Python——文献翻译

IsYuh

已于 2022-10-27 10:09:41 修改

阅读量573

点赞数 2

分类专栏： Python 文章标签： python 开发语言自然语言处理

于 2022-10-26 16:46:54 首次发布

本文链接：https://blog.csdn.net/a1150162163/article/details/127535329

版权

Python 专栏收录该内容

15 篇文章 0 订阅

订阅专栏

一、API获取

自行注册
https://www.xfyun.cn/service/niutrans

二、用到的库

python_docx
requests
提示什么安装什么就好了

三、使用说明

3.1 主要为了解决英文文献复制出来不是连续的，而是和PDF中一样一行一段的问题，会导致翻译出现一点偏差

在这里插入图片描述

3.2复制英文文献到txt中，每段之间用空行隔开即可

在这里插入图片描述

3.3 代码会自动整理，把每段合一起（会生成一个中间文件，路径见代码，请自行更改）

3.4 会在结果路径生成结果word文档

会将英文和翻译的结果输出
在这里插入图片描述

4 代码

默认英译中，有其他语言需求请自行更改
API有五千字的限制，故采用分段翻译，如果一段超过五千字，请自行再分。

import docx
from docx.shared import Pt
from docx.oxml.ns import qn
import os
import requests
import datetime
import hashlib
import base64
import hmac
import json


class get_result(object):
    def __init__(self,host):
        # 应用ID（到控制台获取）
        self.APPID = ""
        # 接口APISercet（到控制台机器翻译服务页面获取）
        self.Secret = ""
        # 接口APIKey（到控制台机器翻译服务页面获取）
        self.APIKey= ""
        
        
        # 以下为POST请求
        self.Host = host
        self.RequestUri = "/v2/ots"
        # 设置url
        # print(host)
        self.url="https://"+host+self.RequestUri
        self.HttpMethod = "POST"
        self.Algorithm = "hmac-sha256"
        self.HttpProto = "HTTP/1.1"

        # 设置当前时间
        curTime_utc = datetime.datetime.utcnow()
        self.Date = self.httpdate(curTime_utc)
        # 设置业务参数
        # 语种列表参数值请参照接口文档：https://www.xfyun.cn/doc/nlp/niutrans/API.html
        
        if line !="\n":
            self.Text=line
            self.BusinessArgs={
                    "from": "en",
                    "to": "cn",
                }
       #语言在这里改         

    def hashlib_256(self, res):
        m = hashlib.sha256(bytes(res.encode(encoding='utf-8'))).digest()
        result = "SHA-256=" + base64.b64encode(m).decode(encoding='utf-8')
        return result

    def httpdate(self, dt):
        """
        Return a string representation of a date according to RFC 1123
        (HTTP/1.1).

        The supplied date must be in UTC.

        """
        weekday = ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"][dt.weekday()]
        month = ["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep",
                 "Oct", "Nov", "Dec"][dt.month - 1]
        return "%s, %02d %s %04d %02d:%02d:%02d GMT" % (weekday, dt.day, month,
                                                        dt.year, dt.hour, dt.minute, dt.second)

    def generateSignature(self, digest):
        signatureStr = "host: " + self.Host + "\n"
        signatureStr += "date: " + self.Date + "\n"
        signatureStr += self.HttpMethod + " " + self.RequestUri \
                        + " " + self.HttpProto + "\n"
        signatureStr += "digest: " + digest
        signature = hmac.new(bytes(self.Secret.encode(encoding='utf-8')),
                             bytes(signatureStr.encode(encoding='utf-8')),
                             digestmod=hashlib.sha256).digest()
        result = base64.b64encode(signature)
        return result.decode(encoding='utf-8')

    def init_header(self, data):
        digest = self.hashlib_256(data)
        #print(digest)
        sign = self.generateSignature(digest)
        authHeader = 'api_key="%s", algorithm="%s", ' \
                     'headers="host date request-line digest", ' \
                     'signature="%s"' \
                     % (self.APIKey, self.Algorithm, sign)
        #print(authHeader)
        headers = {
            "Content-Type": "application/json",
            "Accept": "application/json",
            "Method": "POST",
            "Host": self.Host,
            "Date": self.Date,
            "Digest": digest,
            "Authorization": authHeader
        }
        return headers

    def get_body(self):
        content = str(base64.b64encode(self.Text.encode('utf-8')), 'utf-8')
        postdata = {
            "common": {"app_id": self.APPID},
            "business": self.BusinessArgs,
            "data": {
                "text": content,
            }
        }
        body = json.dumps(postdata)
        #print(body)
        return body

    def call_url(self):
        if self.APPID == '' or self.APIKey == '' or self.Secret == '':
            print('Appid 或APIKey 或APISecret 为空！请打开demo代码，填写相关信息。')
        else:
            code = 0
            body=self.get_body()
            headers=self.init_header(body)
            #print(self.url)
            response = requests.post(self.url, data=body, headers=headers,timeout=8)
            status_code = response.status_code
            #print(response.content)
            if status_code!=200:
                # 鉴权失败
                print("Http请求失败，状态码：" + str(status_code) + "，错误信息：" + response.text)
                print("请根据错误信息检查代码，接口文档：https://www.xfyun.cn/doc/nlp/niutrans/API.html")
            else:
                # 鉴权成功
                respData = json.loads(response.text)
                doc.add_paragraph(respData['data']['result']['trans_result']['src']).paragraph_format.first_line_indent = Pt(14) * 2
                doc.add_paragraph(respData['data']['result']['trans_result']['dst']).paragraph_format.first_line_indent = Pt(14) * 2    ##返回值是dict字典    
                #print(respData)
                # 以下仅用于调试
                code = str(respData["code"])
                if code!='0':
                    print("请前往https://www.xfyun.cn/document/error-code?code=" + code + "查询解决办法")


def txtchange():
    file=open(path_A,encoding='UTF-8')
    file_write=open(path_B,mode='w',encoding='UTF-8')
    linesa = file.readlines()
    print(linesa)
    pi_string=''
    for line in linesa:
        line = line.strip()
        if len(line):
            pi_string = pi_string+' '+line         
        else:
            file_write.write(pi_string+'\n')
            pi_string = ''
    file_write.write(pi_string+'\n')        


def file_exist(dirpath):
    if not os.path.exists(dirpath):  # os模块判断并创建
        os.mkdir(dirpath)



if __name__ == '__main__':
    path_A=r"D:\\Desktop\\参考文献1.txt"  #复制英文的保存的文件路径  
    path_B=r"D:\\Desktop\\参考文献2.txt"  #中间过程文件
    path_C=r"D:\\Desktop\\result.docx"   #结果文件

    txtchange()

    doc=docx.Document()
    doc.styles['Normal'].font.size = Pt(14)
    doc.styles['Normal'].font.name = u'Times New Roman'
    doc.styles['Normal'].element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')

    ##示例:  host="ntrans.xfyun.cn"域名形式
    host = "ntrans.xfyun.cn"
    #初始化类
    file=open(path_B,encoding='UTF-8')
    file_write=open(path_C,mode='w',encoding='UTF-8')
    linesb = file.readlines()
    for line in linesb:
        if line =='\n':
            next 
        else:
            gClass=get_result(host)
            gClass.call_url()
    doc.save(path_C)
    print("翻译完成！")