236 lines
10 KiB
Python
236 lines
10 KiB
Python
import json
|
||
import os
|
||
import mimetypes
|
||
import requests
|
||
from PyPDF2 import PdfReader
|
||
from flask_app.general.读取文件.clean_pdf import is_scanned_pdf, is_pure_image
|
||
|
||
|
||
def download_file(url, local_filename,enable=False):
|
||
"""
|
||
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）。
|
||
- enable: 是否需要判断为扫描型/纯图片文件
|
||
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
|
||
- "": 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'
|
||
extension_lower = extension.lower() #显式地将 extension 转换为小写（存入 extension_lower），更加健壮
|
||
# 根据传入的 local_filename 构造完整的文件名
|
||
base, current_ext = os.path.splitext(local_filename)
|
||
if current_ext.lower() != extension_lower:
|
||
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 enable and 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, force=True)
|
||
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 "",4
|
||
|
||
def local_file_2_url(file_path, url):
|
||
receive_file_url = ""
|
||
# 定义文件名和路径
|
||
filename = file_path.split('/')[-1]
|
||
|
||
# 打开文件以二进制形式读取
|
||
with open(file_path, 'rb') as f:
|
||
# 使用multipart/form-data格式发送文件
|
||
files = {'file': (filename, f)}
|
||
|
||
# 发送POST请求
|
||
response = requests.post(url, files=files)
|
||
|
||
# 检查响应状态码
|
||
if response.status_code == 200:
|
||
print("format_change 文件上传成功")
|
||
receive_file_response = response.content.decode('utf-8')
|
||
receive_file_json = json.loads(receive_file_response)
|
||
receive_file_url = receive_file_json["data"]
|
||
|
||
else:
|
||
print(f"format_change 文件上传失败，状态码: {response.status_code}")
|
||
print(f"format_change {response.text}")
|
||
|
||
return receive_file_url
|
||
|
||
|
||
def get_filename_and_folder(file_path):
|
||
# 使用os.path.basename获取文件名
|
||
original_filename = os.path.basename(file_path)
|
||
filename_without_ext, ext = os.path.splitext(original_filename)
|
||
|
||
# 替换文件名中的点为下划线，避免分割问题
|
||
safe_filename = filename_without_ext.replace('.', '_')
|
||
|
||
# 使用os.path.dirname获取文件所在的完整目录路径
|
||
directory = os.path.dirname(file_path)
|
||
return safe_filename, directory
|
||
|
||
#参数为要转换的文件路径，以及输出的文件名，文件类型为自动补全。
|
||
def pdf2docx(local_path_in):
|
||
if not local_path_in:
|
||
return ""
|
||
|
||
# 获取文件名和所在文件夹
|
||
filename, folder = get_filename_and_folder(local_path_in)
|
||
|
||
# 检查是否已经存在同名的 .docx 文件
|
||
docx_file_path = os.path.join(folder, f"{filename}.docx")
|
||
if os.path.exists(docx_file_path):
|
||
print(f"Skipping conversion, {docx_file_path} already exists.")
|
||
return docx_file_path
|
||
|
||
remote_url = 'http://47.98.59.178:8000/v3/3rd/files/transfer/p2d'
|
||
receive_download_url = local_file_2_url(local_path_in, remote_url) # 转换完成，得到下载链接
|
||
|
||
local_filename = os.path.join(folder,filename) # 输出文件名 C:\Users\Administrator\Desktop\货物标\zbfiles\6.2定版视频会议磋商文件 不带后缀
|
||
downloaded_filepath, file_type = download_file(receive_download_url, local_filename)
|
||
print(f"format_change p2d:have downloaded file to: {downloaded_filepath}")
|
||
return downloaded_filepath
|
||
|
||
def doc2docx(local_path_in):
|
||
if not local_path_in:
|
||
return ""
|
||
# 获取文件名和所在文件夹
|
||
filename, folder = get_filename_and_folder(local_path_in)
|
||
|
||
# 检查是否已经存在同名的 .docx 文件
|
||
docx_file_path = os.path.join(folder, f"{filename}.docx")
|
||
if os.path.exists(docx_file_path):
|
||
print(f"Skipping conversion, {docx_file_path} already exists.")
|
||
return docx_file_path
|
||
|
||
remote_url = 'http://47.98.59.178:8000/v3/3rd/files/transfer/d2d'
|
||
receive_download_url = local_file_2_url(local_path_in, remote_url)
|
||
print(receive_download_url)
|
||
filename, folder = get_filename_and_folder(local_path_in) # 输入输出在同一个文件夹
|
||
local_filename = os.path.join(folder, filename) # 输出文件名
|
||
downloaded_filepath, file_type = download_file(receive_download_url, local_filename)
|
||
print(f"format_change d2d:have downloaded file to: {downloaded_filepath}")
|
||
return downloaded_filepath
|
||
|
||
def docx2pdf(local_path_in,force=False):
|
||
"""
|
||
将 DOCX 文件转换为 PDF。
|
||
|
||
参数:
|
||
- local_path_in (str): 输入的 DOCX 文件路径。
|
||
- force (bool): 是否强制转换并覆盖已存在的 PDF 文件。默认为 False。
|
||
|
||
返回:
|
||
- str: 转换后的 PDF 文件路径
|
||
- "" 如果转换失败
|
||
"""
|
||
if not local_path_in:
|
||
return ""
|
||
# 获取文件名和所在文件夹
|
||
filename, folder = get_filename_and_folder(local_path_in)
|
||
# 检查是否已经存在同名的 .pdf 文件
|
||
pdf_file_path = os.path.join(folder, f"{filename}.pdf")
|
||
if os.path.exists(pdf_file_path):
|
||
if force:
|
||
print(f"强制转换，覆盖已存在的文件: {pdf_file_path}") #覆盖掉原来的扫描型pdf
|
||
else:
|
||
print(f"跳过转换，文件已存在: {pdf_file_path}")
|
||
return pdf_file_path # 跳过转换
|
||
remote_url = 'http://47.98.59.178:8000/v3/3rd/files/transfer/d2p'
|
||
receive_download_url = local_file_2_url(local_path_in, remote_url)
|
||
filename, folder = get_filename_and_folder(local_path_in) # 输入输出在同一个文件夹
|
||
local_filename = os.path.join(folder, filename) # 输出文件名
|
||
downloaded_filepath,file_type = download_file(receive_download_url, local_filename)
|
||
print(f"format_change d2p:have downloaded file to: {downloaded_filepath}")
|
||
return downloaded_filepath
|
||
|
||
def get_pdf_page_count(file_path):
|
||
"""
|
||
获取 PDF 文件的页码数量
|
||
"""
|
||
try:
|
||
pdf_path=file_path
|
||
if file_path.lower().endswith(('.doc', '.docx')):
|
||
pdf_path = docx2pdf(file_path)
|
||
reader = PdfReader(pdf_path)
|
||
return len(reader.pages)
|
||
except Exception as e:
|
||
print(f"读取 PDF 页码时出错：{e}")
|
||
return 0
|
||
|
||
if __name__ == '__main__':
|
||
# 替换为你的文件路径和API URL
|
||
# local_path_in="C:\\Users\\Administrator\\Desktop\\fsdownload\\1fbbb6ff-7ddc-40bb-8857-b7de37aece3f\\兴欣工程.pdf"
|
||
local_path_in = r"C:\Users\Administrator\Desktop\fsdownload\bf0346dc-8711-43f5-839e-e4076acea84a\tmp\invalid_added.pdf"
|
||
# local_path_in="C:\\Users\\Administrator\\Desktop\\fsdownload\\ztbfile.pdf"
|
||
# local_path_in ="C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\招标文件.pdf"
|
||
# local_path_in=r"C:\Users\Administrator\Desktop\fsdownload\457ee03d-c61c-4672-b959-2bbb35a1de29\ztbfile_invalid.pdf"
|
||
# local_path_in = r"C:\Users\Administrator\Desktop\新建文件夹 (3)\ztbfile(1).pdf"
|
||
# intermediate_docx = pdf2docx(local_path_in)
|
||
# if intermediate_docx:
|
||
# normal_pdf = docx2pdf(intermediate_docx, force=True)
|
||
downloaded_file=pdf2docx(local_path_in)
|
||
# downloaded_file=docx2pdf(local_path_in)
|
||
print(downloaded_file)
|
||
|
||
# test_url = "https://bid-assistance.oss-cn-wuhan-lr.aliyuncs.com/test/%E6%B5%8B%E8%AF%95%E4%BF%A1%E5%8F%B7%E6%B5%8B%E8%AF%95%E4%BF%A1%E5%8F%B7.pdf?Expires=1736852995&OSSAccessKeyId=TMP.3Kg1oKKcsSWb7DXNe4F56bfGfKY5nNWUi274p39HyY7GR3mghMCaFWy69Fi83SBab6PmSkErh4JUD4yAxAGzVVx2hxxoxm&Signature=rmxS5lett4MzWdksDI57EujCklw%3"
|
||
# local_file_name = r'D:\flask_project\flask_app\static\output\output1\1d763771-f25a-4b65-839e-3b2ca56577b1\tmp\ztbfile.pdf'
|
||
# 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")
|
||
# res=pdf2docx(local_path_in)
|
||
# print(res)
|
||
|
||
|
||
|