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
我更喜欢request(),因为你可以同时使用http和https。
request('http://i3.ytimg.com/vi/J---aiyznGQ/mqdefault.jpg')
.pipe(fs.createWriteStream('cat.jpg'))
其他回答
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。
就像Michelle Tilley说的,但是要有适当的控制流:
var http = require('http');
var fs = require('fs');
var download = function(url, dest, cb) {
var file = fs.createWriteStream(dest);
http.get(url, function(response) {
response.pipe(file);
file.on('finish', function() {
file.close(cb);
});
});
}
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。
编辑:感谢@Augusto Roman指出cb应该传递到文件。Close,没有显式调用。
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}: ${response.statusMessage}`);
}
});
request.on('error', err => {
reject(err.message);
});
});
});
}
现代版本(ES6, Promise, Node 12。X +)适用于https/http。它还支持重定向302和301。我决定不使用第三方库,因为它可以很容易地使用标准Node.js库。
// download.js
import fs from 'fs'
import https from 'https'
import http from 'http'
import { basename } from 'path'
import { URL } from 'url'
const TIMEOUT = 10000
function download (url, dest) {
const uri = new URL(url)
if (!dest) {
dest = basename(uri.pathname)
}
const pkg = url.toLowerCase().startsWith('https:') ? https : http
return new Promise((resolve, reject) => {
const request = pkg.get(uri.href).on('response', (res) => {
if (res.statusCode === 200) {
const file = fs.createWriteStream(dest, { flags: 'wx' })
res
.on('end', () => {
file.end()
// console.log(`${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()
说到处理错误,监听请求错误甚至更好。我甚至会通过检查响应代码来验证。这里认为只有200个响应代码成功,但其他代码可能很好。
const fs = require('fs');
const http = require('http');
const download = (url, dest, cb) => {
const file = fs.createWriteStream(dest);
const request = http.get(url, (response) => {
// check if response is success
if (response.statusCode !== 200) {
return cb('Response status was ' + response.statusCode);
}
response.pipe(file);
});
// close() is async, call cb after close completes
file.on('finish', () => file.close(cb));
// check for request error too
request.on('error', (err) => {
fs.unlink(dest, () => cb(err.message)); // delete the (partial) file and then return the error
});
file.on('error', (err) => { // Handle errors
fs.unlink(dest, () => cb(err.message)); // delete the (partial) file and then return the error
});
};
尽管这段代码相对简单,但我建议使用request模块,因为它处理更多http不支持的协议(你好,HTTPS!)。
可以这样做:
const fs = require('fs');
const request = require('request');
const download = (url, dest, cb) => {
const file = fs.createWriteStream(dest);
const sendReq = request.get(url);
// verify response code
sendReq.on('response', (response) => {
if (response.statusCode !== 200) {
return cb('Response status was ' + response.statusCode);
}
sendReq.pipe(file);
});
// close() is async, call cb after close completes
file.on('finish', () => file.close(cb));
// check for request errors
sendReq.on('error', (err) => {
fs.unlink(dest, () => cb(err.message)); // delete the (partial) file and then return the error
});
file.on('error', (err) => { // Handle errors
fs.unlink(dest, () => cb(err.message)); // delete the (partial) file and then return the error
});
};
编辑:
要使它与https兼容,请更改
const http = require('http');
to
const http = require('https');