。

可以这样做:

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

const download = (url, dest, cb) => {
    const file = fs.createWriteStream(dest);
    const sendReq = request.get(url);
    
    // verify response code
    sendReq.on('response', (response) => {
        if (response.statusCode !== 200) {
            return cb('Response status was ' + response.statusCode);
        }

        sendReq.pipe(file);
    });

    // close() is async, call cb after close completes
    file.on('finish', () => file.close(cb));

    // check for request errors
    sendReq.on('error', (err) => {
        fs.unlink(dest, () => cb(err.message)); // delete the (partial) file and then return the error
    });

    file.on('error', (err) => { // Handle errors
        fs.unlink(dest, () => cb(err.message)); // delete the (partial) file and then return the error
    });
};

编辑:

要使它与https兼容,请更改

const http = require('http');

to

const http = require('https');

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) {}
);