zbparse/flask_app/old_version/download_old.py

import os

import requests
import mimetypes

from flask_app.general.clean_pdf import is_scanned_pdf
from flask_app.general.format_change import pdf2docx, docx2pdf


def download_file(url, local_filename):
    """
    下载文件并保存到本地，基于Content-Type设置文件扩展名。

    参数:
    - url (str): 文件的URL地址。
    - local_filename (str): 本地保存的文件名（不含扩展名）。

    返回:
    - tuple: (完整文件名, 文件类型代码)
             文件类型代码:
                 1 - .docx
                 2 - .pdf
                 3 - .doc
                 4 - 其他
    - None: 下载失败
    """
    try:
        with requests.get(url, stream=True) as response:
            response.raise_for_status()  # 确保请求成功，否则抛出异常

            # 获取Content-Type并猜测文件扩展名
            content_type = response.headers.get('Content-Type', '')
            extension = mimetypes.guess_extension(content_type, strict=False) or '.docx'

            # 分离文件名和现有扩展名
            base, ext = os.path.splitext(local_filename)
            if ext.lower() != extension:
                full_filename = base + extension
            else:
                full_filename = local_filename

            # 下载并保存文件
            with open(full_filename, 'wb') as file:
                for chunk in response.iter_content(chunk_size=8192):
                    if chunk:  # 避免写入空块
                        file.write(chunk)

            # 定义扩展名到代码的映射
            extension_mapping = {
                '.docx': 1,
                '.pdf': 2,
                '.doc': 3
            }
            file_code = extension_mapping.get(extension.lower(), 4)
            # 如果是 PDF，判断是否为扫描型
            if extension.lower() == '.pdf':
                print(f"Checking if the PDF is scanned: {full_filename}")
                if is_scanned_pdf(full_filename):
                    print(f"PDF is scanned. Converting to normal PDF: {full_filename}")
                    # 转换扫描型 PDF -> DOCX -> 普通 PDF
                    intermediate_docx = pdf2docx(full_filename)
                    if intermediate_docx:
                        normal_pdf = docx2pdf(intermediate_docx)
                        if normal_pdf:
                            # 替换原始 PDF 文件
                            os.replace(normal_pdf, full_filename)
                            print(f"Replaced scanned PDF with normal PDF: {full_filename}")
            return full_filename, file_code

    except requests.HTTPError as e:
        print(f"download: HTTP 错误: {e}")
    except requests.RequestException as e:
        print(f"download: 下载文件时出错: {e}")
    except Exception as e:
        print(f"download: 发生错误: {e}")

    return None

if __name__ == '__main__':
    # 测试下载的URL
    test_url ="https://bid-assistance.oss-cn-wuhan-lr.aliyuncs.com/test/2020-%E5%AE%89%E5%BE%BD-%E5%AE%89%E5%BE%BD%E7%9C%81%E7%94%9F%E6%80%81%E7%8E%AF%E5%A2%83%E5%8E%85%E7%94%B5%E6%A2%AF%E9%87%87%E8%B4%AD.pdf?Expires=1733410076&OSSAccessKeyId=TMP.3KdesMxbSGgK41BgYKRtckUxdQ2LUh2YMYiH1FnuupFhvRuxMbiuBAsXK9oGvHxaLvsDLQjp3db28cUK5YJSEYTGPnUevo&Signature=1cZOCTJPwOJY%2BwCfnLHc0teGTZQ%3D"
    local_file_name = r'C:\Users\Administrator\Documents\WeChat Files\wxid_d11awe5rp1y722\FileStorage\File\2024-12\ztbfile'
    downloaded = download_file(test_url, local_file_name)
    if not downloaded:
        print("下载文件失败或不支持的文件类型")
    downloaded_filepath, file_type = downloaded
    print(downloaded_filepath)
    print(file_type)
    # 检查文件类型
    if file_type == 4:
        print("error")