小编典典

使用Javascript检索二进制文件内容,对base64进行编码,然后使用Python对其进行反解码

javascript

我正在尝试使用XMLHttpRequest(使用最新的Webkit)下载二进制文件,并使用以下简单功能对base64的内容进行编码:

function getBinary(file){
    var xhr = new XMLHttpRequest();  
    xhr.open("GET", file, false);  
    xhr.overrideMimeType("text/plain; charset=x-user-defined");  
    xhr.send(null);
    return xhr.responseText;
}

function base64encode(binary) {
    return btoa(unescape(encodeURIComponent(binary)));
}

var binary = getBinary('http://some.tld/sample.pdf');
var base64encoded = base64encode(binary);

附带说明一下,以上所有内容都是标准Javascript内容,包括btoa()encodeURIComponent()

这工作非常顺利,我什至可以使用Javascript解码base64内容:

function base64decode(base64) {
    return decodeURIComponent(escape(atob(base64)));
}

var decodedBinary = base64decode(base64encoded);
decodedBinary === binary // true

现在,我想使用Python解码base64编码的内容,该内容使用一些JSON字符串来获取base64encoded字符串值。天真的,这就是我的工作:

import urllib
import base64
# ... retrieving of base64 encoded string through JSON
base64 = "77+9UE5HDQ……………oaCgA="
source_contents = urllib.unquote(base64.b64decode(base64))
destination_file = open(destination, 'wb')
destination_file.write(source_contents)
destination_file.close()

但是生成的文件无效,看起来该操作已被UTF-8,编码或其他尚不清楚的东西弄乱了。

如果在将UTF-8内容放入目标文件之前尝试对其进行解码,则会引发错误:

import urllib
import base64
# ... retrieving of base64 encoded string through JSON
base64 = "77+9UE5HDQ……………oaCgA="
source_contents = urllib.unquote(base64.b64decode(base64)).decode('utf-8')
destination_file = open(destination, 'wb')
destination_file.write(source_contents)
destination_file.close()

$ python test.py
// ...
UnicodeEncodeError: 'ascii' codec can't encode character u'\ufffd' in position 0: ordinal not in range(128)

附带说明一下,这是同一文件的两种文本表示形式的屏幕截图;左:原件;右:从base64解码的字符串创建的一个

尝试重新创建文件时,是否存在已知的技巧来规避编码问题?您将如何实现自己?

任何帮助或暗示非常感谢:)


阅读 288

收藏
2020-05-01

共1个答案

小编典典

所以我对自己回答-对此感到抱歉-但我认为这对于像我一样迷路的人可能有用;)

所以,你必须使用ArrayBuffer和设置responseType您的属性XMLHttpRequest对象实例的arraybuffer检索字节的原始数组,可以转换为使用下列方便的功能的base64(发现那里,笔者可以在这里祝福):

function base64ArrayBuffer(arrayBuffer) {
  var base64    = ''
  var encodings = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/'

  var bytes         = new Uint8Array(arrayBuffer)
  var byteLength    = bytes.byteLength
  var byteRemainder = byteLength % 3
  var mainLength    = byteLength - byteRemainder

  var a, b, c, d
  var chunk

  // Main loop deals with bytes in chunks of 3
  for (var i = 0; i < mainLength; i = i + 3) {
    // Combine the three bytes into a single integer
    chunk = (bytes[i] << 16) | (bytes[i + 1] << 8) | bytes[i + 2]

    // Use bitmasks to extract 6-bit segments from the triplet
    a = (chunk & 16515072) >> 18 // 16515072 = (2^6 - 1) << 18
    b = (chunk & 258048)   >> 12 // 258048   = (2^6 - 1) << 12
    c = (chunk & 4032)     >>  6 // 4032     = (2^6 - 1) << 6
    d = chunk & 63               // 63       = 2^6 - 1

    // Convert the raw binary segments to the appropriate ASCII encoding
    base64 += encodings[a] + encodings[b] + encodings[c] + encodings[d]
  }

  // Deal with the remaining bytes and padding
  if (byteRemainder == 1) {
    chunk = bytes[mainLength]

    a = (chunk & 252) >> 2 // 252 = (2^6 - 1) << 2

    // Set the 4 least significant bits to zero
    b = (chunk & 3)   << 4 // 3   = 2^2 - 1

    base64 += encodings[a] + encodings[b] + '=='
  } else if (byteRemainder == 2) {
    chunk = (bytes[mainLength] << 8) | bytes[mainLength + 1]

    a = (chunk & 64512) >> 10 // 64512 = (2^6 - 1) << 10
    b = (chunk & 1008)  >>  4 // 1008  = (2^6 - 1) << 4

    // Set the 2 least significant bits to zero
    c = (chunk & 15)    <<  2 // 15    = 2^4 - 1

    base64 += encodings[a] + encodings[b] + encodings[c] + '='
  }

  return base64
}

所以这是一个工作代码:

var xhr = new XMLHttpRequest();
xhr.open('GET', 'http://some.tld/favicon.png', false);
xhr.responseType = 'arraybuffer';
xhr.onload = function(e) {
    console.log(base64ArrayBuffer(e.currentTarget.response));
};
xhr.send();

这将记录一个表示二进制文件内容的 有效 base64编码的字符串。

编辑: 对于无法访问ArrayBufferbtoa()编码字符失败的旧版浏览器,这是获取任何二进制文件的base64编码版本的另一种方法:

function getBinary(file){
    var xhr = new XMLHttpRequest();
    xhr.open("GET", file, false);
    xhr.overrideMimeType("text/plain; charset=x-user-defined");
    xhr.send(null);
    return xhr.responseText;
}

function base64Encode(str) {
    var CHARS = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
    var out = "", i = 0, len = str.length, c1, c2, c3;
    while (i < len) {
        c1 = str.charCodeAt(i++) & 0xff;
        if (i == len) {
            out += CHARS.charAt(c1 >> 2);
            out += CHARS.charAt((c1 & 0x3) << 4);
            out += "==";
            break;
        }
        c2 = str.charCodeAt(i++);
        if (i == len) {
            out += CHARS.charAt(c1 >> 2);
            out += CHARS.charAt(((c1 & 0x3)<< 4) | ((c2 & 0xF0) >> 4));
            out += CHARS.charAt((c2 & 0xF) << 2);
            out += "=";
            break;
        }
        c3 = str.charCodeAt(i++);
        out += CHARS.charAt(c1 >> 2);
        out += CHARS.charAt(((c1 & 0x3) << 4) | ((c2 & 0xF0) >> 4));
        out += CHARS.charAt(((c2 & 0xF) << 2) | ((c3 & 0xC0) >> 6));
        out += CHARS.charAt(c3 & 0x3F);
    }
    return out;
}

console.log(base64Encode(getBinary('http://www.google.fr/images/srpr/logo3w.png')));

希望这能对我有所帮助。

2020-05-01