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
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!
其他回答
这里还有另一种方法来处理它没有第三方依赖,也搜索重定向:
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!");
});
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);
});
});
}
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!