import time from submit_conversion import submit_conversion_task from check_status import get_download_url from download import download_file def download_pdf_convert_docx(url, downloaded_filename): """ Download a PDF from a URL, convert it to a DOCX, and save it locally. Args: url (str): The URL of the PDF to be downloaded. downloaded_filename (str): The filename to save the converted DOCX as. """ # 提交转换任务并获取task_id task_id = submit_conversion_task(url) if task_id: download_url = None # 使用while循环进行每秒的查询 while not download_url: time.sleep(0.5) download_url = get_download_url(task_id) # 如果得到下载链接 if download_url: # 下载文件 download_file(download_url, downloaded_filename) print(f'File downloaded and saved as {downloaded_filename}') else: print("Failed to get download URL.") else: print("Failed to submit conversion task.") if __name__ == "__main__": # PDF文件URL pdf_url = "https://temp-pdf2docx.oss-cn-wuhan-lr.aliyuncs.com/pdf/02cf0a7a8cda432a8ba7a929862510eb.pdf?Expires=1724035295&OSSAccessKeyId=TMP.3Kj9nRWk3bspYRpZJJeKSSDjuoiSsd1SYBnHtac62JciczGbftutcSUcM5RpLTQNQXeANRNbdSxK2VnX9cQZ9bUgR3dWDv&Signature=MJfXEZe1fy5CEIoJ1IxhliSv0Ss%3D" # pdf_url="C:\\Users\\Administrator\\Desktop\\招标文件\\output1\\zbfile.pdf" downloaded_filename = 'downloaded_document.docx' download_pdf_convert_docx(pdf_url, downloaded_filename)