From 72d787c899a81752a442d995aaac2496407b11aa Mon Sep 17 00:00:00 2001
From: zy123 <646228430@qq.com>
Date: Tue, 7 Jan 2025 14:03:58 +0800
Subject: [PATCH] =?UTF-8?q?1.6=20=E5=95=86=E5=8A=A1=E5=B8=A6=E6=98=9F?=
 =?UTF-8?q?=E8=A6=81=E6=B1=82=E5=9C=A8=E6=A0=87=E9=A2=98=E4=B8=AD->?=
 =?UTF-8?q?=E4=BC=A0=E9=80=92=E5=88=B0=E5=85=B7=E4=BD=93=E8=A6=81=E6=B1=82?=
 =?UTF-8?q?=E4=B8=AD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 flask_app/工程标/截取pdf工程标版.py | 15 +++++++--------
 flask_app/货物标/截取pdf货物标版.py | 18 +++++++++---------
 2 files changed, 16 insertions(+), 17 deletions(-)

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 bd7a9f3..3b5f859 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
@@ -68,7 +68,7 @@ def extract_pages_tobidders_notice(pdf_path, output_folder, begin_pattern, begin
                         # 定义基础的 mid_pattern
                         base_mid_pattern = r'^\s*(?:[（(]\s*[一二12]?\s*[)）]\s*[、．.]*|' \
                                            r'[一二12][、．.]+|[、．.]+)\s*(说\s*明|总\s*则|名\s*词\s*解\s*释)' \
-                                           r'|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商)\s*须知正文\s*$'
+                                           r'|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)\s*须知正文\s*$'
                         # 合并基础模式和额外模式
                         if additional_mid_pattern:
                             combined_mid_pattern = regex.compile(
@@ -176,8 +176,7 @@ def extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, l
         if output_suffix == "qualification":
             print("twice:qualificaiton!")
             # 动态设置 include_keys
-            include_keys = ["资格审查", "资质审查", "符合性审查", "资格性检查", "符合性检查", "资格检查", "能力",
-                            "信誉"]
+            include_keys = ["资格审查", "资质审查", "符合性审查", "资格性检查", "符合性检查", "资格检查", "能力","信誉"]
             # 定义起始匹配模式，仅匹配“附录”、“附件”或“附表”
             begin_pattern = r'^(?:附录(?:[一1])?[：:]|附件(?:[一1])?[：:]|附表(?:[一1])?[：:])'
             # 定义结束匹配模式 - 附录、附件、附表等（移除负向前瞻）
@@ -260,7 +259,7 @@ def truncate_pdf_main_engineering(input_path, output_folder, selection, logger,
                                 regex.MULTILINE
                             ),
                             regex.compile(
-                                r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知(?:前附表)?\s*$',
+                                r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|供应商|谈判供应商|磋商供应商|应答人)须知(?:前附表)?\s*$',
                                 regex.MULTILINE
                             )
                         )
@@ -324,8 +323,8 @@ def truncate_pdf_main_engineering(input_path, output_folder, selection, logger,
                     pattern_pairs = [
                         (
                             regex.compile(
-                                r'(?:第[一二三四五六七八九十百千]+(?:章|部分).*(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商)须知|'
-                                r'(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商)须知前附表)\s*$',
+                                r'(?:第[一二三四五六七八九十百千]+(?:章|部分).*(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知|'
+                                r'(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知前附表)\s*$',
                                 regex.MULTILINE
                             ),
                             regex.compile(
@@ -335,8 +334,8 @@ def truncate_pdf_main_engineering(input_path, output_folder, selection, logger,
                         ),
                         (
                             regex.compile(
-                                r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商)须知\s*$|'
-                                r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商)须知前附表\s*$',
+                                r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知\s*$|'
+                                r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知前附表\s*$',
                                 regex.MULTILINE
                             ),
                             regex.compile(
diff --git a/flask_app/货物标/截取pdf货物标版.py b/flask_app/货物标/截取pdf货物标版.py
index 32ce61c..3441a6a 100644
--- a/flask_app/货物标/截取pdf货物标版.py
+++ b/flask_app/货物标/截取pdf货物标版.py
@@ -209,7 +209,7 @@ def extract_pages_tobidders_notice(pdf_path, begin_pattern, begin_page, common_h
                             # 定义基础的 mid_pattern
                             base_mid_pattern = r'^\s*(?:[（(]\s*[一二12]?\s*[)）]\s*[、．.]*|' \
                                                r'[一二12][、．.]+|[、．.]+)\s*(说\s*明|总\s*则|名\s*词\s*解\s*释)' \
-                                               r'|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商)\s*须知正文\s*$'
+                                               r'|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)\s*须知正文\s*$'
 
                             # 合并基础模式和额外模式
                             if additional_mid_pattern:
@@ -276,8 +276,8 @@ def extract_pages_tobidders_notice(pdf_path, begin_pattern, begin_page, common_h
         else:
             # 定义新的 begin_pattern 和 end_pattern
             new_begin_pattern = regex.compile(
-                r'.*(?:投标人|磋商|谈判|供应商|谈判供应商|磋商供应商)须知\s*$|'
-                r'(?:一\s*、\s*)?(?:投标人?|磋商|谈判|供应商)须知前附表',
+                r'.*(?:投标人|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知\s*$|'
+                r'(?:一\s*、\s*)?(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知前附表',
                 regex.MULTILINE
             )
             new_end_pattern = regex.compile(
@@ -294,7 +294,7 @@ def extract_pages_tobidders_notice(pdf_path, begin_pattern, begin_page, common_h
 def extract_pages_twice_tobidders_notice(pdf_document, common_header, begin_page):
     output_suffix = "tobidders_notice"
     begin_pattern = regex.compile(
-        r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商)须知)+',
+        r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知)+',
         regex.MULTILINE
     )
     end_pattern = regex.compile(
@@ -516,8 +516,8 @@ def truncate_pdf_main_goods(input_path, output_folder, selection,logger, output_
                     local_output_suffix = "qualification1"
                 elif selection == 4:
                     begin_pattern = regex.compile(
-                        r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商)须知+|'
-                        r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商)须知前附表\s*$',
+                        r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知+|'
+                        r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知前附表\s*$',
                         regex.MULTILINE
                     )
                     end_pattern = None
@@ -612,11 +612,11 @@ if __name__ == "__main__":
     logger = get_global_logger("123")
     # input_path = r"C:\Users\Administrator\Desktop\new招标文件\货物标"
     # pdf_path = r"C:\Users\Administrator\Desktop\招标文件-采购类\2024-贵州-贵州医科大学附属医院导视系统零星制作安装项目.pdf"
-    pdf_path=r"C:\Users\Administrator\Desktop\fsdownload\0bb9cf31-280c-4d96-bc21-0871ee7fd6df\ztbfile.pdf"
+    pdf_path=r"D:\flask_project\flask_app\static\output\output1\f91db70d-8d96-44a5-b840-27d2f1ecbe95\ztbfile.pdf"
     # input_path = r"C:\Users\Administrator\Desktop\货物标\zbfiles\2-招标文件（广水市教育局封闭管理）.pdf"
     # pdf_path=r"C:\Users\Administrator\Desktop\文件解析问题\文件解析问题\1414cb9c-7bf4-401c-8761-2acde151b9c2\ztbfile.pdf"
-    output_folder = r"C:\Users\Administrator\Desktop\fsdownload\0bb9cf31-280c-4d96-bc21-0871ee7fd6df\tmp"
+    output_folder = r"D:\flask_project\flask_app\static\output\output1\f91db70d-8d96-44a5-b840-27d2f1ecbe95\tmp"
     # output_folder = r"C:\Users\Administrator\Desktop\new招标文件\output2"
-    selection = 5  # 例如：1 - 公告, 2 - 评标办法, 3 - 资格审查后缀有qualification1或qualification2（与评标办法一致）  4.投标人须知前附表part1 投标人须知正文part2   5-采购需求
+    selection = 4  # 例如：1 - 公告, 2 - 评标办法, 3 - 资格审查后缀有qualification1或qualification2（与评标办法一致）  4.投标人须知前附表part1 投标人须知正文part2   5-采购需求
     generated_files = truncate_pdf_main_goods(pdf_path, output_folder, selection,logger)
     # print(generated_files)