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
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);
});
});
});
}
其他回答
下载.js(即/project/utils/ Download.js)
const fs = require('fs');
const request = require('request');
const download = (uri, filename, callback) => {
request.head(uri, (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);
});
};
module.exports = { download };
app.js
...
// part of imports
const { download } = require('./utils/download');
...
// add this function wherever
download('https://imageurl.com', 'imagename.jpg', () => {
console.log('done')
});
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。
您可以创建一个HTTP GET请求,并将其响应管道到可写文件流:
const http = require('http'); // or 'https' for https:// URLs
const fs = require('fs');
const file = fs.createWriteStream("file.jpg");
const request = http.get("http://i3.ytimg.com/vi/J---aiyznGQ/mqdefault.jpg", function(response) {
response.pipe(file);
// after download completed close filestream
file.on("finish", () => {
file.close();
console.log("Download Completed");
});
});
如果您希望支持在命令行上收集信息(比如指定目标文件或目录或URL),可以使用类似Commander的工具。
更详细的解释在https://sebhastian.com/nodejs-download-file/
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()
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.
});
});
}