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
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);
});
});
}
其他回答
不要忘记处理错误!下面的代码是基于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);
});
};
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!
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.
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);
});
};
Gfxmonk的答案在回调和file.close()完成之间有一个非常紧张的数据竞赛。File.close()实际上接受一个回调函数,该函数在close完成时被调用。否则,立即使用文件可能会失败(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finish事件,幼稚的脚本可能最终得到一个不完整的文件。如果不通过close调度cb回调,您可能会在访问文件和文件实际准备就绪之间出现竞争。