python实现APP多语种翻译

用户6367961

发布于 2019-10-24 16:15:30

2K0

发布于 2019-10-24 16:15:30

文章被收录于专栏：自学测试之道自学测试之道自学测试之道

前言

最近接触运动手环项目，因业务需求，需对APP进行多国语言进行翻译，因人工比对容易出错，加上需要大量的时间去反复验证。因此就想能不能通过脚本的方式去实现。

在此记录下过程：

在网上搜了一些如何用python实现google脚本，大致有三种：

1.调用google API的

2.使用别人已经封装好的库

3.类似爬虫方式获取（我没爬过，也不知道算不算）

这里采用第三种，主要是看了利用python调用谷歌翻译API这篇文章，感觉蛮简单，也感觉比较靠谱，然后就开搞了。

按照<利用python调用谷歌翻译API>这篇文章实现脚本以后，发现只能翻译成中文，而且不适合翻译多个句子。最后将这个脚本稍微改了下，支持翻译多条语句，将结果从一个Excel文档保存到另一个Excel文档中去。

一、环境准备

1、这里我使用python3.7 + pycharm

2、需要安装的库：

pip install xlwd

pip install xlrd

pip install requests

pip install PyExecJs

3、需翻译的数据

test_Language:

4、需要存储的文件：test_result_Language，，内容为空就好

二、实现代码

脚本目录：

主要代码

main.py

#!/usr/bin/python

import xlrd
import xlwt
import os
import threading
import time

from translate_google import get_translate

# 英文的列，此处翻译都是基于中文
#TRANSLATE_BASE_FIELD = "English"
TRANSLATE_BASE_FIELD = "zh-CN"

# 是否使用多线程翻译，多线程容易导致超时，适合翻译少量数据
IS_MULTITHREADING = False

# 是否显示日志
IS_DEBUG = True

# 翻译后数据存放的Excel文件
translate_file = "data/translate_result_Language.xls"

# 待翻译的文件
translate_source_file = 'data/test_Language.xls'

# 需要翻译的Excel文件
book = xlrd.open_workbook(translate_source_file)
# 默认获取第一张表
sheet = book.sheet_by_index(0)

file = xlwt.Workbook(encoding='utf-8')


def print_log(text):
    """
    打印日志
    """
    if IS_DEBUG:
        print(str(text))


def get_english_column():
    """
    获取英文字段的列
    """
    tmp_english_col = 0
    for col in range(1, sheet.ncols):
        field_name = sheet.cell_value(0, col)
        if field_name == TRANSLATE_BASE_FIELD:
            print_log(field_name)
            tmp_english_col = col
            break

    return tmp_english_col


# 需要翻译的语言
translate_dict = {
    # '中文': 'zh-CN',
    '英文':'english',
    # # 挪威语
    # 'Norwegian': 'nb',
    '中文繁体': 'zh-TW',
    # # 德语
    # 'German': 'de',
    # '韩语': 'ko',
    'Japanese': 'ja',
    # '法语': 'fr',
    # '西班牙语': 'es',
    # # 波兰语
    # 'Polski': 'pl',
    # # 意大利语
    # 'Italian': 'it',
    # # 希伯来语
    # 'Hebrew (עברית(': 'iw',
    # # 荷兰语
    # 'Dutch': 'nl',
    # # 印度尼西亚（印尼）
    # 'Indonesian': 'id',
    '捷克语': 'cs',
    # '芬兰语': 'fi',
    #  # 葡萄牙语(巴西),葡萄牙语(葡萄牙)
    # '葡萄牙语': 'pt',
    # '罗马尼亚语': 'ro',
    # '俄语': 'ru',
    # '瑞典语': 'sv',
    # '土耳其语': 'tr',
}
dict_len = len(translate_dict)


class ExcelUtil:
    save_count = 0

    def __init__(self, title, tl, english_col):
        self.tl = tl
        self.title = title
        self.english_col = english_col
        self.translate_sheet = file.add_sheet(tl)
        language_list = []
        language_list.append("Language")
        for row in range(1, sheet.nrows):
            english_field_name = sheet.cell_value(row,  self.english_col)
            if english_field_name is None or english_field_name == "":
                print_log("empty filed!")
                break
            language_list.append(english_field_name)

        self.write_to_sheet(language_list, 0)

    def write_to_sheet(self, field_list, column=0):
        """
        将内容写到Excel的工作表
        :param field_list:
        :param column:
        :return:
        """
        print_log("write_to_sheet")
        row = 0
        for item in field_list:
            print(item)
            self.translate_sheet.write(row, column, item)
            row += 1

    def write_to_excel(self):
        language_list = self.get_translate_list()
        print_log("===========================")
        self.write_to_sheet(language_list, 1)

        if IS_MULTITHREADING:
            ExcelUtil.save_count += 1
            dict_len = len(translate_dict)
            print_log("ExcelUtil.save_count=%d" % ExcelUtil.save_count)
            if dict_len == ExcelUtil.save_count:
                print_log("ExcelUtil.save_count==dict_len")
                file.save(translate_file)

            print_log("===========================")

    def get_translate_list(self):
        print_log("title: %s, col: %s, tl: %s\n" % (self.title, self.english_col, self.tl))
        language_list = []
        language_list.append(self.title)
        translate_text = ""
        total_row = sheet.nrows
        print_log("sheet total row=%d" % total_row)
        row_count = 0

        for row in range(1, sheet.nrows):
            english_field_name = sheet.cell_value(row, self.english_col)
            if '\n' in english_field_name:
                print_log("row==%d, exist \\n" % row)
                # 替换内容中带换行符的，否则google翻译会返回两个结果
                english_field_name = str(english_field_name).replace("\n", "")
            print_log("row=%d field name = %s" % (row, english_field_name))

            next_english_field_name = ""
            if row + 1 < sheet.nrows:
                # 获取下一行内容
                next_english_field_name = sheet.cell_value(row + 1, self.english_col)

            translate_text += (english_field_name + "\n")
            translate_length = len(translate_text)
            row_count += 1
            # 要翻译的内容不能带有英文的句号或者问号，字段中存在多句的需要单独翻译
            if row == total_row - 1 or '.' in next_english_field_name or '?' in next_english_field_name or '.' in english_field_name or '?' in english_field_name or translate_length >= 512:
                print_log("translate_text==" + translate_text)
                self.translate_text(language_list, translate_text, row_count)

                # 重置数据，准备下次翻译
                row_count = 0
                translate_text = ""

        return language_list

    def translate_text(self, language_list, translate_text, row_count):
        translate_result = ""
        this_translate_list = []
        for i in range(0, 5):
            translate_result = get_translate(translate_text, self.tl)
            if len(translate_result):
                try_again = False
                if '.' in translate_text or '?' in translate_text:
                    duplicate_count = 0
                    result_text = ""
                    for results in translate_result:
                        if results is None or results[0] is None:
                            break
                        result_text += results[0]
                        if results[0] in translate_text:
                            duplicate_count += 1

                    # 判断是否是真的进行翻译了
                    if duplicate_count >= 2:
                        try_again = True
                        print_log("include '.' and '？',no translate, result_text==" + result_text + ",duplicate_count==" + str(duplicate_count))

                else:
                    duplicate_count = 0
                    for results in translate_result:
                        if results[0] is None:
                            continue
                        if results[0] in translate_text:
                            duplicate_count += 1

                    print_log("duplicate_count==%d, row_count=%d" % (duplicate_count, row_count))
                    if duplicate_count == row_count:
                        try_again = True
                        print_log("no translate duplicate_count==row_count")

                if not try_again:
                    break

            time.sleep(1)

        if len(translate_result):
            if '.' in translate_text or '?' in translate_text:
                temp_result = ""
                for results in translate_result:
                    if results is None or results[0] is None:
                        break
                    temp_result += results[0]

                temp_result = replace_text(temp_result)
                language_list.append(temp_result)
                print_log(". exist")
                this_translate_list.append("")
            else:
                for results in translate_result:
                    if results[0] is None:
                        continue
                    result = replace_text(results[0])

                    language_list.append(result)
                    this_translate_list.append("")
                print_log(". not exist")
        else:
            # 如果是翻译失败，需要用空格替换对应的行，防止结果对不上
            print_log("result empty! row_count=%d" % row_count)
            for count in range(0, row_count):
                print_log("add empty! count=%d" % count)
                language_list.append(translate_text)
                this_translate_list.append("")

        this_len = len(this_translate_list)

        print_log("this_len==%d, row_count==%d" % (this_len, row_count))

        if this_len != row_count:
            raise Exception("translate count not match!")
        this_translate_list.clear()


def replace_text(text):
    """
    Android资源文件英文的双引号或单引号需要加斜杠，否则会报错，中文的双引号和单引号不需要
    :param text:
    :return:
    """
    temp_text = text.replace(r' \ "', r' \"').replace(r' / ', r'/').replace(r'% ', r' %') \
        .replace(r' $ ', r'$').replace(r'$ ', r'$').replace(r'¥  ', r'¥ ').replace(r'￥  ', r'￥ ').replace(r"'", r"\'").replace(r'"', r'\"').replace("\\\\", "\\")

    return temp_text


def del_file(_translate_file):
    """
    删除文件
    """
    is_exists = os.path.exists(_translate_file)
    if is_exists:
        os.remove(_translate_file)


def start_translate(title, tl, _english_col):
    ExcelUtil(title, tl, _english_col).write_to_excel()


if __name__ == '__main__':
    # 删除文件
    del_file(translate_file)
    english_col = get_english_column()
    print_log("dict size==" + str(len(translate_dict)))
    print_log("english column-->" + str(english_col))
    if IS_MULTITHREADING:
        for key, value in translate_dict.items():
            threading.Thread(target=start_translate, args=(key, value, english_col)).start()
    else:
        for key, value in translate_dict.items():
            start_translate(key, value, english_col)
        file.save(translate_file)

    # print(replace_text("This cellphone number doesn\\'t exsist, please input again"))

translate_google.py

import requests
import json
import execjs  # 必须，需要先用pip 安装，用来执行js脚本
from urllib.parse import quote
# 用来判断是否需要打印日志
debug = True

class Py4Js:

    def __init__(self):
        self.ctx = execjs.compile(""" 
            function TL(a) { 
                var k = ""; 
                var b = 406644; 
                var b1 = 3293161072;       
                var jd = "."; 
                var $b = "+-a^+6"; 
                var Zb = "+-3^+b+-f";    
                for (var e = [], f = 0, g = 0; g < a.length; g++) { 
                    var m = a.charCodeAt(g); 
                    128 > m ? e[f++] = m : (2048 > m ? e[f++] = m >> 6 | 192 : (55296 == (m & 64512) && g + 1 < a.length && 56320 == (a.charCodeAt(g + 1) & 64512) ? (m = 65536 + ((m & 1023) << 10) + (a.charCodeAt(++g) & 1023), 
                    e[f++] = m >> 18 | 240, 
                    e[f++] = m >> 12 & 63 | 128) : e[f++] = m >> 12 | 224, 
                    e[f++] = m >> 6 & 63 | 128), 
                    e[f++] = m & 63 | 128) 
                } 
                a = b; 
                for (f = 0; f < e.length; f++) a += e[f], 
                a = RL(a, $b); 
                a = RL(a, Zb); 
                a ^= b1 || 0; 
                0 > a && (a = (a & 2147483647) + 2147483648); 
                a %= 1E6; 
                return a.toString() + jd + (a ^ b) 
            };      
            function RL(a, b) { 
                var t = "a"; 
                var Yb = "+"; 
                for (var c = 0; c < b.length - 2; c += 3) { 
                    var d = b.charAt(c + 2), 
                    d = d >= t ? d.charCodeAt(0) - 87 : Number(d), 
                    d = b.charAt(c + 1) == Yb ? a >>> d: a << d; 
                    a = b.charAt(c) == Yb ? a + d & 4294967295 : a ^ d 
                } 
                return a 
            }
        """)

    def get_tk(self, text):
        return self.ctx.call("TL", text)


def build_url(text, tk, tl='zh-CN'):
    """
    需要用转URLEncoder
    :param text:
    :param tk:
    :param tl:
    :return:
    """
    return 'https://translate.google.cn/translate_a/single?client=webapp&sl=auto&tl=' + tl + '&hl=zh-CN&dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca&dt=rw&dt=rm&dt=ss&dt=t&source=btn&ssel=0&tsel=0&kc=0&tk=' \
           + str(tk) + '&q=' + quote(text, encoding='utf-8')


def translate(js, text, tl='zh-CN'):
    """
    tl为要翻译的语言
    de：德语
    ja：日语
    sv：瑞典语
    nl：荷兰语
    ar：阿拉伯语
    ko：韩语
    pt：葡萄牙语
    zh-CN：中文简体
    zh-TW：中文繁体
    """

    header = {
        'authority': 'translate.google.cn',
        'method': 'GET',
        'path': '',
        'scheme': 'https',
        'accept': '*/*',
        'accept-encoding': 'gzip, deflate, br',
        'accept-language': 'zh-CN,zh;q=0.9,ja;q=0.8',
        # 'cookie': '_ga=GA1.3.110668007.1547438795; _gid=GA1.3.791931751.1548053917; 1P_JAR=2019-1-23-1; NID=156=biJbQQ3j2gPAJVBfdgBjWHjpC5m9vPqwJ6n6gxTvY8n1eyM8LY5tkYDRsYvacEnWNtMh3ux0-lUJr439QFquSoqEIByw7al6n_yrHqhFNnb5fKyIWMewmqoOJ2fyNaZWrCwl7MA8P_qqPDM5uRIm9SAc5ybSGZijsjalN8YDkxQ',
         'cookie':'_ga=GA1.3.110668007.1547438795; _gid=GA1.3.1522575542.1548327032; 1P_JAR=2019-1-24-10; NID=156=ELGmtJHel1YG9Q3RxRI4HTgAc3l1n7Y6PAxGwvecTJDJ2ScgW2p-CXdvh88XFb9dTbYEBkoayWb-2vjJbB-Rhf6auRj-M-2QRUKdZG04lt7ybh8GgffGtepoA4oPN9OO9TeAoWDY0HJHDWCUwCpYzlaQK-gKCh5aVC4HVMeoppI',
        # 'cookie': '',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64)  AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36',
        'x-client-data': 'CKi1yQEIhrbJAQijtskBCMG2yQEIqZ3KAQioo8oBCL+nygEI7KfKAQjiqMoBGPmlygE='
    }
    url = build_url(text, js.get_tk(text), tl)
    res = []
    try:
        r = requests.get(url, headers=header)
        result = json.loads(r.text)
        r.encoding = "UTF-8"
        if debug:
            print(r.url)
            print(r.headers)
            print(r.request.headers)
            print(result)

        res = result[0]
        if res is None:
            if result[7] is not None:
                # 如果我们文本输错，提示你是不是要找xxx的话，那么重新把xxx正确的翻译之后返回
                try:
                    correct_text = result[7][0].replace('<b><i>', ' ').replace('</i></b>', '')
                    if debug:
                        print(correct_text)
                    correct_url = build_url(correct_text, js.get_tk(correct_text), tl)
                    correct_response = requests.get(correct_url)
                    correct_result = json.loads(correct_response.text)
                    res = correct_result[0]
                except Exception as e:
                    if debug:
                        print(e)
                    res = []

    except Exception as e:
        res = []
        if debug:
            print(url)
            print("翻译" + text + "失败")
            print("错误信息:")
            print(e)
    finally:
        return res


def get_translate(word, tl):
    js = Py4Js()
    translate_result = translate(js, word, tl)

    if debug:
        print("word== %s, tl== %s" % (word, tl))
        print(translate_result)
    return translate_result


if __name__ == '__main__':
    debug = True
    translate_text = '3.Hear voice prompt \"start configuration mode\". click \"reset successfully\" button\n'
    results = get_translate(translate_text, 'cs')
    translate_result = ""

    if "." in translate_text or "?" in translate_text:
        for result in results:
            translate_result += result[0]
    else:
        result_translate = results[0]

    if debug:
        print("translate_result:" + translate_result)

三、运行结果

中文转捷克语