577

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。我只想从给定的 URL 下载文件，然后将其保存到给定的目录。

4

30 回答 30

762

您可以创建一个 HTTPGET请求并将其通过管道response传输到可写文件流中：

const http = require('http'); // or 'https' for https:// URLs
const fs = require('fs');

const file = fs.createWriteStream("file.jpg");
const request = http.get("http://i3.ytimg.com/vi/J---aiyznGQ/mqdefault.jpg", function(response) {
  response.pipe(file);
});

如果你想支持在命令行上收集信息——比如指定目标文件或目录，或者 URL——请查看Commander之类的东西。

于 2012-08-14T02:28:16.983 回答
568

不要忘记处理错误！以下代码基于 Augusto Roman 的回答。

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

var download = function(url, dest, cb) {
  var file = fs.createWriteStream(dest);
  var request = http.get(url, function(response) {
    response.pipe(file);
    file.on('finish', function() {
      file.close(cb);  // close() is async, call cb after close completes.
    });
  }).on('error', function(err) { // Handle errors
    fs.unlink(dest); // Delete the file async. (But we don't check the result)
    if (cb) cb(err.message);
  });
};
于 2014-04-07T08:24:11.793 回答
171

正如 Michelle Tilley 所说，但使用适当的控制流程：

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

var download = function(url, dest, cb) {
  var file = fs.createWriteStream(dest);
  http.get(url, function(response) {
    response.pipe(file);
    file.on('finish', function() {
      file.close(cb);
    });
  });
}

如果不等待finish事件，天真的脚本可能会以不完整的文件结束。

编辑：感谢@Augusto Roman 指出cb应该传递给file.close，而不是显式调用。

于 2013-07-16T12:40:54.123 回答
80

说到处理错误，听请求错误也更好。我什至会通过检查响应代码来验证。此处仅对 200 响应代码认为成功，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，但我还是建议使用request 模块，因为它可以处理更多的协议（你好 HTTPS！），而http.

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：

为了使它工作https，改变

const http = require('http');

至

const http = require('https');
于 2015-08-21T07:38:18.467 回答
50

file.close()gfxmonk 的答案在回调和完成 之间存在非常紧张的数据竞争。file.close()实际上需要一个在关闭完成时调用的回调。否则，文件的立即使用可能会失败（非常罕见！）。

一个完整的解决方案是：

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

var download = function(url, dest, cb) {
  var file = fs.createWriteStream(dest);
  var request = http.get(url, function(response) {
    response.pipe(file);
    file.on('finish', function() {
      file.close(cb);  // close() is async, call cb after close completes.
    });
  });
}

如果不等待完成事件，天真的脚本可能会以不完整的文件结束。如果不通过 close 安排cb回调，您可能会在访问文件和实际准备好的文件之间发生竞争。

于 2014-04-01T18:11:58.073 回答
28

也许 node.js 发生了变化，但其他解决方案似乎存在一些问题（使用 node v8.1.2）：

  1. 您无需file.close()在finish活动中致电。默认情况下，fs.createWriteStream设置为自动关闭：https ://nodejs.org/api/fs.html#fs_fs_createwritestream_path_options
  2. file.close()应该在错误时调用。删除文件时可能不需要（unlink()），但通常是：https ://nodejs.org/api/stream.html#stream_readable_pipe_destination_options
  3. 临时文件没有被删除statusCode !== 200
  4. fs.unlink()不推荐使用没有回调的（输出警告）
  5. 如果dest文件存在；它被覆盖

下面是一个修改过的解决方案（使用 ES6 和 Promise）来处理这些问题。

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);
            }
        });
    });
}
于 2017-07-10T08:52:43.417 回答
18

对于那些寻找基于 es6 风格的 Promise 方式的人来说，我想它会是这样的：

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

function pDownload(url, dest){
  var file = fs.createWriteStream(dest);
  return new Promise((resolve, reject) => {
    var responseSent = false; // flag to make sure that response is sent only once.
    http.get(url, response => {
      response.pipe(file);
      file.on('finish', () =>{
        file.close(() => {
          if(responseSent)  return;
          responseSent = true;
          resolve();
        });
      });
    }).on('error', err => {
        if(responseSent)  return;
        responseSent = true;
        reject(err);
    });
  });
}

//example
pDownload(url, fileLocation)
  .then( ()=> console.log('downloaded file no issues...'))
  .catch( e => console.error('error while downloading', e));
于 2015-12-30T07:13:07.443 回答
16

超时解决方案，防止内存泄漏：

以下代码基于 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();
    });
});

遇到错误时不要生成文件，并且更喜欢在 X 秒后使用超时来关闭您的请求。

于 2014-10-07T09:49:22.897 回答
14

基于上面的其他答案和一些微妙的问题，这是我的尝试。

  1. 在访问网络之前使用 . 检查文件不存在fs.access。
  2. fs.createWriteStream仅当您获得200 OK状态代码时才创建。这减少了fs.unlink整理临时文件句柄所需的命令数量。
  3. 即使在 a 上，200 OK我们仍然可能reject由于EEXIST文件已经存在（想象另一个进程在我们进行网络调用时创建了该文件）。
  4. 如果您在标题中提供的链接位置之后download获得301 Moved Permanently或重定向，则递归调用。302 Found (Moved Temporarily)
  5. 递归调用的其他一些答案的问题download是它们调用resolve(download)而不是download(...).then(() => resolve())在Promise下载实际完成之前返回。这样，嵌套的承诺链以正确的顺序解析。
  6. 异步清理临时文件似乎很酷，但我也选择在完成后才拒绝，所以我知道当这个承诺解决或拒绝时，一切都开始完成。
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);
          });
    });
  });
}
于 2020-07-08T01:55:24.247 回答
10

你好，我想你可以使用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，当你想下载大、多文件时，可以使用集群模块来使用更多的cpu核心。

于 2019-02-15T09:56:07.340 回答
8

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 3rd 方库，因为它可以使用标准 Node.js 库轻松完成。

// 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

我修改了Andrey Tkachenko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()
于 2021-03-06T15:45:57.980 回答
7

Vince Yuan 的代码很棒，但似乎有问题。

function download(url, dest, callback) {
    var file = fs.createWriteStream(dest);
    var request = http.get(url, function (response) {
        response.pipe(file);
        file.on('finish', function () {
            file.close(callback); // close() is async, call callback after close completes.
        });
        file.on('error', function (err) {
            fs.unlink(dest); // Delete the file async. (But we don't check the result)
            if (callback)
                callback(err.message);
        });
    });
}
于 2014-12-02T07:06:09.797 回答
7

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'))
于 2019-09-04T17:23:33.943 回答
7 
const download = (url, path) => new Promise((resolve, reject) => {
http.get(url, response => {
    const statusCode = response.statusCode;

    if (statusCode !== 200) {
        return reject('Download error!');
    }

    const writeStream = fs.createWriteStream(path);
    response.pipe(writeStream);

    writeStream.on('error', () => reject('Error writing to file!'));
    writeStream.on('finish', () => writeStream.close(resolve));
});}).catch(err => console.error(err));
于 2017-01-18T21:14:47.013 回答
6

✅因此，如果您使用管道，它将关闭所有其他流并确保没有内存泄漏。

工作示例：

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.');
    }
  );
});

从我对“流中 .pipe 和 .pipeline 有什么区别”的回答开始。

于 2020-03-14T16:21:08.117 回答
5

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

request.download('http://res.m.ctrip.com/html5/Content/images/57.png', 
  function(err, res, body) {}
);
于 2014-12-04T03:11:44.283 回答
5

使用 http2 模块

我看到了使用http、https和request模块的答案。我想使用另一个支持 http 或 https 协议的本机 NodeJS 模块添加一个：

解决方案

对于我正在做的事情，我参考了官方的 NodeJS API，以及关于这个问题的其他一些答案。以下是我为尝试而编写的测试，它按预期工作：

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!
}

// ...

外部参考

编辑信息

  • 该解决方案是为 typescript 编写的，该函数是一个类方法function- 但是如果没有注意到这一点，如果没有正确使用我们的贡献者已如此迅速添加的声明，该解决方案将不适用于假定的 javascript 用户。谢谢！
于 2020-12-06T14:52:49.680 回答
5

使用 promise 下载，它解析一个可读流。放置额外的逻辑来处理重定向。

var http = require('http');
var promise = require('bluebird');
var url = require('url');
var fs = require('fs');
var assert = require('assert');

function download(option) {
    assert(option);
    if (typeof option == 'string') {
        option = url.parse(option);
    }

    return new promise(function(resolve, reject) {
        var req = http.request(option, function(res) {
            if (res.statusCode == 200) {
                resolve(res);
            } else {
                if (res.statusCode === 301 && res.headers.location) {
                    resolve(download(res.headers.location));
                } else {
                    reject(res.statusCode);
                }
            }
        })
        .on('error', function(e) {
            reject(e);
        })
        .end();
    });
}

download('http://localhost:8080/redirect')
.then(function(stream) {
    try {

        var writeStream = fs.createWriteStream('holyhigh.jpg');
        stream.pipe(writeStream);

    } catch(e) {
        console.error(e);
    }
});
于 2016-04-12T02:33:36.567 回答
4

download.js（即/project/utils/download.js）

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

const download = (uri, filename, callback) => {
    request.head(uri, (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);
    });
};

module.exports = { download };


应用程序.js

... 
// part of imports
const { download } = require('./utils/download');

...
// add this function wherever
download('https://imageurl.com', 'imagename.jpg', () => {
  console.log('done')
});
于 2020-05-16T23:16:14.727 回答
3

如果您使用的是 express 使用 res.download() 方法。否则 fs 模块使用。

app.get('/read-android', function(req, res) {
   var file = "/home/sony/Documents/docs/Android.apk";
    res.download(file) 
});

（或者）

   function readApp(req,res) {
      var file = req.fileName,
          filePath = "/home/sony/Documents/docs/";
      fs.exists(filePath, function(exists){
          if (exists) {     
            res.writeHead(200, {
              "Content-Type": "application/octet-stream",
              "Content-Disposition" : "attachment; filename=" + file});
            fs.createReadStream(filePath + file).pipe(res);
          } else {
            res.writeHead(400, {"Content-Type": "text/plain"});
            res.end("ERROR File does NOT Exists.ipa");
          }
        });  
    }
于 2017-04-14T18:51:14.500 回答
2

路径：img 类型：jpg 随机 uniqid

    function resim(url) {

    var http = require("http");
    var fs = require("fs");
    var sayi = Math.floor(Math.random()*10000000000);
    var uzanti = ".jpg";
    var file = fs.createWriteStream("img/"+sayi+uzanti);
    var request = http.get(url, function(response) {
  response.pipe(file);
});

        return sayi+uzanti;
}
于 2015-08-23T15:54:10.017 回答
1

编写我自己的解决方案，因为现有的不符合我的要求。

这包括什么：

  • HTTPS 下载（将包切换到httpHTTP 下载）
  • 基于承诺的功能
  • 处理转发路径（状态 302）
  • 浏览器标头 - 一些 CDN 需要
  • 来自 URL 的文件名（以及硬编码）
  • 错误处理

它是打字的，它更安全。.d.ts如果您使用纯 JS（无 Flow，无 TS）或转换为文件，请随意删除类型

index.js

import httpsDownload from httpsDownload;
httpsDownload('https://example.com/file.zip', './');

https下载。[js|ts]

import https from "https";
import fs from "fs";
import path from "path";

function download(
  url: string,
  folder?: string,
  filename?: string
): Promise<void> {
  return new Promise((resolve, reject) => {
    const req = https
      .request(url, { headers: { "User-Agent": "javascript" } }, (response) => {
        if (response.statusCode === 302 && response.headers.location != null) {
          download(
            buildNextUrl(url, response.headers.location),
            folder,
            filename
          )
            .then(resolve)
            .catch(reject);
          return;
        }

        const file = fs.createWriteStream(
          buildDestinationPath(url, folder, filename)
        );
        response.pipe(file);
        file.on("finish", () => {
          file.close();
          resolve();
        });
      })
      .on("error", reject);
    req.end();
  });
}

function buildNextUrl(current: string, next: string) {
  const isNextUrlAbsolute = RegExp("^(?:[a-z]+:)?//").test(next);
  if (isNextUrlAbsolute) {
    return next;
  } else {
    const currentURL = new URL(current);
    const fullHost = `${currentURL.protocol}//${currentURL.hostname}${
      currentURL.port ? ":" + currentURL.port : ""
    }`;
    return `${fullHost}${next}`;
  }
}

function buildDestinationPath(url: string, folder?: string, filename?: string) {
  return path.join(folder ?? "./", filename ?? generateFilenameFromPath(url));
}

function generateFilenameFromPath(url: string): string {
  const urlParts = url.split("/");
  return urlParts[urlParts.length - 1] ?? "";
}

export default download;
于 2020-08-03T17:21:25.563 回答
1

如果没有库，只是指出它可能是错误的。这里有几个：

这是我的建议：

  • 调用系统工具，如wget或curl
  • 使用一些工具，比如node-wget-promise，它也很容易使用。 var wget = require('node-wget-promise'); wget('http://nodejs.org/images/logo.svg');
于 2018-02-25T03:25:42.523 回答
0 
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);
  });
};
于 2018-04-09T05:25:46.047 回答
0

这是另一种在没有第三方依赖和搜索重定向的情况下处理它的方法：

        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.
              });
            });
          }
于 2019-10-23T10:25:55.897 回答
0 
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');
});
于 2019-02-15T03:27:05.427 回答
-1

我发现这种方法最有帮助，尤其是在涉及 pdf 和随机其他文件时。

import fs from "fs";

  fs.appendFile("output_file_name.ext", fileDataInBytes, (err) => {
    if (err) throw err;
    console.log("File saved!");
  });
于 2021-02-15T17:58:46.547 回答
-1

您可以尝试使用res.redirecthttps 文件下载 url，然后它将下载文件。

喜欢：res.redirect('https//static.file.com/file.txt');

于 2018-06-07T11:33:49.027 回答
-3

我建议你使用res.download相同的如下：

app.get('/download', function(req, res){
  const file = `${__dirname}/folder/abc.csv`;
  res.download(file); // Set disposition and send it.
});
于 2020-10-21T08:35:15.237 回答
-4 
var requestModule=require("request");

requestModule(filePath).pipe(fs.createWriteStream('abc.zip'));
于 2017-06-01T09:25:49.770 回答