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
也许node.js已经改变了,但似乎其他解决方案(使用node v8.1.2)有一些问题:
You don't need to call file.close() in the finish event. Per default the fs.createWriteStream is set to autoClose: https://nodejs.org/api/fs.html#fs_fs_createwritestream_path_options file.close() should be called on error. Maybe this is not needed when the file is deleted (unlink()), but normally it is: https://nodejs.org/api/stream.html#stream_readable_pipe_destination_options Temp file is not deleted on statusCode !== 200 fs.unlink() without a callback is deprecated (outputs warning) If dest file exists; it is overridden
下面是一个修改后的解决方案(使用ES6和promises),它可以处理这些问题。
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);
}
});
});
}
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);
});
};
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));
路径:img 类型:JPG 随机函数
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;
}
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);
});
});
});
}