10.29截取工程标新逻辑
This commit is contained in:
parent
54b2738ea1
commit
5a5ac65f34
@ -53,7 +53,8 @@ def aggregate_basic_info_engineering(baseinfo_list):
|
||||
dynamic_key_handling(key_groups, relevant_keys_detected)
|
||||
|
||||
# 创建一个副本以存储未分类的项目
|
||||
unclassified_items = {k: v for k, v in combined_data.items() if k not in [item for sublist in key_groups.values() for item in sublist]}
|
||||
unclassified_items = {k: v for k, v in combined_data.items() if
|
||||
k not in [item for sublist in key_groups.values() for item in sublist]}
|
||||
|
||||
# 按键组分类并嵌套
|
||||
for group_name, keys in key_groups.items():
|
||||
@ -73,6 +74,7 @@ def aggregate_basic_info_engineering(baseinfo_list):
|
||||
|
||||
return combined_data
|
||||
|
||||
|
||||
def dynamic_key_handling(key_groups, detected_keys):
|
||||
# 检查和调整键组配置
|
||||
for key in detected_keys:
|
||||
@ -120,6 +122,7 @@ def update_baseinfo_lists(baseinfo_list1, baseinfo_list2):
|
||||
|
||||
return updated_list
|
||||
|
||||
|
||||
def process_judge_questions(judge_file_path, chosen_numbers, tobidders_notice_table, baseinfo_list1):
|
||||
judge_questions = read_questions_from_judge(judge_file_path, chosen_numbers)
|
||||
judge_consortium = judge_consortium_bidding(baseinfo_list1)
|
||||
@ -138,6 +141,7 @@ def process_judge_questions(judge_file_path, chosen_numbers, tobidders_notice_ta
|
||||
for question, response in res2:
|
||||
baseinfo_list1.append(clean_json_string(response))
|
||||
|
||||
|
||||
def process_baseinfo_list(baseinfo_list, tobidders_notice):
|
||||
questions_list = []
|
||||
for item in baseinfo_list:
|
||||
@ -157,6 +161,7 @@ def process_baseinfo_list(baseinfo_list, tobidders_notice):
|
||||
else:
|
||||
return []
|
||||
|
||||
|
||||
def combine_basic_info(merged_baseinfo_path, tobidders_notice_table, tobidders_notice, clause_path):
|
||||
"""
|
||||
综合和处理基础信息，生成最终的基础信息字典。
|
||||
@ -189,7 +194,8 @@ def combine_basic_info(merged_baseinfo_path,tobidders_notice_table, tobidders_no
|
||||
|
||||
with concurrent.futures.ThreadPoolExecutor(max_workers=2) as executor:
|
||||
# 提交两个任务
|
||||
future1 = executor.submit(process_judge_questions, judge_file_path, chosen_numbers, tobidders_notice_table, baseinfo_list1)
|
||||
future1 = executor.submit(process_judge_questions, judge_file_path, chosen_numbers, tobidders_notice_table,
|
||||
baseinfo_list1)
|
||||
future2 = executor.submit(process_baseinfo_list, baseinfo_list1_copy, tobidders_notice)
|
||||
|
||||
# 等待两个任务完成并获取结果
|
||||
@ -205,6 +211,7 @@ def combine_basic_info(merged_baseinfo_path,tobidders_notice_table, tobidders_no
|
||||
aggregated_baseinfo = aggregate_basic_info_engineering(updated_list)
|
||||
return {"基础信息": aggregated_baseinfo}
|
||||
|
||||
|
||||
# TODO:先不带投标人须知正文，如果是未知，再直接问正文，
|
||||
if __name__ == "__main__":
|
||||
start_time = time.time()
|
||||
@ -217,7 +224,3 @@ if __name__ == "__main__":
|
||||
print(json.dumps(res, ensure_ascii=False, indent=4))
|
||||
end_time = time.time()
|
||||
print("elapsed_time:" + str(end_time - start_time))
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@ -196,7 +196,7 @@ def extract_pages_tobidders_notice(pdf_path, output_folder,begin_pattern, begin_
|
||||
r'^附表(?:一)?[：:]', # Match "附表一" with optional "一" and colon
|
||||
re.MULTILINE
|
||||
)
|
||||
print(f"使用默认的 end_pattern: {end_pattern.pattern}") # 打印默认的 end_pattern
|
||||
# print(f"使用默认的 end_pattern: {end_pattern.pattern}") # 打印默认的 end_pattern
|
||||
|
||||
# 定义基础的 mid_pattern
|
||||
base_mid_pattern = r'^\s*(?:[（(]\s*[一1]?\s*[)）]\s*[、．.]*|[一1][、．.]+|[、．.]+)\s*(说\s*明|总\s*则)'
|
||||
@ -204,9 +204,6 @@ def extract_pages_tobidders_notice(pdf_path, output_folder,begin_pattern, begin_
|
||||
rf'{base_mid_pattern}',
|
||||
re.MULTILINE
|
||||
)
|
||||
print(
|
||||
f"使用默认的 combined_mid_pattern: {combined_mid_pattern.pattern}") # 打印默认的 combined_mid_pattern
|
||||
|
||||
continue
|
||||
|
||||
if start_page is not None and mid_page is None and combined_mid_pattern:
|
||||
@ -306,6 +303,8 @@ def get_start_and_common_header(input_path):
|
||||
begin_pattern = re.compile(r'.*(?:招标公告|投标邀请书|投标邀请函)\s*$',re.MULTILINE)
|
||||
pdf_document = PdfReader(input_path)
|
||||
for i, page in enumerate(pdf_document.pages):
|
||||
if i > 25:
|
||||
return common_header, 0 # 如果页码大于25，直接返回last_begin_index=0
|
||||
text = page.extract_text()
|
||||
if text:
|
||||
cleaned_text = clean_page_content(text, common_header)
|
||||
@ -371,7 +370,7 @@ def truncate_pdf_main(input_path, output_folder, selection):
|
||||
re.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', re.MULTILINE)
|
||||
),
|
||||
(
|
||||
re.compile(r'.*(?:招标公告|投标邀请书|投标邀请函)\s*$', re.MULTILINE),
|
||||
re.compile(r'.*(?:招标公告|投标邀请书|投标邀请函|第一卷)\s*$', re.MULTILINE),
|
||||
re.compile(r".*(?:投标人须知|投标人须知前附表)\s*$", re.MULTILINE)
|
||||
)
|
||||
]
|
||||
@ -381,7 +380,12 @@ def truncate_pdf_main(input_path, output_folder, selection):
|
||||
# Selection 5: 无效标
|
||||
pattern_pairs = [
|
||||
(
|
||||
re.compile(r'第[一二三四五六七八九十]+章\s*(招标公告|.*邀请.*)|第一卷|招标编号:|招标编号：'),
|
||||
re.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).*|^第一卷|^投标邀请书'),
|
||||
re.compile(r'第[一二三四五六七八九十]+章\s*合同|[：:]清标报告|^第二卷', re.MULTILINE)
|
||||
),
|
||||
(
|
||||
re.compile(r'.*(?:招标公告|投标邀请书|投标邀请函|第一卷)\s*$', re.MULTILINE),
|
||||
re.compile(r'第[一二三四五六七八九十]+章\s*合同|[：:]清标报告|^第二卷', re.MULTILINE)
|
||||
)
|
||||
]
|
||||
@ -393,8 +397,14 @@ def truncate_pdf_main(input_path, output_folder, selection):
|
||||
|
||||
for idx, (begin_pattern, end_pattern) in enumerate(pattern_pairs, start=1):
|
||||
is_secondary_match = (idx == 2)
|
||||
begin_page = last_begin_index if last_begin_index != 0 else {
|
||||
1: 3, #前附表
|
||||
2: 10, #评标
|
||||
3: 5, #资格
|
||||
4: 0, #公告
|
||||
5: 0 #无效标
|
||||
}.get(selection, 0)
|
||||
if selection == 1: #投标人须知
|
||||
begin_page = 3
|
||||
output_paths = list(
|
||||
extract_pages_tobidders_notice(input_path,output_folder, begin_pattern, begin_page, common_header))
|
||||
if output_paths and any(os.path.isfile(f) for f in output_paths):
|
||||
@ -402,10 +412,6 @@ def truncate_pdf_main(input_path, output_folder, selection):
|
||||
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 == 2: #评分细则
|
||||
begin_page = 10
|
||||
else:
|
||||
begin_page = last_begin_index
|
||||
output_paths = extract_pages(
|
||||
input_path,
|
||||
output_folder,
|
||||
@ -669,7 +675,7 @@ def truncate_pdf_specific_engineering(pdf_path, output_folder, selections, uniqu
|
||||
#TODO:目前merged_baseinfo没有包含投标人须知正文。
|
||||
#投标人须知前附表改为货物标一样的
|
||||
if __name__ == "__main__":
|
||||
input_path = "C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest8.pdf" # 可以是单个PDF文件路径或文件夹路径 #zbtest20.pdf zbtest4_evaluation_method.pdf zbtest8.pdf
|
||||
input_path = "C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest7.pdf" # 可以是单个PDF文件路径或文件夹路径 #zbtest20.pdf zbtest4_evaluation_method.pdf zbtest8.pdf
|
||||
# input_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\68549b0b-e892-41a9-897c-c3694535ee61\\ztbfile.pdf"
|
||||
# input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\2-招标文件.pdf"
|
||||
output_folder="C:\\Users\\Administrator\\Desktop\\招标文件\\new_test\\新建文件夹"
|
||||
@ -679,5 +685,5 @@ if __name__ == "__main__":
|
||||
# print(files)
|
||||
selection = 5 # 例如：1 - 投标人须知前附表+正文, 2 - 评标办法, 3 -资格审查条件 4-招标公告 5-无效标
|
||||
generated_files = truncate_pdf_main(input_path, output_folder, selection)
|
||||
print(generated_files)
|
||||
|
||||
# print("生成的文件:", generated_files)
|
||||
@ -180,7 +180,7 @@ def convert_clause_to_json(input_path,output_folder,type=1):
|
||||
r'^附(?:录|件|表)(?:一)?[:：]'
|
||||
]
|
||||
else:
|
||||
start_word = r'第[一二三四五六七八九十]+章\s*招标公告|第一卷|招标编号:|招标编号：'
|
||||
start_word = r'第[一二三四五六七八九十]+章\s*招标公告|第一卷|招标编号:|招标编号：|投标邀请书|投标邀请函'
|
||||
end_phrases=[r'第[一二三四五六七八九十]+章\s*投标人须知',r'投标人须知前附表']
|
||||
result = convert_to_json(input_path, start_word, end_phrases) #过滤无关信息
|
||||
# 检查输出文件夹是否存在，如果不存在则创建
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user