如何使用Node.js下载文件(不使用第三方库)?

2020/09/26 15:21 · javascript ·  · 0评论

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。

您可以创建一个HTTP GET请求并将其response通过管道传递到可写文件流中:

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

如果要支持在命令行上收集信息(例如指定目标文件或目录或URL),请签出Commander之类的内容

不要忘记处理错误!以下代码基于Augusto Roman的答案。

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);
  });
};

正如Michelle Tilley所说,但具有适当的控制流程:

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);
    });
  });
}

不等待finish事件,天真的脚本可能会以不完整的文件结尾。

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

说到处理错误,最好还是听听请求错误。我什至可以通过检查响应代码来验证。在这里,仅200条响应代码被认为是成功的,但是其他代码可能是不错的。

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);
        return cb(err.message);
    });

    file.on('error', (err) => { // Handle errors
        fs.unlink(dest); // Delete the file async. (But we don't check the result) 
        return cb(err.message);
    });
};

尽管这段代码相对简单,但我还是建议您使用request模块,因为它可以处理更多协议(原生HTTPS不能支持)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);
        return cb(err.message);
    });

    file.on('error', (err) => { // Handle errors
        fs.unlink(dest); // Delete the file async. (But we don't check the result)
        return cb(err.message);
    });
};

gfxmonk的答案在回调和file.close()完成之间有非常紧密的数据竞争file.close()实际上需要关闭完成时调用的回调。否则,该文件的立即使用可能会失败(非常罕见!)。

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.
    });
  });
}

不等待完成事件,天真的脚本可能会以不完整的文件结尾。如果不cb通过关闭计划回调,则可能会在访问文件和文件实际准备就绪之间产生竞争。

也许node.js已更改,但其他解决方案似乎存在一些问题(使用节点v8.1.2):

  1. 您无需file.close()finish活动中致电默认情况下,将fs.createWriteStream其设置为自动关闭: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(unlink()时可能不需要这样做,但通常它是:https : //nodejs.org/api/stream.html#stream_visible_pipe_destination_options
  3. 临时文件未在删除 statusCode !== 200
  4. fs.unlink() 不建议不使用回调(输出警告)
  5. 如果dest文件存在;它被覆盖

下面是修改后的解决方案(使用ES6和Promise),用于解决这些问题。

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);
            }
        });
    });
}

解决超时问题,防止内存泄漏:

以下代码基于Brandon Tilley的答案:

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();
    });
});

遇到错误时不要制作文件,而是希望在X秒后使用超时来关闭请求。

对于那些寻求基于es6样式基于promise的方式的人,我想它应该是这样的:

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));

文斯·袁(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);
        });
    });
}

我更喜欢request(),因为您可以同时使用http和https。

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

嗨,我认为您可以使用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,当您要下载大文件,多个文件时,可以使用群集模块使用更多的cpu内核。

✅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.');
    }
  );
});

“ .pipe和.pipeline on stream有什么区别”的答案开始

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) {}
);

使用Promise下载,可解决可读流。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);
    }
});

如果您使用Express,请使用res.download()方法。否则使用fs模块。

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

(要么)

   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");
          }
        });  
    }

根据上面的其他答案和一些细微的问题,这是我的尝试。

  1. fs.createWriteStream当获得200 OK状态代码时创建这减少了fs.unlink整理临时文件句柄所需命令
  2. 即使在上,200 OK我们仍然可能reject由于EEXIST文件已经存在。
  3. download如果在标题中提供的链接位置后得到301 Moved Permanently302 Found (Moved Temporarily)重定向,递归调用
  4. 与一些其他的答案递归调用的问题download是,他们所谓resolve(download)的替代download(...).then(() => resolve()),因此Promise实际上完成下载之前返回。这样,嵌套的诺言链就可以按正确的顺序解析。
  5. 异步清理临时文件似乎很酷,但是我也选择仅在完成之后拒绝,因此我知道当这个承诺解决或拒绝时,一切开始完成。
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) => {
    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);
    });
  });
}

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;
}

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 };

app.js

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

...
// add this function wherever
download('https://imageurl.com', 'imagename.jpg', () => {
  console.log('done')
});

因为现有的解决方案不符合我的要求,所以编写我自己的解决方案。

涵盖范围:

  • HTTPS下载(将软件包切换到httpHTTP下载)
  • 基于承诺的功能
  • 处理转发的路径(状态302)
  • 浏览器标头-一些CDN上必需
  • URL中的文件名(以及硬编码)
  • 错误处理

它被输入,更安全。如果您使用纯JS(无Flow,无TS)或转换为.d.ts文件,请随意删除类型

index.js

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

httpsDownload。[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;

需要指出的是,如果没有图书馆,这可能是一个错误。这里有一些:

这是我的建议:

  • 呼叫系统工具,例如wgetcurl
  • 使用诸如node-wget-promise之类的工具,该工具也非常易于使用。

    var wget = require('node-wget-promise');
    wget('http://nodejs.org/images/logo.svg');
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);
  });
};

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');

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');
});

这是在没有第三方依赖的情况下进行处理并搜索重定向的另一种方法:

        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.
              });
            });
          }

我们可以使用下载节点模块,它非常简单,请参考下面的
https://www.npmjs.com/package/download

var requestModule=require("request");

requestModule(filePath).pipe(fs.createWriteStream('abc.zip'));
本文地址:http://javascript.askforanswer.com/ruheshiyongnode-jsxiazaiwenjianbushiyongdisanfangku.html
文章标签: ,   ,   ,   ,  
版权声明:本文为原创文章,版权归 javascript 所有,欢迎分享本文,转载请保留出处!

文件下载

老薛主机终身7折优惠码boke112

上一篇:
下一篇:

评论已关闭!