【python】使用腾讯翻译API对文件进行翻译

最新推荐文章于 2025-03-25 16:51:11 发布

Z_W_H_

最新推荐文章于 2025-03-25 16:51:11 发布

阅读量1.2k

点赞数 5

分类专栏： python 文章标签： python 腾讯翻译

本文链接：https://blog.csdn.net/qq_39397927/article/details/142860574

版权

python 专栏收录该内容

92 篇文章

订阅专栏

综合考虑腾讯翻译是目前翻译软件中免费字符数最多的一家厂商，一个月有500w免费字符

详细计费请查看以下链接

机器翻译计费概述-购买指南-文档中心-腾讯云 (tencent.com)

申请

参考文档【萌译】如何注册腾讯云API_腾讯翻译api申请-CSDN博客

使用

python库下载及安装

tencentcloud-sdk-python · PyPI

https://download.csdn.net/download/qq_39397927/89876455

安装

https://blog.csdn.net/HUANG370/article/details/119182313

pip install tencentcloud_sdk_python-3.0.1247-py2.py3-none-any.whl

代码

读取文件可以换成pandas库

import csv
import io
import pandas as pd
from tencentcloud.common import credential
from tencentcloud.common.profile.client_profile import ClientProfile
from tencentcloud.common.profile.http_profile import HttpProfile
from tencentcloud.common.exception.tencent_cloud_sdk_exception import TencentCloudSDKException
from tencentcloud.tmt.v20180321 import tmt_client, models
SecretId = "**"
SecretKey = "**"
class Translator:
    def __init__(self, from_lang, to_lang):
        self.from_lang = from_lang
        self.to_lang = to_lang

    def translate(self, text):
        try:
            cred = credential.Credential(SecretId, SecretKey)
            httpProfile = HttpProfile()
            httpProfile.endpoint = "tmt.tencentcloudapi.com"

            clientProfile = ClientProfile()
            clientProfile.httpProfile = httpProfile
            client = tmt_client.TmtClient(cred, "ap-beijing", clientProfile)

            req = models.TextTranslateRequest()
            req.SourceText = text
            req.Source = self.from_lang
            req.Target = self.to_lang
            req.ProjectId = 0

            resp = client.TextTranslate(req)
            return resp.TargetText

        except TencentCloudSDKException as err:
            return err
#需要翻译的文件路径
translateFileSourcePath=r"**.csv"
#翻译后的文档路径
translateFileTargetPath=r"C:\Users\admin\Desktop\翻译.csv"
def get_csv(table):

    with io.open(table,'r', encoding='UTF-8', errors='ignore') as f:
        reader=csv.reader(f)
        return [row for row in reader]
if __name__ =="__main__":
    translator = Translator(from_lang="en", to_lang="zh")
    #存放翻译文档
    translatefile = {"content":[],"translate":[]}
    #读取CSV文件
    Table_fullmatch=get_csv(translateFileSourcePath)
    for item in Table_fullmatch:
        translatefile["content"].append(item[0])
        #进行翻译
        translateString = translator.translate(item[0])
        translatefile["translate"].append(translateString)
        print("翻译："+translateString)
    df = pd.DataFrame(translatefile)
    df = df.drop_duplicates(subset=["content"])
    df.to_csv(translateFileTargetPath)
print("全部结束")