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

11.4

Browse Source
This commit is contained in:
zy123 2024-11-05 09:33:18 +08:00
parent 9f2fceb8c2
commit 599915fe29
3 changed files with 32 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
flask_app/general/little_zbparse.py
View File

@ -72,7 +72,7 @@ def little_parse_engineering(output_folder, file_path):
dict: 包含 '基础信息' 的字典。 dict: 包含 '基础信息' 的字典。
""" """
# 截取特定的工程 PDF 文件 # 截取特定的工程 PDF 文件
selections = [ 1,5] #公告+投标人须知前附表 selections = [ 1,4] #公告+投标人须知前附表
files = truncate_pdf_specific_engineering(file_path, output_folder,selections) files = truncate_pdf_specific_engineering(file_path, output_folder,selections)
if not files: if not files:
raise ValueError("未找到截取后的文件。") raise ValueError("未找到截取后的文件。")

20
flask_app/main/截取pdf.py
View File

@ -339,14 +339,14 @@ def truncate_pdf_main(input_path, output_folder, selection):
# Selection 2: 评标办法 # Selection 2: 评标办法
pattern_pairs = [ pattern_pairs = [
( (
re.compile(r'^第[一二三四五六七八九十]+(?:章|部分)\s*(磋商|谈判|评标|评定|评审)'), re.compile(r'^第[一二三四五六七八九十]+(?:章|部分)\s*(磋商|谈判|评标|评定|评审)\s*(办法|方法)'),
# Alternative begin pattern # Alternative begin pattern
re.compile(r'评标办法正文|评标办法|^第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+') re.compile(r'评标办法正文|评标办法|^第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+')
# Alternative end pattern # Alternative end pattern
), ),
( (
re.compile( re.compile(
r'第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff、]*?(磋商|谈判|评标|评定|评审)[\u4e00-\u9fff、]*\s*$|\s*评标(办法|方法)前附表\s*$', r'第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff、]*?(磋商|谈判|评标|评定|评审)\s*(办法|方法)[\u4e00-\u9fff、]*\s*$|\s*评标(办法|方法)前附表\s*$',
re.MULTILINE re.MULTILINE
), ),
re.compile(r'第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+\s*$', re.MULTILINE) re.compile(r'第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+\s*$', re.MULTILINE)
@ -566,18 +566,18 @@ def truncate_pdf_specific_engineering(pdf_path, output_folder, selections, uniqu
# 投标人须知前附表改为货物标一样的 # 投标人须知前附表改为货物标一样的
if __name__ == "__main__": if __name__ == "__main__":
start_time = time.time() start_time = time.time()
input_path = "C:\\Users\\Administrator\\Desktop\\new招标文件\\工程标\\HBDL-2024-0017-001-招标文件.pdf" # input_path = "C:\\Users\\Administrator\\Desktop\\new招标文件\\工程标\\HBDL-2024-0017-001-招标文件.pdf"
# input_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\68549b0b-e892-41a9-897c-c3694535ee61\\ztbfile.pdf" input_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\0b1861e6-c7f6-4541-9182-b1384ba84f3b\\ztbfile.pdf"
# input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\2-招标文件.pdf" # input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\2-招标文件.pdf"
# input_path="C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest1.pdf" # input_path="C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest1.pdf"
output_folder = "C:\\Users\\Administrator\\Desktop\\new招标文件\\招标文件\\tmp" output_folder = "C:\\Users\\Administrator\\Desktop\\fsdownload\\0b1861e6-c7f6-4541-9182-b1384ba84f3b\\tmp"
# files=truncate_pdf_multiple(input_path,output_folder) # files=truncate_pdf_multiple(input_path,output_folder)
# selections = [5, 1] # 仅处理 selection 5、1 selections = [4, 1] # 仅处理 selection 4、1
# files=truncate_pdf_specific_engineering(input_path,output_folder,selections) files=truncate_pdf_specific_engineering(input_path,output_folder,selections)
# print(files) # print(files)
selection = 2 # 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 # selection = 2 # 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) # generated_files = truncate_pdf_main(input_path, output_folder, selection)
print(generated_files) # print(generated_files)
# print("生成的文件:", generated_files) # print("生成的文件:", generated_files)
end_time = time.time() end_time = time.time()
print("耗时：" + str(end_time - start_time)) print("耗时：" + str(end_time - start_time))

32
flask_app/货物标/截取pdf货物标版.py
View File

@ -158,8 +158,18 @@ def get_patterns_for_procurement():
def get_patterns_for_evaluation_method(): def get_patterns_for_evaluation_method():
# begin_pattern = re.compile(
# r'第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]*?(磋商|谈判|评标|评定|评审)\s*(办法|方法)[\u4e00-\u9fff、()（）]*\s*$',
# re.MULTILINE
# )
begin_pattern = re.compile( begin_pattern = re.compile(
r'第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff、]*?(磋商|谈判|评标|评定|评审)[\u4e00-\u9fff、]*\s*$', re.MULTILINE) r'第[一二三四五六七八九1-9]+(?:章|部分)\s*' # 匹配“第X章”或“第X部分”
r'(?:[\u4e00-\u9fff、()（）]*?)' # 匹配允许的字符（中文、顿号、括号）
r'(?=.*(?:磋商|谈判|评标|评定|评审))' # 确保包含“磋商”、“谈判”、“评标”、“评定”或“评审”
r'(?=.*(?:办法|方法))' # 确保包含“办法”或“方法”
r'[\u4e00-\u9fff、()（）]*\s*$', # 继续匹配允许的字符直到行尾
re.MULTILINE
)
end_pattern = re.compile( end_pattern = re.compile(
r'第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+\s*$', re.MULTILINE) r'第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+\s*$', re.MULTILINE)
return begin_pattern, end_pattern return begin_pattern, end_pattern
@ -599,7 +609,7 @@ def process_input(input_path, output_folder, selection, output_suffix):
local_output_suffix = "notice" local_output_suffix = "notice"
elif selection == 2: elif selection == 2:
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)\s*[\u4e00-\u9fff、]*?(磋商|谈判|评标|评定|评审)[\u4e00-\u9fff、]*') r'^第[一二三四五六七八九十百千]+(?:章|部分).*(磋商|谈判|评标|评定|评审|办法|方法).*(磋商|谈判|评标|评定|评审|办法|方法)')
end_pattern = re.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+') end_pattern = re.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+')
local_output_suffix = "evaluation_method" local_output_suffix = "evaluation_method"
elif selection == 3: elif selection == 3:
@ -727,21 +737,21 @@ def truncate_pdf_specific_goods(pdf_path, output_folder, selections,unique_id="1
logger.warning(f"合并失败，没有生成合并文件 for {pdf_path}") logger.warning(f"合并失败，没有生成合并文件 for {pdf_path}")
return truncate_files return truncate_files
#TODO:截取还有问题
# TODO:交通智能系统和招标(1)(1)文件有问题 包头 绍兴 资格审查文件可能不需要默认与"evaluation"同一章 无效投标可能也要考虑 “more”的情况，类似工程标 唐山投标只有正文，没有附表 # TODO:交通智能系统和招标(1)(1)文件有问题 包头 绍兴 资格审查文件可能不需要默认与"evaluation"同一章 无效投标可能也要考虑 “more”的情况，类似工程标 唐山投标只有正文，没有附表
if __name__ == "__main__": if __name__ == "__main__":
# input_path = "C:\\Users\\Administrator\\Desktop\\new招标文件\\货物标\\HBDL-2024-0519-001-招标文件.pdf" input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles"
# input_path = "C:\\Users\\Administrator\\Desktop\\fsdownload\\b151fcd0-4cd8-49b4-8de3-964057a9e653\\ztbfile.pdf" # input_path = "C:\\Users\\Administrator\\Desktop\\fsdownload\\f8b793b5-aa60-42d3-ae59-a3f474e06610\\ztbfile.pdf"
input_path="C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\zbtest4_evaluation_method.pdf" # input_path="C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\zbtest4_evaluation_method.pdf"
# input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\output1\\2-招标文件_procurement.pdf" # input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\output1\\2-招标文件_procurement.pdf"
# input_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\a091d107-805d-4e28-b8b2-0c7327737238\\ztbfile.pdf" # input_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\a091d107-805d-4e28-b8b2-0c7327737238\\ztbfile.pdf"
# output_folder = "C:\\Users\\Administrator\\Desktop\\fsdownload\\a091d107-805d-4e28-b8b2-0c7327737238\\tmp" # output_folder = "C:\\Users\\Administrator\\Desktop\\fsdownload\\a091d107-805d-4e28-b8b2-0c7327737238\\tmp"
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"
# files = truncate_pdf_multiple(input_path, output_folder) # files = truncate_pdf_multiple(input_path, output_folder)
selections = [1,4] # selections = [1,4]
files=truncate_pdf_specific_goods(input_path,output_folder,selections) # files=truncate_pdf_specific_goods(input_path,output_folder,selections)
print(files) # print(files)
# 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 selection = 2# 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(input_path, output_folder, selection) generated_files = truncate_pdf_main(input_path, output_folder, selection)
# print(generated_files) # print(generated_files)