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。
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
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);
});
});
});
}
其他回答
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。
对于那些寻找es6风格的基于承诺的方式的人来说,我猜它会是这样的:
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));
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!
没有库,它可能是错误的,只是指出。以下是一些例子:
不能处理http重定向,比如这个url https://calibre-ebook.com/dist/portable,它是二进制的。 http模块不能https url,你将得到协议“https:”不支持。
以下是我的建议:
调用系统工具,如wget或curl 使用一些类似node-wget-promise的工具,使用起来也非常简单。 Var wget = require('node-wget-promise'); wget(“http://nodejs.org/images/logo.svg”);
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。