Google Translate API Hacking #knowhow #tools

01.js

function Bp(a, b) {
    var c = b.split(".");
    b = Number(c[0]) || 0;
    for (var d = [], e = 0, f = 0; f < a.length; f++) {
        var h = a.charCodeAt(f);
        128 > h ? d[e++] = h : (2048 > h ? d[e++] = h >> 6 | 192 : (55296 == (h & 64512) && f + 1 < a.length && 56320 == (a.charCodeAt(f + 1) & 64512) ? (h = 65536 + ((h & 1023) << 10) + (a.charCodeAt(++f) & 1023), d[e++] = h >> 18 | 240, d[e++] = h >> 12 & 63 | 128) : d[e++] = h >> 12 | 224, d[e++] = h >> 6 & 63 | 128), d[e++] = h & 63 | 128)
    }
    a = b;
    for (e = 0; e < d.length; e++) a += d[e], a = Ap(a, "+-a^+6");
    a = Ap(a, "+-3^+b+-f");
    a ^= Number(c[1]) || 0;
    0 > a && (a = (a & 2147483647) + 2147483648);
    c = a % 1E6;
    return c.toString() +
        "." + (c ^ b)
}

02.js

Tr.prototype.translate = function (a, b, c, d, e, f, h, k) {
    var l = this,
        m = this.a.wc(a),
        n = {
            q: b,
            sl: c,
            tl: d
        };
    this.h.sp && 0 == this.h.sp.indexOf("nmt") || (n.sp = "nmt");
    n.tc = e;
    f && (n.ctt = 1);
    h && (n.dom = 1);
    k && (n.sr = 1);
    n[Dp()] = Bp(b.join(""), Hq);
    return this.s ? this.s.b().then(function (r) {
        null != r && (n.jwtt = r, n.rurl = location.hostname);
        return l.a.na.send(n, C(Wr(m), l))
    }, function (r) {
        r && l.Vb && l.Vb(r)
    }) : this.a.na.send(n, m)
};

03.js

Hq = function () {
    function a(d) {
        return function () {
            return d
        }
    }
    var b = String.fromCharCode(107),
        c = a(String.fromCharCode(116));
    b = a(b);
    c = [c(), c()];
    c[1] = b();
    return yq["_c" + c.join(b())] || ""
}(),

04.js

Hq = function () {
    var b = 'k',
        c = 't';
    c = [c, c];
    c[1] = b();
    return yq['_c' + c.join(b())] || ''
}(),

05.js

Hq = function () {
    return yq['_ctkk'] || ''
}(),

06.js

var yq = window.google && google.translate && google.translate._const;

07.js

console.log(window.google.translate._const._ctkk);

08.cc

GURL TranslateScript::GetTranslateScriptURL() {
  GURL translate_script_url;
  // Check if command-line contains an alternative URL for translate service.
  const base::CommandLine& command_line =
      *base::CommandLine::ForCurrentProcess();
  if (command_line.HasSwitch(translate::switches::kTranslateScriptURL)) {
    translate_script_url = GURL(command_line.GetSwitchValueASCII(
        translate::switches::kTranslateScriptURL));
    if (!translate_script_url.is_valid() ||
        !translate_script_url.query().empty()) {
      LOG(WARNING) << "The following translate URL specified at the "
                   << "command-line is invalid: "
                   << translate_script_url.spec();
      translate_script_url = GURL();
    }
  }
  // Use default URL when command-line argument is not specified, or specified
  // URL is invalid.
  if (translate_script_url.is_empty())
    translate_script_url = GURL(kScriptURL);
  translate_script_url = net::AppendQueryParameter(
      translate_script_url,
      kCallbackQueryName,
      kCallbackQueryValue);
  translate_script_url = net::AppendQueryParameter(
      translate_script_url,
      kAlwaysUseSslQueryName,
      kAlwaysUseSslQueryValue);
  translate_script_url = net::AppendQueryParameter(
      translate_script_url,
      kCssLoaderCallbackQueryName,
      kCssLoaderCallbackQueryValue);
  translate_script_url = net::AppendQueryParameter(
      translate_script_url,
      kJavascriptLoaderCallbackQueryName,
      kJavascriptLoaderCallbackQueryValue);
  translate_script_url = AddHostLocaleToUrl(translate_script_url);
  translate_script_url = AddApiKeyToUrl(translate_script_url);
  return translate_script_url;
}

09.cc

const char TranslateScript::kScriptURL[] =
    "https://translate.googleapis.com/translate_a/element.js";

10.js

function _setupNS(b) {
    b = b.split(".");
    for (var a = window, c = 0; c < b.length; ++c) a.hasOwnProperty ? a.hasOwnProperty(b[c]) ? a = a[b[c]] : a = a[b[c]] = {} : a = a[b[c]] || (a[b[c]] = {});
    return a
}
window.addEventListener && "undefined" == typeof document.readyState && window.addEventListener("DOMContentLoaded", function () {
    document.readyState = "complete"
}, !1);
if (_isNS('google.translate.Element')) {
    return
}(function () {
    var c = _setupNS('google.translate._const');
    c._cest = gtConstEvalStartTime;
    gtConstEvalStartTime = undefined;
    c._cl = 'de';
    c._cac = '';
    c._cam = '';
    c._ctkk = '440159.776620256';
    var h = 'translate.googleapis.com';
    var s = (true ? 'https' : window.location.protocol == 'https:' ? 'https' : 'http') + '://';
    var b = s + h;
    c._pah = h;
    c._pas = s;
    c._pbi = b + '/translate_static/img/te_bk.gif';
    c._pci = b + '/translate_static/img/te_ctrl3.gif';
    c._pli = b + '/translate_static/img/loading.gif';
    c._plla = h + '/translate_a/l';
    c._pmi = b + '/translate_static/img/mini_google.png';
    c._ps = b + '/translate_static/css/translateelement.css';
    c._puh = 'translate.google.com';
    _loadCss(c._ps);
    _loadJs(b + '/translate_static/js/element/main_de.js');
})();

11.cc

GURL AddApiKeyToUrl(const GURL& url) {
  return net::AppendQueryParameter(url, kApiKeyName, google_apis::GetAPIKey());
}

12.cc

#if !defined(GOOGLE_API_KEY)
#define GOOGLE_API_KEY DUMMY_API_TOKEN
#endif

13.js

x.Pf = function (a, b) {
    b.g && this.l.remove(b.f);
    if (!this.b) return !1;
    if (this.l.has(b.ea(), !1)) {
        var c = this.l;
        if (c.has(b.f, !1)) {
            var d = b.f,
                e = c.a[d];
            e || (e = c.b[d], c.a[d] = e);
            b.b = e;
            b.K = !0
        } else c.remove(b.f), b.g = !0;
        zt(b)
    } else if (c = this.l, b.g) c.remove(b.f);
    else if (b.o) {
        d = b.o.replace(/<a /g, "<span ").replace(/\/a>/g, "/span>");
        b.K = !0;
        delete b.o;
        b.o = null;
        b.b = [];
        e = jg(document, Za);
        Q(e, !1);
        e.innerHTML = 0 <= d.indexOf("<i>") ? d : "<b>" + d + "</b>";
        document.body.appendChild(e);
        d = [];
        var f;
        for (f = e.firstChild; f; f = f.nextSibling)
            if ("I" ==
                f.tagName) var h = yt(b, Kg(f), f.innerHTML);
            else if ("B" == f.tagName) {
            h || (h = yt(b, "", ""));
            if (1 == b.a.length) xt(h.$, d, 0, f);
            else {
                var k = d;
                var l = f;
                var m = b.a;
                h = h.$;
                for (var n = [], r, w = l.firstChild; w; w = r) r = w.nextSibling, Ct(w);
                for (r = l.firstChild; r; r = r.nextSibling) r.attributes && r.attributes.i ? (l = parseInt(r.attributes.i.nodeValue, 10), !isNaN(l) && 0 <= l && l < m.length && (m[l].ee && n[l] ? n[l].T += r.firstChild && 3 == r.firstChild.nodeType ? r.firstChild.nodeValue : Kg(r) : n[l] = xt(h, k, l, r))) : 3 == r.nodeType && h.push({
                    R: -1,
                    T: De(r.nodeValue)
                });
                null != h && 0 < h.length && -1 == h[0].R && (1 == h.length ? h[0].R = 0 : (h[1].T = h[0].T + h[1].T, h.shift()))
            }
            h = void 0
        }
        f = b.b;
        for (k = 0; k < f.length - 1; ++k) m = f[k], h = ze(m.$[m.$.length - 1].T), h = h.charCodeAt(h.length - 1), 12288 <= h && 12351 >= h || 65280 <= h && 65519 >= h || (m.$[m.$.length - 1].T += " ");
        sg(e);
        for (e = 0; e < b.a.length; ++e) e < d.length && e < b.l.length && null != d[e] && (f = b.l[e], k = d[e].start, null != k && (m = f.substring(0, f.length - ye(f).length), " " == m && (m = ""), m && (k.T = m + ye(k.T))), k = d[e].end, null != k && (f = f.substring(ze(f).length), " " == f && (f = ""), f && (k.T =
            ze(k.T) + f)));
        1 != b.b.length || b.b[0].lf || (b.b[0].lf = b.f);
        c.write(b.f, b.b);
        zt(b)
    }
    b.H || (this.W = !1);
    c = b.g ? !0 : void 0;
    a.K += b.G;
    null != c && (a.qa = !0);
    b = Math.min(Math.floor(100 * a.K / a.f), 100);
    if (a.o != b || c) a.o = b, a.L ? (a.l(a.o, !0, c), a.W(a.K)) : a.l(a.o, !1, c);
    return !1
};

14.php

<?php
require_once __DIR__ . '/vendor/autoload.php';
use vielhuber\stringhelper\__;
use Faker\Factory;

class GoogleTranslate
{
    function translate($string)
    {
        $string = $this->parseResultPre($string);
        $args = [
            'anno' => 3,
            'client' => 'te_lib',
            'format' => 'html',
            'v' => '1.0',
            'key' => 'AIzaSyBOti4mM-6x9WDnZIjIeyEU21OpBXqWBgw',
            'logld' => 'vTE_20200210_00',
            'sl' => 'de',
            'tl' => 'en',
            'sp' => 'nmt',
            'tc' => 1,
            'sr' => 1,
            'tk' => $this->generateTk($string, $this->generateTkk()),
            'mode' => 1
        ];
        $response = __::curl(
            'https://translate.googleapis.com/translate_a/t?' . http_build_query($args),
            ['q' => $string],
            'POST',
            [
                'User-Agent' =>
                    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36',
                'Content-Length' => strlen('q=' . urlencode($string))
            ],
            false,
            false,
            3
        );
        return ['result' => $this->parseResultPost($response->result), 'status' => $response->status];
    }

    private function parseResultPre($input)
    {
        // google sometimes surrounds the translation with <i> and <b> tags
        // do distinguish real i-/b-tags, replace them (we undo that later on)
        $dom = __::str_to_dom($input);
        $xpath = new \DOMXPath($dom);
        foreach (['i', 'b'] as $tags__value) {
            foreach ($dom->getElementsByTagName($tags__value) as $divs__value) {
                $divs__value->setAttribute('data-native', 'true');
            }
        }
        $nodes = $xpath->query('/html/body//*');
        if (count($nodes) > 0) {
            $id = 1;
            foreach ($nodes as $nodes__value) {
                $nodes__value->setAttribute('gtid', $id);
                $id++;
            }
        }
        $output = __::dom_to_str($dom);
        return $output;
    }

    private function parseResultPost($input)
    {
        // sometimes google returns an array
        if (is_array($input) && !empty($input)) {
            $input = $input[0];
        }
        // discard the (outer) <i>-tags and take the content of the <b>-tags
        $output = '';
        $pointer = 0;
        $lvl_i = 0;
        $lvl_i_inner = 0;
        $lvl_b = 0;
        $lvl_b_inner = 0;
        // multibyte split to array of chars
        foreach (preg_split('//u', $input, -1, PREG_SPLIT_NO_EMPTY) as $chars__value) {
            if ($pointer >= 3 && mb_substr($input, $pointer - 3, 3) === '<i>') {
                $lvl_i_inner++;
            }
            if ($pointer >= 3 && mb_substr($input, $pointer - 3, 3) === '<b>') {
                $lvl_b_inner++;
            }
            if (mb_substr($input, $pointer, 4) === '</i>' && $lvl_i_inner > 0) {
                $lvl_i_inner--;
            }
            if (mb_substr($input, $pointer, 4) === '</b>' && $lvl_b_inner > 0) {
                $lvl_b_inner--;
            }
            if (mb_substr($input, $pointer, 3) === '<i>') {
                $lvl_i++;
            }
            if (mb_substr($input, $pointer, 3) === '<b>') {
                $lvl_b++;
            }
            if ($pointer >= 4 && mb_substr($input, $pointer - 4, 4) === '</i>' && $lvl_i > 0) {
                $lvl_i--;
            }
            if ($pointer >= 4 && mb_substr($input, $pointer - 4, 4) === '</b>' && $lvl_b > 0) {
                $lvl_b--;
            }
            $pointer++;
            // discard multiple spaces
            if ($chars__value === ' ' && mb_strlen($output) > 0 && mb_substr($output, -1) === ' ') {
                continue;
            }
            // save
            if (($lvl_b_inner >= 1 && $lvl_i_inner === 0) || ($lvl_b === 0 && $lvl_i === 0)) {
                $output .= $chars__value;
            }
        }
        $output = trim($output);
        $dom = __::str_to_dom($output);
        $xpath = new \DOMXPath($dom);
        foreach (['i', 'b'] as $tags__value) {
            foreach ($dom->getElementsByTagName($tags__value) as $divs__value) {
                $divs__value->removeAttribute('data-native');
            }
        }
        // merge neighbour elements with the same id together
        $nodes = $xpath->query('/html/body//*[@gtid]');
        if (count($nodes) > 0) {
            foreach ($nodes as $nodes__value) {
                if ($nodes__value->hasAttribute('please-remove')) {
                    continue;
                }
                $id = $nodes__value->getAttribute('gtid');
                $html = $nodes__value->nodeValue;
                $nextSibling = $nodes__value->nextSibling;
                if ($nextSibling === null) {
                    continue;
                }
                if ($nextSibling->nodeName === '#text' && trim($nextSibling->textContent) == '') {
                    $nextSibling = $nextSibling->nextSibling;
                }
                if ($nextSibling === null || $nextSibling->nodeName === '#text') {
                    continue;
                }
                $id2 = $nextSibling->getAttribute('gtid');
                if ($id !== $id2) {
                    continue;
                }
                $nextSibling->setAttribute('please-remove', '1');
                $html .= ' ' . $nextSibling->nodeValue;
                $nodes__value->nodeValue = $html;
            }
            foreach ($nodes as $nodes__value) {
                $nodes__value->removeAttribute('gtid');
                if ($nodes__value->hasAttribute('please-remove')) {
                    $nodes__value->parentNode->removeChild($nodes__value);
                }
            }
        }
        $output = __::dom_to_str($dom);
        return $output;
    }

    private function generateTkk()
    {
        $cache = sys_get_temp_dir() . '/tkk.cache';
        if (file_exists($cache) && filemtime($cache) > strtotime('now - 1 hour')) {
            return file_get_contents($cache);
        }
        $data = __::curl('https://translate.googleapis.com/translate_a/element.js', null, 'GET');
        $response = $data->result;
        $pos1 = mb_strpos($response, 'c._ctkk=\'') + mb_strlen('c._ctkk=\'');
        $pos2 = mb_strpos($response, '\'', $pos1);
        $tkk = mb_substr($response, $pos1, $pos2 - $pos1);
        file_put_contents($cache, $tkk);
        return $tkk;
    }

    private function generateTk($f0, $w1)
    {
        // ported from js to php from https://translate.googleapis.com/element/TE_20200210_00/e/js/element/element_main.js
        $w1 = explode('.', $w1);
        $n2 = $w1[0];
        for ($j3 = [], $t4 = 0, $h5 = 0; $h5 < strlen(mb_convert_encoding($f0, 'UTF-16LE', 'UTF-8')) / 2; $h5++) {
            $z6 =
                ord(mb_convert_encoding($f0, 'UTF-16LE', 'UTF-8')[$h5 * 2]) +
                (ord(mb_convert_encoding($f0, 'UTF-16LE', 'UTF-8')[$h5 * 2 + 1]) << 8);
            if (128 > $z6) {
                $j3[$t4++] = $z6;
            } else {
                if (2048 > $z6) {
                    $j3[$t4++] = ($z6 >> 6) | 192;
                } else {
                    if (
                        55296 == ($z6 & 64512) &&
                        $h5 + 1 < strlen(mb_convert_encoding($f0, 'UTF-16LE', 'UTF-8')) / 2 &&
                        56320 ==
                            ((ord(mb_convert_encoding($f0, 'UTF-16LE', 'UTF-8')[($h5 + 1) * 2]) +
                                (ord(mb_convert_encoding($f0, 'UTF-16LE', 'UTF-8')[($h5 + 1) * 2 + 1]) << 8)) &
                                64512)
                    ) {
                        $h5++;
                        $z6 =
                            65536 +
                            (($z6 & 1023) << 10) +
                            ((ord(mb_convert_encoding($f0, 'UTF-16LE', 'UTF-8')[$h5 * 2]) +
                                (ord(mb_convert_encoding($f0, 'UTF-16LE', 'UTF-8')[$h5 * 2 + 1]) << 8)) &
                                1023);
                        $j3[$t4++] = ($z6 >> 18) | 240;
                        $j3[$t4++] = (($z6 >> 12) & 63) | 128;
                    } else {
                        $j3[$t4++] = ($z6 >> 12) | 224;
                    }
                    $j3[$t4++] = (($z6 >> 6) & 63) | 128;
                }
                $j3[$t4++] = ($z6 & 63) | 128;
            }
        }
        $f0 = $n2;
        for ($t4 = 0; $t4 < count($j3); $t4++) {
            $f0 += $j3[$t4];
            $c7 = $f0;
            $x8 = '+-a^+6';
            for ($r9 = 0; $r9 < strlen($x8) - 2; $r9 += 3) {
                $u10 = $x8[$r9 + 2];
                $u10 = 'a' <= $u10 ? ord($u10[0]) - 87 : intval($u10);
                $a11 = $c7;
                $c12 = $u10;
                if ($c12 >= 32 || $c12 < -32) {
                    $c13 = (int) ($c12 / 32);
                    $c12 = $c12 - $c13 * 32;
                }
                if ($c12 < 0) {
                    $c12 = 32 + $c12;
                }
                if ($c12 == 0) {
                    return (($a11 >> 1) & 0x7fffffff) * 2 + (($a11 >> $c12) & 1);
                }
                if ($a11 < 0) {
                    $a11 = $a11 >> 1;
                    $a11 &= 2147483647;
                    $a11 |= 0x40000000;
                    $a11 = $a11 >> $c12 - 1;
                } else {
                    $a11 = $a11 >> $c12;
                }
                $b14 = $a11;
                $u10 = '+' == $x8[$r9 + 1] ? $b14 : $c7 << $u10;
                $c7 = '+' == $x8[$r9] ? ($c7 + $u10) & 4294967295 : $c7 ^ $u10;
            }
            $f0 = $c7;
        }
        $c7 = $f0;
        $x8 = '+-3^+b+-f';
        for ($r9 = 0; $r9 < strlen($x8) - 2; $r9 += 3) {
            $u10 = $x8[$r9 + 2];
            $u10 = 'a' <= $u10 ? ord($u10[0]) - 87 : intval($u10);
            $a11 = $c7;
            $c12 = $u10;
            if ($c12 >= 32 || $c12 < -32) {
                $c13 = (int) ($c12 / 32);
                $c12 = $c12 - $c13 * 32;
            }
            if ($c12 < 0) {
                $c12 = 32 + $c12;
            }
            if ($c12 == 0) {
                return (($a11 >> 1) & 0x7fffffff) * 2 + (($a11 >> $c12) & 1);
            }
            if ($a11 < 0) {
                $a11 = $a11 >> 1;
                $a11 &= 2147483647;
                $a11 |= 0x40000000;
                $a11 = $a11 >> $c12 - 1;
            } else {
                $a11 = $a11 >> $c12;
            }
            $b14 = $a11;
            $u10 = '+' == $x8[$r9 + 1] ? $b14 : $c7 << $u10;
            $c7 = '+' == $x8[$r9] ? ($c7 + $u10) & 4294967295 : $c7 ^ $u10;
        }
        $f0 = $c7;
        $f0 ^= $w1[1] ? $w1[1] + 0 : 0;
        if (0 > $f0) {
            $f0 = ($f0 & 2147483647) + 2147483648;
        }
        $f0 = fmod($f0, pow(10, 6));
        return $f0 . '.' . ($f0 ^ $n2);
    }
}

$gt = new GoogleTranslate();
$faker = Factory::create('de_DE');
$chars = 0;
for ($i = 0; $i < 1000; $i++) {
    $orig = $faker->realText(250);
    $chars += mb_strlen($orig);
    $response = $gt->translate($orig);
    logStatus([$response['status'], $chars, $orig, $response['result']]);
    echo $response['status'] . ': ' . $chars . PHP_EOL;
}

function logStatus($msg)
{
    file_put_contents('log.txt', date('Y-m-d H:i:s') . "\t" . implode("\t", $msg) . PHP_EOL, FILE_APPEND);
}

How to use that @vielhuber?

@QGB: Checkout this article: https://vielhuber.de/en/blog/google-translation-api-hacking/

Is this still working for you? It was working for me for some time, but now Google answers randomly with "[]" and a 200 status code.

Yes, just tested.
I just had to add a small line since google returns sometimes arrays instead of strings:
https://gist.github.com/vielhuber/b7739bf50b2edcf636c43a8f8910def9/revisions#diff-13c8070b20b0c3271f899b6381691ae2604aecb086fb2a01fd7f99f08ff70fbe

It's working

its not working. are you have any new solution?

its not working,google translate changed