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
我发现这种方法是最有帮助的,特别是当涉及到pdf和其他随机文件时。
import fs from "fs";
fs.appendFile("output_file_name.ext", fileDataInBytes, (err) => {
if (err) throw err;
console.log("File saved!");
});
其他回答
现代版本(ES6, Promise, Node 12。X +)适用于https/http。它还支持重定向302和301。我决定不使用第三方库,因为它可以很容易地使用标准Node.js库。
// 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
感谢安德烈·特卡琴科,我修改了他的要点
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()
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');
});
使用promise下载,它解析可读流。添加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);
}
});
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!
✅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”。