tags: python

讀取pdf 翻譯成中文 再存成word

安裝相關套件

pip install python-dotenv
pip install pdfplumber
pip install python-docx
pip install google-cloud-translate

申請憑證

1. https://console.cloud.google.com/
   

   
   

2. 尋找要啟用的API服務
   

   
   
   

3. 啟用該服務
   點「啟用」
   

4. 申請憑證
   

   
   
   
   
   
   
   
   
   
   

5. 取得憑證
   

   
   
   
   
   

6. 將下載好的json檔搬移到專案目錄中

7. 將.env檔的內容指到這個檔案
   

8. 即可透過以下程式使用翻譯功能

from dotenv import load_dotenv
import pdfplumber
import docx

def get_pdf_content(filepath, page_number):
    pdf = pdfplumber.open(filepath)
    p = pdf.pages[page_number]
    text = p.extract_text()       #讀文字
    # print(text)
    return text

def translate_text_with_model(target, text, model="nmt"):
    """Translates text into the target language.
    Make sure your project is allowlisted.
    Target must be an ISO 639-1 language code.
    See https://g.co/cloud/translate/v2/translate-reference#supported_languages
    """
    from google.cloud import translate_v2 as translate

    translate_client = translate.Client()

    if isinstance(text, bytes):
        text = text.decode("utf-8")

    # Text can also be a sequence of strings, in which case this method
    # will return a sequence of results for each text.
    result = translate_client.translate(text, target_language=target, model=model)

    # print(u"Text: {}".format(result["input"]))
    # print(u"Translation: {}".format(result["translatedText"]))
    # print(u"Detected source language: {}".format(result["detectedSourceLanguage"]))
    return result["translatedText"]

def write_docx(filepath, text):
    mydoc = docx.Document()
    first_para = mydoc.add_paragraph("第一章 aaaa\n")
    first_para.add_run(text)
    mydoc.save(filepath)
 


if __name__ == '__main__':
    load_dotenv()

    source_filepath=r"/home/amos/文件/kivy.pdf"  # 外文pdf檔路徑
    target_filepath=r"./test.docx"  # 翻譯好的word檔路徑
    source = 'en'  # 原始檔案語系
    target = 'zh-TW'  # 要翻譯為哪個語系
    page_number = 14  # 取pdf檔第幾頁內容
    
    text = get_pdf_content(source_filepath, page_number)
    target_text = translate_text_with_model(target, text)
    # print(target_text)

    write_docx(target_filepath, target_text)