node.js - Downloading images with node.js

Question

I'm trying to write a script to download images using node.js. This is what I have so far:

var maxLength = 10 // 10mb
var download = function(uri, callback) {
  http.request(uri)
    .on('response', function(res) {
      if (res.headers['content-length'] > maxLength*1024*1024) {
        callback(new Error('Image too large.'))
      } else if (!~[200, 304].indexOf(res.statusCode)) {
        callback(new Error('Received an invalid status code.'))
      } else if (!res.headers['content-type'].match(/image/)) {
        callback(new Error('Not an image.'))
      } else {
        var body = ''
        res.setEncoding('binary')
        res
          .on('error', function(err) {
            callback(err)
          })
          .on('data', function(chunk) {
            body += chunk
          })
          .on('end', function() {
            // What about Windows?!
            var path = '/tmp/' + Math.random().toString().split('.').pop()
            fs.writeFile(path, body, 'binary', function(err) {
              callback(err, path)
            })
          })
      }
    })
    .on('error', function(err) {
      callback(err)
    })
    .end();
}

I, however, want to make this more robust:

1. Are there libraries that do this and do this better?
2. Is there a chance that response headers lie (about length, about content type)?
3. Are there any other status codes I should care about? Should I bother with redirects?
4. I think I read somewhere that binary encoding is going to be deprecated. What do I do then?
5. How can I get this to work on windows?
6. Any other ways you can make this script better?

Why: for a feature similar to imgur where users can give me a URL, I download that image, and rehost the image in multiple sizes.

Answer 1

我建议使用请求模块。下载文件就像下面的代码一样简单：

var fs = require('fs'),
    request = require('request');

var download = function(uri, filename, callback){
  request.head(uri, function(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);
  });
};

download('https://www.google.com/images/srpr/logo3w.png', 'google.png', function(){
  console.log('done');
});

Answer 2

几天前我遇到了这个问题，对于纯 NodeJS 的答案，我建议使用 Stream 将块合并在一起。

var http = require('http'),                                                
    Stream = require('stream').Transform,                                  
    fs = require('fs');                                                    

var url = 'http://www.google.com/images/srpr/logo11w.png';                    

http.request(url, function(response) {                                        
  var data = new Stream();                                                    

  response.on('data', function(chunk) {                                       
    data.push(chunk);                                                         
  });                                                                         

  response.on('end', function() {                                             
    fs.writeFileSync('image.png', data.read());                               
  });                                                                         
}).end();

最新的 Node 版本不能很好地处理二进制字符串，因此在处理二进制数据时将块与字符串合并不是一个好主意。

*使用'data.read()'时要小心，它将清空流以进行下一个'read()'操作。如果您想多次使用它，请将其存放在某个地方。

Answer 3

您可以使用Axios（基于Promise的 Node.js HTTP 客户端）在异步环境中按照您选择的顺序下载图像：

npm i axios

然后，您可以使用以下基本示例开始下载图像：

const fs = require('fs');
const axios = require('axios');

/* ============================================================
  Function: Download Image
============================================================ */

const download_image = (url, image_path) =>
  axios({
    url,
    responseType: 'stream',
  }).then(
    response =>
      new Promise((resolve, reject) => {
        response.data
          .pipe(fs.createWriteStream(image_path))
          .on('finish', () => resolve())
          .on('error', e => reject(e));
      }),
  );

/* ============================================================
  Download Images in Order
============================================================ */

(async () => {
  let example_image_1 = await download_image('https://example.com/test-1.png', 'example-1.png');

  console.log(example_image_1.status); // true
  console.log(example_image_1.error); // ''

  let example_image_2 = await download_image('https://example.com/does-not-exist.png', 'example-2.png');

  console.log(example_image_2.status); // false
  console.log(example_image_2.error); // 'Error: Request failed with status code 404'

  let example_image_3 = await download_image('https://example.com/test-3.png', 'example-3.png');

  console.log(example_image_3.status); // true
  console.log(example_image_3.error); // ''
})();

Answer 4

如果你想要进度下载试试这个：

var fs = require('fs');
var request = require('request');
var progress = require('request-progress');

module.exports = function (uri, path, onProgress, onResponse, onError, onEnd) {
    progress(request(uri))
    .on('progress', onProgress)
    .on('response', onResponse)
    .on('error', onError)
    .on('end', onEnd)
    .pipe(fs.createWriteStream(path))
};

如何使用：

  var download = require('../lib/download');
  download("https://www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png", "~/download/logo.png", function (state) {
            console.log("progress", state);
        }, function (response) {
            console.log("status code", response.statusCode);
        }, function (error) {
            console.log("error", error);
        }, function () {
            console.log("done");
        });

注意：您应该使用以下方式安装请求和请求进度模块：

npm install request request-progress --save

Answer 5

var fs = require('fs'),
http = require('http'),
https = require('https');

var Stream = require('stream').Transform;

var downloadImageToUrl = (url, filename, callback) => {

    var client = http;
    if (url.toString().indexOf("https") === 0){
      client = https;
     }

    client.request(url, function(response) {                                        
      var data = new Stream();                                                    

      response.on('data', function(chunk) {                                       
         data.push(chunk);                                                         
      });                                                                         

      response.on('end', function() {                                             
         fs.writeFileSync(filename, data.read());                               
      });                                                                         
   }).end();
};

downloadImageToUrl('https://www.google.com/images/srpr/logo11w.png', 'public/uploads/users/abc.jpg');

Answer 6

这是对 Cezary 答案的扩展。如果要将其下载到特定目录，请使用它。另外，使用 const 代替 var。这样安全。

const fs = require('fs');
const request = require('request');
var download = function(uri, filename, callback){
  request.head(uri, function(err, res, body){    
    request(uri).pipe(fs.createWriteStream(filename)).on('close', callback);
  });
};

download('https://www.google.com/images/srpr/logo3w.png', './images/google.png', function(){
  console.log('done');
});

Answer 7

在上述基础上，如果有人需要处理写入/读取流中的错误，我使用了这个版本。请注意stream.read()，如果发生写入错误，这是必需的，以便我们可以完成读取并close在读取流上触发。

var download = function(uri, filename, callback){
  request.head(uri, function(err, res, body){
    if (err) callback(err, filename);
    else {
        var stream = request(uri);
        stream.pipe(
            fs.createWriteStream(filename)
                .on('error', function(err){
                    callback(error, filename);
                    stream.read();
                })
            )
        .on('close', function() {
            callback(null, filename);
        });
    }
  });
};