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

截取pdf工程/货物尝试合并

Browse Source
This commit is contained in:
zy123 2025-01-10 09:20:03 +08:00
parent 8aa7875a52
commit 51a8796353
4 changed files with 12 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
flask_app/general/投标人须知正文提取指定内容.py
View File

@ -394,9 +394,9 @@ def extract_from_notice(merged_baseinfo_path, clause_path, type):
final_result = postprocess_formatted2(extracted_data, target_values) final_result = postprocess_formatted2(extracted_data, target_values)
return final_result 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 # # 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) # final_result = get_requirements_with_gpt(merged_baseinfo_path, type)
return final_result # return final_result
except Exception as e: except Exception as e:
print(f"Error occurred while processing clause_path '{clause_path}': {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__": if __name__ == "__main__":
# file_path = 'C:\\Users\\Administrator\\Desktop\\fsdownload\\3bffaa84-2434-4bd0-a8ee-5c234ccd7fa0\\clause1.json' # 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" 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\ec7d5328-9c57-450f-baf4-2e5a6f90ed1d\tmp\clause1.json" clause_path=r"C:\Users\Administrator\Desktop\fsdownload\b29de31a-297e-42cf-b9ba-6859e530a472\clause1.json"
try: 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) res2 = json.dumps(res, ensure_ascii=False, indent=4)
print(res2) print(res2)
except ValueError as e: except ValueError as e:

7
flask_app/general/投标人须知正文条款提取成json文件.py
View File

@ -1,5 +1,4 @@
import re import re
from PyPDF2 import PdfReader from PyPDF2 import PdfReader
from flask_app.货物标.截取pdf货物标版 import clean_page_content,extract_common_header 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') current_content.append('\n')
return append_newline return append_newline
import re
def parse_text_by_heading(text): def parse_text_by_heading(text):
keywords = ['包含', '以下'] keywords = ['包含', '以下']
data = {} data = {}
@ -367,9 +363,6 @@ def parse_text_by_heading(text):
return data return data
def extract_text_from_pdf(file_path, start_word, end_pattern): def extract_text_from_pdf(file_path, start_word, end_pattern):
# 从PDF文件中提取文本 # 从PDF文件中提取文本
common_header = extract_common_header(file_path) common_header = extract_common_header(file_path)

7
flask_app/routes/货物标解析main.py
View File

@ -284,9 +284,10 @@ def goods_bid_main(output_folder, file_path, file_type, unique_id):
#TODO: #TODO:
# 2.废标项这边，考虑大模型+正则并用 # 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 # 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 投标人须知那块结合 # 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__": if __name__ == "__main__":
# 配置日志器 # 配置日志器

4
flask_app/货物标/截取pdf货物标版.py
View File

@ -363,11 +363,11 @@ if __name__ == "__main__":
logger = get_global_logger("123") logger = get_global_logger("123")
# input_path = r"C:\Users\Administrator\Desktop\new招标文件\货物标" # 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\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" # 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" # 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"D:\flask_project\flask_app\static\output\output1\test"
# output_folder = r"C:\Users\Administrator\Desktop\new招标文件\output2" # 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) generated_files = truncate_pdf_main_goods(pdf_path, output_folder, selection,logger)
print(generated_files) print(generated_files)