diff --git a/flask_app/general/投标人须知正文提取指定内容.py b/flask_app/general/投标人须知正文提取指定内容.py index e48d949..6663dbb 100644 --- a/flask_app/general/投标人须知正文提取指定内容.py +++ b/flask_app/general/投标人须知正文提取指定内容.py @@ -394,9 +394,9 @@ def extract_from_notice(merged_baseinfo_path, clause_path, type): final_result = postprocess_formatted2(extracted_data, target_values) return final_result - # 如果 clause_path 为空，或者所有筛选方法均失败，调用回退函数 - final_result = get_requirements_with_gpt(merged_baseinfo_path, type) - return final_result + # # 如果 clause_path 为空，或者所有筛选方法均失败，调用回退函数 + # final_result = get_requirements_with_gpt(merged_baseinfo_path, type) + # return final_result except Exception as e: print(f"Error occurred while processing clause_path '{clause_path}': {e}") @@ -404,10 +404,10 @@ def extract_from_notice(merged_baseinfo_path, clause_path, type): if __name__ == "__main__": # file_path = 'C:\\Users\\Administrator\\Desktop\\fsdownload\\3bffaa84-2434-4bd0-a8ee-5c234ccd7fa0\\clause1.json' - merged_baseinfo_path=r"C:\Users\Administrator\Desktop\fsdownload\ec7d5328-9c57-450f-baf4-2e5a6f90ed1d\tmp\merged_baseinfo_path_more.pdf" - clause_path=r"C:\Users\Administrator\Desktop\fsdownload\ec7d5328-9c57-450f-baf4-2e5a6f90ed1d\tmp\clause1.json" + merged_baseinfo_path=r"C:\Users\Administrator\Desktop\fsdownload\b29de31a-297e-42cf-b9ba-6859e530a472\ztbfile_merged_baseinfo.pdf" + clause_path=r"C:\Users\Administrator\Desktop\fsdownload\b29de31a-297e-42cf-b9ba-6859e530a472\clause1.json" try: - res = extract_from_notice(merged_baseinfo_path,clause_path, 2) # 可以改变此处的 type 参数测试不同的场景 + res = extract_from_notice(merged_baseinfo_path,clause_path, 1) # 可以改变此处的 type 参数测试不同的场景 res2 = json.dumps(res, ensure_ascii=False, indent=4) print(res2) except ValueError as e: diff --git a/flask_app/general/投标人须知正文条款提取成json文件.py b/flask_app/general/投标人须知正文条款提取成json文件.py index b915a25..c47de3a 100644 --- a/flask_app/general/投标人须知正文条款提取成json文件.py +++ b/flask_app/general/投标人须知正文条款提取成json文件.py @@ -1,5 +1,4 @@ import re - from PyPDF2 import PdfReader from flask_app.货物标.截取pdf货物标版 import clean_page_content,extract_common_header @@ -49,9 +48,6 @@ def handle_content_append(current_content, line_content, append_newline, keyword current_content.append('\n') return append_newline - -import re - def parse_text_by_heading(text): keywords = ['包含', '以下'] data = {} @@ -367,9 +363,6 @@ def parse_text_by_heading(text): return data - - - def extract_text_from_pdf(file_path, start_word, end_pattern): # 从PDF文件中提取文本 common_header = extract_common_header(file_path) diff --git a/flask_app/routes/货物标解析main.py b/flask_app/routes/货物标解析main.py index 445bd7e..349e3b2 100644 --- a/flask_app/routes/货物标解析main.py +++ b/flask_app/routes/货物标解析main.py @@ -284,9 +284,10 @@ def goods_bid_main(output_folder, file_path, file_type, unique_id): #TODO: # 2.废标项这边，考虑大模型+正则并用 -# 废标项，增加对表格的提取+排除重复项 -# 考虑将工程标和货物标的 投标人须知那块结合 - +# 废标项，增加对表格的提取+排除重复项，按顺序处理 +# 考虑将工程标和货物标的 投标人须知那块逻辑结合 +# C:\Users\Administrator\Desktop\fsdownload\b29de31a-297e-42cf-b9ba-6859e530a472 这里的投标文件要求有点问题 +# 解决禅道 测试的bug if __name__ == "__main__": # 配置日志器 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 95c2d67..ee09f4b 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 @@ -363,11 +363,11 @@ 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"D:\flask_project\flask_app\static\output\output1\test\招标文件-第二章-第六章-172404【电能表标准设备172404-1305001-0002】.pdf" + pdf_path=r"C:\Users\Administrator\Downloads\招标文件 (4).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"D:\flask_project\flask_app\static\output\output1\test" # output_folder = r"C:\Users\Administrator\Desktop\new招标文件\output2" - selection = 6 # 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 6-invalid_path + 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 6-invalid_path generated_files = truncate_pdf_main_goods(pdf_path, output_folder, selection,logger) print(generated_files)