177 lines
6.7 KiB
Python
177 lines
6.7 KiB
Python
import json
|
||
import os
|
||
import requests
|
||
|
||
from flask_app.main.download import download_file
|
||
|
||
|
||
def upload_file(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
|
||
filename = os.path.splitext(os.path.basename(file_path))[0] #ztb_tobidders_notice_table,不包括扩展名
|
||
# 使用os.path.dirname获取文件所在的完整目录路径，再次使用basename获取文件夹名称
|
||
directory = os.path.dirname(file_path)
|
||
return 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):
|
||
remote_url = 'http://47.98.59.178:8000/v3/3rd/files/transfer/p2d'
|
||
receive_download_url = upload_file(local_path_in, remote_url) #转换完成，得到下载链接
|
||
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 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):
|
||
# remote_url = 'http://47.98.59.178:8000/v3/3rd/files/transfer/d2d'
|
||
# receive_download_url = upload_file(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):
|
||
# remote_url = 'http://47.98.59.178:8000/v3/3rd/files/transfer/d2p'
|
||
# receive_download_url = upload_file(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 docx2pdf(file_path):
|
||
"""
|
||
将本地的 .docx 或 .doc 文件转换为 .pdf 文件。
|
||
|
||
参数：
|
||
- file_path: str, 本地文件的路径，支持 .docx 和 .doc 格式。
|
||
"""
|
||
# 检查文件是否存在
|
||
if not os.path.isfile(file_path):
|
||
raise FileNotFoundError(f"文件未找到: {file_path}")
|
||
|
||
# 获取文件名和扩展名
|
||
base_name = os.path.basename(file_path)
|
||
name, ext = os.path.splitext(base_name)
|
||
ext = ext.lower().lstrip('.')
|
||
|
||
if ext not in ['docx', 'doc']:
|
||
raise ValueError(f"doc2pdf 仅支持 .docx 和 .doc 文件，当前文件扩展名为: .{ext}")
|
||
|
||
# 定义转换接口
|
||
endpoint = 'http://120.26.236.97:5008/convert_to_pdf'
|
||
|
||
# 获取文件所在目录
|
||
output_dir = os.path.dirname(file_path)
|
||
|
||
# 准备上传的文件
|
||
with open(file_path, 'rb') as f:
|
||
files = {'file': (base_name, f)}
|
||
try:
|
||
print(f"正在将 {base_name} 转换为 .pdf 格式...")
|
||
response = requests.post(endpoint, files=files)
|
||
response.raise_for_status() # 检查请求是否成功
|
||
except requests.RequestException as e:
|
||
print(f"转换过程中发生错误: {e}")
|
||
return
|
||
|
||
# 准备保存转换后文件的路径
|
||
output_file_name = f"{name}.pdf"
|
||
output_path = os.path.join(output_dir, output_file_name)
|
||
|
||
# 保存转换后的文件
|
||
with open(output_path, 'wb') as out_file:
|
||
out_file.write(response.content)
|
||
|
||
print(f"文件已成功转换并保存至: {output_path}")
|
||
|
||
|
||
def doc2docx(file_path):
|
||
"""
|
||
将本地的 .doc 文件转换为 .docx 文件。
|
||
|
||
参数：
|
||
- file_path: str, 本地文件的路径，支持 .doc 格式。
|
||
"""
|
||
# 检查文件是否存在
|
||
if not os.path.isfile(file_path):
|
||
raise FileNotFoundError(f"文件未找到: {file_path}")
|
||
|
||
# 获取文件名和扩展名
|
||
base_name = os.path.basename(file_path)
|
||
name, ext = os.path.splitext(base_name)
|
||
ext = ext.lower().lstrip('.')
|
||
|
||
if ext != 'doc':
|
||
raise ValueError(f"doc2docx 仅支持 .doc 文件，当前文件扩展名为: .{ext}")
|
||
|
||
# 定义转换接口
|
||
endpoint = 'http://120.26.236.97:5008/convert_to_docx'
|
||
|
||
# 获取文件所在目录
|
||
output_dir = os.path.dirname(file_path)
|
||
|
||
# 准备上传的文件
|
||
with open(file_path, 'rb') as f:
|
||
files = {'file': (base_name, f)}
|
||
try:
|
||
print(f"正在将 {base_name} 转换为 .docx 格式...")
|
||
response = requests.post(endpoint, files=files)
|
||
response.raise_for_status() # 检查请求是否成功
|
||
except requests.RequestException as e:
|
||
print(f"转换过程中发生错误: {e}")
|
||
return
|
||
|
||
# 准备保存转换后文件的路径
|
||
output_file_name = f"{name}.docx"
|
||
output_path = os.path.join(output_dir, output_file_name)
|
||
|
||
# 保存转换后的文件
|
||
with open(output_path, 'wb') as out_file:
|
||
out_file.write(response.content)
|
||
|
||
print(f"文件已成功转换并保存至: {output_path}")
|
||
|
||
|
||
|
||
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 = "C:\\Users\\Administrator\\Desktop\\fsdownload\\b151fcd0-4cd8-49b4-8de3-964057a9e653\\ztbfile.docx"
|
||
# local_path_in="C:\\Users\\Administrator\\Desktop\\fsdownload\\ztbfile.pdf"
|
||
# downloaded_file=doc2docx(local_path_in)
|
||
# downloaded_file=pdf2docx(local_path_in)
|
||
downloaded_file=docx2pdf(local_path_in)
|
||
print(downloaded_file)
|
||
|
||
|
||
|
||
|