zy123/zbparse
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

10.24

Browse Source
This commit is contained in:
zy123 2024-10-24 17:12:48 +08:00
parent 4344f9398e
commit 89d709f9d6
3 changed files with 5 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
flask_app/general/format_change.py
View File

@ -66,7 +66,6 @@ def docx2pdf(local_path_in):
downloaded_filepath,file_type = download_file(receive_download_url, local_filename) downloaded_filepath,file_type = download_file(receive_download_url, local_filename)
print(f"format_change d2p:have downloaded file to: {downloaded_filepath}") print(f"format_change d2p:have downloaded file to: {downloaded_filepath}")
return downloaded_filepath return downloaded_filepath
# def docx2pdf(file_path): # def docx2pdf(file_path):
# """ # """
# 将本地的 .docx 或 .doc 文件转换为 .pdf 文件。 # 将本地的 .docx 或 .doc 文件转换为 .pdf 文件。

4
flask_app/main/start_up.py
View File

@ -176,7 +176,7 @@ def get_procurement_reqs():
return jsonify({ return jsonify({
'message': 'procurement_reqs processed successfully', 'message': 'procurement_reqs processed successfully',
'filename': "filename", 'filename': "filename",
'data': response 'data': json.dumps(response, ensure_ascii=False)
}) })
except Exception as e: except Exception as e:
logger.error('Exception occurred: ' + str(e)) # 使用全局 logger 记录 logger.error('Exception occurred: ' + str(e)) # 使用全局 logger 记录
@ -386,7 +386,7 @@ def process_and_stream(file_url, zb_type):
procurement_reqs_response={ procurement_reqs_response={
'message': 'procurement_reqs', 'message': 'procurement_reqs',
'filename': os.path.basename(downloaded_filepath), 'filename': os.path.basename(downloaded_filepath),
'data': procurement_reqs 'data': json.dumps(procurement_reqs, ensure_ascii=False)
} }
yield f"data: {json.dumps(procurement_reqs_response, ensure_ascii=False)}\n\n" yield f"data: {json.dumps(procurement_reqs_response, ensure_ascii=False)}\n\n"

7
flask_app/testdir/截取文件格式.py
View File

@ -178,7 +178,6 @@ def process_input(input_path, output_folder, begin_pattern, begin_page, end_patt
generated_files.append(result) generated_files.append(result)
else: else:
print("提供的路径既不是文件夹也不是PDF/Word文件。") print("提供的路径既不是文件夹也不是PDF/Word文件。")
return [f for f in generated_files if f] # 过滤空字符串 return [f for f in generated_files if f] # 过滤空字符串
@ -191,7 +190,6 @@ def truncate_pdf_main(input_path, output_folder, selection):
begin_page = 10 begin_page = 10
begin_pattern = re.compile( begin_pattern = re.compile(
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:响应|投标).*?格式.*', r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:响应|投标).*?格式.*',
re.MULTILINE
) )
end_pattern = re.compile( end_pattern = re.compile(
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+',
@ -211,9 +209,10 @@ def truncate_pdf_main(input_path, output_folder, selection):
if __name__ == "__main__": if __name__ == "__main__":
# 定义输入和输出路径 # 定义输入和输出路径
input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\包头市公安支队机动车查验监管系统招标文201907.pdf" # input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles"
input_path="C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹"
output_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\新建文件夹" output_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\新建文件夹"
selection = 1 # 1 - 投标文件格式 selection = 1 # 1 - 投标文件格式
# 执行截取 # 执行截取
generated_files = truncate_pdf_main(input_path, output_folder, selection) generated_files = truncate_pdf_main(input_path, output_folder, selection)
print("生成的文件:", generated_files) # print("生成的文件:", generated_files)