translate.py

# -*- coding: utf-8 -*-
"""
Translator module that uses the Google Translate API.

Adapted from Terry Yin's google-translate-python.
Language detection added by Steven Loria.
"""
from __future__ import absolute_import

import sys

PY2 = int(sys.version[0]) == 2

import codecs
import ctypes
import json
import re

if PY2:
    import urllib2 as request
    from urllib import urlencode
else:  # PY3
    from urllib import request
    from urllib.parse import urlencode


class Translator(object):
    """A language translator and detector.

    Usage:
    ::
        >>> from translate import Translator
        >>> t = Translator()
        >>> t.translate('hello', from_lang='en', to_lang='fr')
        u'bonjour'
        >>> t.detect("hola")
        u'es'
    """

    url = "https://translate.google.se/translate_a/t?client=webapp&dt=bd&dt=ex&dt=ld&dt=md&dt=qca&dt=rw&dt=rm&dt=ss&dt=t&dt=at&ie=UTF-8&oe=UTF-8&otf=2&ssel=0&tsel=0&kc=1"

    headers = {
        'Accept': '*/*',
        'Connection': 'keep-alive',
        'User-Agent': (
            'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36')
    }

    def translate(self, source, from_lang='auto', to_lang='en', host=None, type_=None):
        """Translate the source text from one language to another."""
        if PY2:
            source = source.encode('utf-8')
        data = {"q": source}
        url = self.url + "&sl=" + from_lang + "&tl=" + to_lang + "&hl=" + to_lang + "&tk=" + _calculate_tk(source)
        response = self._request(url, host=host, type_=type_, data=data)
        result = json.loads(response)
        if isinstance(result, list):
            try:
                result = result[0]  # ignore detected language
            except IndexError:
                pass
        self._validate_translation(source, result)
        return result

    def detect(self, source, host=None, type_=None):
        """Detect the source text's language."""
        if PY2:
            source = source.encode('utf-8')
        if len(source) < 3:
            raise Exception('Must provide a string with at least 3 characters.')
        data = {"q": source}
        url = self.url + "&sl=auto&tk=" + _calculate_tk(source)
        response = self._request(url, host=host, type_=type_, data=data)
        result, language = json.loads(response)
        return language

    def _validate_translation(self, source, result):
        """Validate API returned expected schema, and that the translated text
        is different than the original string.
        """
        if not result:
            raise Exception('Translation API returned and empty response.')
        if PY2:
            result = result.encode('utf-8')

    def _request(self, url, host=None, type_=None, data=None):
        encoded_data = urlencode(data).encode('utf-8')
        req = request.Request(url=url, headers=self.headers, data=encoded_data)
        if host or type_:
            req.set_proxy(host=host, type=type_)
        resp = request.urlopen(req)
        content = resp.read()
        return content.decode('utf-8')


def _unescape(text):
    """Unescape unicode character codes within a string.
    """
    pattern = r'\\{1,2}u[0-9a-fA-F]{4}'
    decode = lambda x: codecs.getdecoder('unicode_escape')(x.group())[0]
    return re.sub(pattern, decode, text)


def _calculate_tk(source):
    """Reverse engineered cross-site request protection."""
    # Source: https://github.com/soimort/translate-shell/issues/94#issuecomment-165433715
    # Source: http://www.liuxiatool.com/t.php

    tkk = [406398, 561666268 + 1526272306]
    b = tkk[0]

    if PY2:
        d = map(ord, source)
    else:
        d = source.encode('utf-8')

    def RL(a, b):
        for c in range(0, len(b) - 2, 3):
            d = b[c + 2]
            d = ord(d) - 87 if d >= 'a' else int(d)
            xa = ctypes.c_uint32(a).value
            d = xa >> d if b[c + 1] == '+' else xa << d
            a = a + d & 4294967295 if b[c] == '+' else a ^ d
        return ctypes.c_int32(a).value

    a = b

    for di in d:
        a = RL(a + di, "+-a^+6")

    a = RL(a, "+-3^+b+-f")
    a ^= tkk[1]
    a = a if a >= 0 else ((a & 2147483647) + 2147483648)
    a %= pow(10, 6)

    tk = '{0:d}.{1:d}'.format(a, a ^ b)
    return tk