Python实现批量翻译的示例代码

#!/usr/bin/python
# -*- coding: UTF-8 -*-

from copy import deepcopy
from distutils.log import Log
from email import utils
import json
import http.client  #修改引用的模块
import hashlib
from msilib import Table
from multiprocessing.dummy import Array
from operator import index, truediv
from tokenize import group
from turtle import st    #修改引用的模块
from urllib import parse
import random
from Log import Debug

# 百度注册开发者 并创建通用翻译 使用高级翻译app应用接口 获取 appid和secretKey
# 百度开发使用的api接口 翻译的句子会比 游客身份翻译的结果 更准确
appid = '20220829001324165' #你的appid 这里可以先用我的试用一下
secretKey = 'owSrQDeWHGPvI0U1BUm8' #你的密钥
singleTranslteMaxCount = 3 #单个单词翻译失败次数的上限

class WordInformation:
    
    _reqCount = None
    _from = None
    _to = None
    _text = None
    _translateText = None
    _nextWorld = None
    def __init__(self, text:str,fromLanguage:str,toLanguage:str,nextWorld) -> None:
        self._reqCount = 0
        self._text = text
        self._from = fromLanguage
        self._to = toLanguage
        self._nextWorld = nextWorld

    def CanReq(self):
        if self._reqCount > singleTranslteMaxCount:
            return False
        self._reqCount += 1
        return True

    def GetText(self):
        return self._text

    def GetTranslateText(self):
        if None != self._translateText:
            return self._translateText
        return self._text

    def GetNext(self):
        return self._nextWorld

def Translater( worldInfo:WordInformation):
    if worldInfo == None:
        return
    Debug.Log(f"{worldInfo.GetText()} 正在翻译...")
    myurl = '/api/trans/vip/translate'
    q = worldInfo.GetText()
    fromLang = worldInfo._from
    toLang = worldInfo._to
    salt = random.randint(32768, 65536)

    sign = appid+q+str(salt)+secretKey
    m1 = hashlib.md5()
    m1.update(sign.encode("utf-8"))
    sign = m1.hexdigest()
    myurl = myurl+'?appid='+appid+'&q='+parse.quote(q)+'&from='+fromLang+'&to='+toLang+'&salt='+str(salt)+'&sign='+sign
    httpClient = http.client.HTTPConnection('api.fanyi.baidu.com')
    httpClient.request('GET', myurl)
    response = httpClient.getresponse()
    #转码
    html = response.read().decode('utf-8')
    html = json.loads(html)

    if httpClient:
        httpClient.close()
    
    if "trans_result" in html:
        dst = html["trans_result"][0]["dst"]
        worldInfo._translateText = dst
        # Translater(worldInfo.GetNext())
    # else:
    #     if worldInfo.CanReq():
    #         Translater(worldInfo)
    #     else:
    #         Translater(worldInfo.GetNext())

def GetWorldInfoArrByTextArr( texts:Array,fromLanguage:str,toLanguage:str ):
    num = len(texts)
    worlds = []
    for i in range(num-1,0,-1):
        if i == num - 1:
            world = WordInformation(texts[i],fromLanguage,toLanguage,None)
            worlds.append(world)
        else:
            world = WordInformation(texts[i],fromLanguage,toLanguage,worlds[len(worlds)-1])
            worlds.append(world)
    return worlds

def Translation( needTranslateTexts:Array,fromLanguage:str,toLanguage:str ):
    worlds = GetWorldInfoArrByTextArr(needTranslateTexts,fromLanguage,toLanguage)
    
    Debug.Runtime("翻译用时: ")
    # 递推方式  next指针不为none 递归执行next
    # Translater(worlds[len(worlds)-1])
    # 迭代方式 
    for i in range(0,len(worlds)):
        Translater(worlds[i])
        if worlds[i].GetTranslateText() == None and worlds[i].CanReq():
            i -= 1
    Debug.Runtime("翻译用时: ")

    worlds.reverse()
    translateTexts = [ ]
    for world in worlds:
        translateTexts.append(world.GetTranslateText())
    return translateTexts,worlds

import sys
import time
import traceback
import Utils

DEBUG = True #if sys.gettrace() else False

class Debug:
    __log = ''
    __time = dict()
    @staticmethod
    def Log(textContent:str):
        '''
            输出日志 DEBUG模式下 同时输出编辑器显示
        '''
        times = time.time()
        local_time = time.localtime(times)
        tstr = time.strftime("%Y-%m-%d %H:%M:%S",local_time)
        str1 = f"{tstr}\t{textContent}\n"
        if DEBUG:
            print(str1)
        Debug.__log += str1

    @staticmethod
    def LogExcept():
        '''
            输出堆栈信息 一般用于捕获异常报错后调用
        '''
        Debug.Log(traceback.format_exc())

    @staticmethod
    def Runtime(str1):
        '''
            输出两次打印间程序的运行时间
            成双成对的方式出现

            第一次调用并不会打印任何信息
            仅在第二次调用后 返回与第一调用间的间隔
        '''
        if(str1 in Debug.__time.keys()):
            runtime = time.time() - Debug.__time[str1]
            del Debug.__time[str1]
            Debug.Log("%s%f秒"%(str1,runtime))
        else:
            Debug.__time[str1] = time.time()

    @staticmethod
    def Output():
        Utils.writeInFile('./log.txt', Debug.__log)

'''
    工具类

'''

import base64
import json  # json相关
import os  # 文件流相关
import zipfile  # zip亚索文件
import shutil  # 删除整个文件夹


def fromFile(url):
    try:
        with open(url, 'r', encoding='utf-8') as fp:
            return fp.read()
    finally:
        fp.close()
        
def fromFile2Base64(url):
    try:
        with open(url, 'rb') as f1:
            return str(base64.b64encode(f1.read()), encoding='utf-8')
    finally:
        f1.close()

def writeInFile(toFile, content):
    try:
        with open(toFile, 'w', encoding='utf-8') as fp:
            fp.write(content)
    finally:
        fp.close()


def fromJsonAsDict(url):
    return json.loads((fromFile(url)))


def writeDictInFile(url, dict1):
    writeInFile(url, json.dumps(dict1, ensure_ascii=False, indent=2))

def revealInFileExplorer(targetDir):
    try:
        os.startfile(targetDir)
    except:
        os.system("explorer.exe %s" % targetDir)


def zipFile(src, dest):
    '''
        src: 目标文件位置   D:/123.txt
        dest: 压缩后输出的zip路径 D:/123.zip
    '''
    with zipfile.ZipFile(dest, 'w',zipfile.ZIP_DEFLATED) as p:
        
        p.write(src,os.path.split(src)[1])

        p.close()     


def zipFiles(src,dest):
    '''
        src: 目标文件夹位置   D:/hellowd
        dest: 压缩后输出的zip路径 D:/hellowd.zip
    '''
    with zipfile.ZipFile(dest, 'w',zipfile.ZIP_DEFLATED) as pZip:
        for folder, _, files in os.walk(src):
            relative_url = folder.replace(src, '')
            for file in files:
                pZip.write(os.path.join(folder,file),os.path.join(relative_url,file))
        pZip.close()

def removeFile(url):
    if os.path.isdir(url):
        shutil.rmtree(url)
    else:
        os.remove(url)

# 导入Translation
from Translator import Translation

zhTexts = ["为了解决商家的让利活动我压力很大。","为了解决商家的让利活动我压力很大。","消耗{0}体力","获取{0}钞票" ]

enTexts,enWorlds = Translation(zhTexts,'zh','en')
print(enTexts)