From ca56a0894f0347e805073e79a74d6f082891c6f6 Mon Sep 17 00:00:00 2001
From: zy123 <646228430@qq.com>
Date: Wed, 18 Dec 2024 14:02:46 +0800
Subject: [PATCH] =?UTF-8?q?12.18=20=E6=88=AA=E5=8F=96pdf?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 flask_app/general/截取pdf通用函数.py | 18 ++++++++++++++++++
 flask_app/工程标/截取pdf工程标版.py  | 17 ++++++++++++++++-
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/flask_app/general/截取pdf通用函数.py b/flask_app/general/截取pdf通用函数.py
index 19876d3..30b2ef9 100644
--- a/flask_app/general/截取pdf通用函数.py
+++ b/flask_app/general/截取pdf通用函数.py
@@ -108,4 +108,22 @@ def convert_to_pdf(file_path):
         return docx2pdf(file_path)
     return file_path
 
+def get_invalid_file(file_path,output_folder,common_header):
+    pdf_document = PdfReader(file_path)
+    total_pages = len(pdf_document.pages)
+    begin_pattern=[regex.compile(
+                                r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:公告|邀请书|邀请函|邀请).*|^第一卷|^投标邀请书|^投标邀请函|^投标邀请',regex.MULTILINE
+                            ),
+        regex.compile(
+        r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:招标公告|磋商公告|谈判公告|邀请书|邀请函|投标邀请|磋商邀请|谈判邀请)[\)）]?\s*$',
+        regex.MULTILINE
+    )]
+    end_pattern=[regex.compile(
+                                r'第[一二三四五六七八九十]+章\s*合同|[：:]清标报告|^第二卷',
+                                regex.MULTILINE
+                            ),
+        regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:响应|投标).*?格式.*', regex.MULTILINE),
+        regex.compile(r"\s*(投标文件格式|响应文件格式|响应性文件格式)\s*"
+    ]
+
 
diff --git a/flask_app/工程标/截取pdf工程标版.py b/flask_app/工程标/截取pdf工程标版.py
index f030f86..799a128 100644
--- a/flask_app/工程标/截取pdf工程标版.py
+++ b/flask_app/工程标/截取pdf工程标版.py
@@ -5,7 +5,7 @@ import time
 from PyPDF2 import PdfReader, PdfWriter
 from flask_app.general.clean_pdf import clean_page_content
 
-from flask_app.general.截取pdf通用函数 import get_start_and_common_header,save_extracted_pages
+from flask_app.general.截取pdf通用函数 import get_start_and_common_header,save_extracted_pages,get_invalid_file
 from flask_app.general.通用功能函数 import get_global_logger
 
 def extract_pages_tobidders_notice(pdf_path, output_folder, begin_pattern, begin_page, common_header,
@@ -383,6 +383,21 @@ def truncate_pdf_main_engineering(input_path, output_folder, selection,logger,ou
                         5: 0  # 无效标
                     }.get(selection, 0)
 
+                    if selection == 5: #无效标
+                        invalid_path = list(
+                            get_invalid_file(
+                                file_path,
+                                output_folder,
+                                begin_pattern,
+                                common_header,
+                            )
+                        )
+                        if invalid_path:
+                            return invalid_path
+                        else:
+                            # print(f"Selection {selection}: 使用组合提取函数失败。尝试下一个模式对。")
+                            continue
+
                     if selection == 4:  # 投标人须知
                         output_paths = list(
                             extract_pages_tobidders_notice(