zy123/zbparse
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
zbparse/flask_app/general/format_change.py

298 lines
12 KiB
Python
Raw Normal View History

8.29
2024-08-29 16:37:09 +08:00
import json
import os
12.6
2024-12-05 15:01:37 +08:00
import mimetypes
8.29
2024-08-29 16:37:09 +08:00
import requests
9.11 改为全局logger，完善了无效标的bug
2024-09-11 12:02:09 +08:00
12.6
2024-12-05 15:01:37 +08:00
from flask_app.general.clean_pdf import is_scanned_pdf
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
8.29
2024-08-29 16:37:09 +08:00
12.6
2024-12-05 15:01:37 +08:00
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
8.29
2024-08-29 16:37:09 +08:00
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:
9.13
2024-09-13 15:03:55 +08:00
print("format_change 文件上传成功")
8.29
2024-08-29 16:37:09 +08:00
receive_file_response = response.content.decode('utf-8')
receive_file_json = json.loads(receive_file_response)
receive_file_url = receive_file_json["data"]
else:
9.13
2024-09-13 15:03:55 +08:00
print(f"format_change 文件上传失败，状态码: {response.status_code}")
print(f"format_change {response.text}")
8.29
2024-08-29 16:37:09 +08:00
return receive_file_url
11.1适配货物标
2024-11-01 14:28:10 +08:00
8.29
2024-08-29 16:37:09 +08:00
def get_filename_and_folder(file_path):
# 使用os.path.basename获取文件名
11.1适配货物标
2024-11-01 14:28:10 +08:00
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
8.29
2024-08-29 16:37:09 +08:00
directory = os.path.dirname(file_path)
11.1适配货物标
2024-11-01 14:28:10 +08:00
return safe_filename, directory
8.29
2024-08-29 16:37:09 +08:00
#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):
10.30健壮性优化
2024-10-30 16:56:05 +08:00
if not local_path_in:
return ""
12.6
2024-12-05 15:01:37 +08:00
# 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
8.29
2024-08-29 16:37:09 +08:00
remote_url = 'http://47.98.59.178:8000/v3/3rd/files/transfer/p2d'
12.6
2024-12-05 15:01:37 +08:00
receive_download_url = upload_file(local_path_in, remote_url) # 转换完成，得到下载链接
12.18 截取pdf
2024-12-19 12:18:50 +08:00
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
12.6
2024-12-05 15:01:37 +08:00
downloaded_filepath, file_type = download_file(receive_download_url, local_filename)
9.13
2024-09-13 15:03:55 +08:00
print(f"format_change p2d:have downloaded file to: {downloaded_filepath}")
8.29
2024-08-29 16:37:09 +08:00
return downloaded_filepath
11.1适配货物标
2024-11-01 14:28:10 +08:00
def doc2docx(local_path_in):
if not local_path_in:
10.30健壮性优化
2024-10-30 16:56:05 +08:00
return ""
12.18 截取pdf
2024-12-19 12:18:50 +08:00
# 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
11.1适配货物标
2024-11-01 14:28:10 +08:00
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):
if not local_path_in:
10.30健壮性优化
2024-10-30 16:56:05 +08:00
return ""
12.18 截取pdf
2024-12-19 12:18:50 +08:00
# 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):
print(f"Skipping conversion, {pdf_file_path} already exists.")
return pdf_file_path
11.1适配货物标
2024-11-01 14:28:10 +08:00
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
10.24
2024-10-24 20:51:48 +08:00
11.1适配货物标
2024-11-01 14:28:10 +08:00
# 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 file_path:
# return ""
# # 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'
# # endpoint = 'http://192.168.0.2:5008/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}")
# return 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 file_path:
# return ""
# # 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}")
# return output_path
10.23 无效标优化
2024-10-23 20:33:41 +08:00
8.29
2024-08-29 16:37:09 +08:00
if __name__ == '__main__':
# 替换为你的文件路径和API URL
10.24
2024-10-24 10:56:33 +08:00
# local_path_in="C:\\Users\\Administrator\\Desktop\\fsdownload\\1fbbb6ff-7ddc-40bb-8857-b7de37aece3f\\兴欣工程.pdf"
10.24
2024-10-24 20:51:48 +08:00
# local_path_in = "C:\\Users\\Administrator\\Desktop\\fsdownload\\b151fcd0-4cd8-49b4-8de3-964057a9e653\\ztbfile.docx"
10.24
2024-10-24 15:52:35 +08:00
# local_path_in="C:\\Users\\Administrator\\Desktop\\fsdownload\\ztbfile.pdf"
10.29截取工程标新逻辑
2024-10-29 20:40:14 +08:00
# local_path_in ="C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\招标文件.pdf"
11.21 修复了工程标资格审查的bug
2024-11-21 11:54:30 +08:00
# local_path_in=r"C:\Users\Administrator\Desktop\fsdownload\457ee03d-c61c-4672-b959-2bbb35a1de29\ztbfile_invalid.pdf"
12.6 优化解析
2024-12-06 14:40:22 +08:00
# local_path_in = r"C:\Users\Administrator\Documents\WeChat Files\wxid_d11awe5rp1y722\FileStorage\File\2024-12\ztbfile.pdf"
# downloaded_file=pdf2docx(local_path_in)
12.6
2024-12-05 15:01:37 +08:00
# # downloaded_file=pdf2docx(local_path_in)
# # downloaded_file=docx2pdf(local_path_in)
12.6 优化解析
2024-12-06 14:40:22 +08:00
# print(downloaded_file)
test_url = "https://bid-assistance.oss-cn-wuhan-lr.aliyuncs.com/test/094%E5%AE%9A%E7%A8%BF-%E6%B9%96%E5%8C%97%E5%B7%A5%E4%B8%9A%E5%A4%A7%E5%AD%A6%E8%BD%BB%E6%AD%A6%E5%99%A8%E6%A8%A1%E6%8B%9F%E5%B0%84%E5%87%BB%E8%AE%BE%E5%A4%87%E9%87%87%E8%B4%AD%E9%A1%B9%E7%9B%AE%E6%8B%9B%E6%A0%87%E6%96%87%E4%BB%B6%20-%20%E5%89%AF%E6%9C%AC.PDF?Expires=1733478585&OSSAccessKeyId=TMP.3KhfwZc3kpT9TUmsb46yBDdnRq8bbENcEWBbZP8nLMgmSjVkjg9edpTPUQUsH8VXtvvg839Xbm8N5paYxPKvxCGqx3Vx4m&Signature=RYOo7tMEyahaMA3cSsf2kkf8co8%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")
8.29
2024-08-29 16:37:09 +08:00
Reference in New Issue Copy Permalink