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
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');
其他回答
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);
});
});
});
}
超时解决方案,防止内存泄漏:
下面的代码是基于Brandon Tilley的回答:
var http = require('http'),
fs = require('fs');
var request = http.get("http://example12345.com/yourfile.html", function(response) {
if (response.statusCode === 200) {
var file = fs.createWriteStream("copy.html");
response.pipe(file);
}
// Add timeout.
request.setTimeout(12000, function () {
request.abort();
});
});
当您得到一个错误时,不要创建文件,并倾向于使用超时在X秒后关闭您的请求。
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.
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/
我建议你使用res.download,如下:
app.get('/download', function(req, res){
const file = `${__dirname}/folder/abc.csv`;
res.download(file); // Set disposition and send it.
});