10.29截取工程标新逻辑
This commit is contained in:
parent
2aaaaa3c02
commit
559d52f03d
@ -10,8 +10,7 @@
|
||||
],
|
||||
"关键字": [
|
||||
"营业执照",
|
||||
"自然人的身份证明",
|
||||
"独立承担民事责任的能力"
|
||||
"自然人的身份证明"
|
||||
]
|
||||
},
|
||||
"开户信息": {
|
||||
@ -117,7 +116,7 @@
|
||||
"施工项目"
|
||||
]
|
||||
},
|
||||
"财务信息(财务审计报告)": {
|
||||
"财务审计报告": {
|
||||
"章节": [
|
||||
"提供依法缴纳税收和社会保障资金的相关材料",
|
||||
"具有依法缴纳税收和社会保障资金的良好记录",
|
||||
@ -134,7 +133,7 @@
|
||||
"财务会计报表"
|
||||
]
|
||||
},
|
||||
"财务信息(缴纳税收证明)": {
|
||||
"缴纳税收证明": {
|
||||
"章节": [
|
||||
"提供依法缴纳税收和社会保障资金的相关材料",
|
||||
"具有依法缴纳税收和社会保障资金的良好记录",
|
||||
@ -151,7 +150,7 @@
|
||||
"税收缴纳证明"
|
||||
]
|
||||
},
|
||||
"财务信息(公司缴纳社保证明)": {
|
||||
"公司缴纳社保证明": {
|
||||
"章节": [
|
||||
"投标人资质证明文件",
|
||||
"按照“供应商资格要求”规定提交的相关证明材料",
|
||||
|
||||
@ -1,12 +1,101 @@
|
||||
# -*- encoding:utf-8 -*-
|
||||
import ast
|
||||
import json
|
||||
import re
|
||||
import os
|
||||
import sys
|
||||
from flask_app.general.多线程提问 import multi_threading
|
||||
from flask_app.general.通义千问long import upload_file
|
||||
from pathlib import Path
|
||||
from openai import OpenAI
|
||||
import concurrent.futures
|
||||
import queue
|
||||
import time
|
||||
|
||||
def qianwen_long(file_id, user_query):
|
||||
print("call qianwen-long...")
|
||||
"""
|
||||
Uses a previously uploaded file to generate a response based on a user query.
|
||||
"""
|
||||
client = OpenAI(
|
||||
api_key=os.getenv("DASHSCOPE_API_KEY"),
|
||||
base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
|
||||
)
|
||||
|
||||
# Generate a response based on the file ID
|
||||
completion = client.chat.completions.create(
|
||||
model="qwen-long",
|
||||
top_p=0.5,
|
||||
temperature=0.4,
|
||||
messages=[
|
||||
{
|
||||
'role': 'system',
|
||||
'content': f'fileid://{file_id}'
|
||||
},
|
||||
{
|
||||
'role': 'user',
|
||||
'content': user_query
|
||||
}
|
||||
],
|
||||
stream=False
|
||||
)
|
||||
|
||||
# Return the response content
|
||||
return completion.choices[0].message.content
|
||||
|
||||
def llm_call(question, knowledge_name,file_id, result_queue, ans_index, llm_type):
|
||||
|
||||
if llm_type==2:
|
||||
print(f"qianwen_long! question:{question}")
|
||||
qianwen_res = qianwen_long(file_id,question)
|
||||
result_queue.put((ans_index,(question,qianwen_res)))
|
||||
return
|
||||
def multi_threading(queries, knowledge_name="", file_id="", llm_type=1):
|
||||
if not queries:
|
||||
return []
|
||||
|
||||
print("多线程提问：starting multi_threading...")
|
||||
result_queue = queue.Queue()
|
||||
|
||||
# 使用 ThreadPoolExecutor 管理线程
|
||||
with concurrent.futures.ThreadPoolExecutor(max_workers=15) as executor:
|
||||
# 逐个提交任务，每提交一个任务后休眠1秒
|
||||
future_to_query = {}
|
||||
for index, query in enumerate(queries):
|
||||
future = executor.submit(llm_call, query, knowledge_name, file_id, result_queue, index, llm_type)
|
||||
future_to_query[future] = index
|
||||
time.sleep(1) # 每提交一个任务后等待1秒
|
||||
|
||||
# 收集每个线程的结果
|
||||
for future in concurrent.futures.as_completed(future_to_query):
|
||||
index = future_to_query[future]
|
||||
try:
|
||||
future.result() # 捕获异常或确认任务完成
|
||||
except Exception as exc:
|
||||
print(f"Query {index} generated an exception: {exc}")
|
||||
# 确保在异常情况下也向 result_queue 添加占位符
|
||||
result_queue.put((index, None))
|
||||
|
||||
# 从队列中获取所有结果并按索引排序
|
||||
results = [None] * len(queries)
|
||||
while not result_queue.empty():
|
||||
index, result = result_queue.get()
|
||||
results[index] = result
|
||||
# 检查是否所有结果都是 None
|
||||
if all(result is None for result in results):
|
||||
return []
|
||||
# 过滤掉None值
|
||||
results = [r for r in results if r is not None]
|
||||
# 返回一个保证是列表的结构
|
||||
return results
|
||||
|
||||
def upload_file(file_path):
|
||||
"""
|
||||
Uploads a file to DashScope and returns the file ID.
|
||||
"""
|
||||
client = OpenAI(
|
||||
api_key=os.getenv("DASHSCOPE_API_KEY"),
|
||||
base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
|
||||
)
|
||||
file = client.files.create(file=Path(file_path), purpose="file-extract")
|
||||
return file.id
|
||||
|
||||
def load_data(json_path):
|
||||
"""
|
||||
@ -47,9 +136,9 @@ def define_target_names():
|
||||
# "劳动合同",
|
||||
"企业证书",
|
||||
"企业业绩",
|
||||
"财务信息(财务审计报告)",
|
||||
"财务信息(缴纳税收证明)",
|
||||
"财务信息(公司缴纳社保证明)"
|
||||
"财务审计报告",
|
||||
"缴纳税收证明",
|
||||
"公司缴纳社保证明"
|
||||
]
|
||||
|
||||
|
||||
@ -65,9 +154,14 @@ def generate_user_query(target, chapters, keywords):
|
||||
Returns:
|
||||
str: 生成的用户查询字符串。
|
||||
"""
|
||||
template3 = f"""这是投标文件模板，作为投标人，我需要把不同的投标材料填充到对应位置，请你根据该文件回答：{target}应该插入在该文件哪个地方？你可能需要查找以下关键词出现的地方：{', '.join([f"'{kw}'" for kw in keywords])}，并确认插入的位置。我已在原文中打上若干待插入位置的标记，形如'[$$第17个可插入位置$$]'，它的标记与它上面的小节内容关联。你需要返回给我{target}应该插入位置的标记序号，即'[$$第17个可插入位置$$]'中的'17'，而不是页码，若有多个位置需要插入，可以返回多个序号，你的回答以数组返回，如[17, 19]，若插入位置不明确，那么返回[-1]。
|
||||
template3 = f"""这是投标文件模板，作为投标人，我需要把不同的投标材料填充到对应位置，请你根据该文件回答：{target}应该插入在该文件哪个地方？你可能需要查找以下关键词出现的地方：{', '.join([f"'{kw}'" for kw in keywords])}，并确认插入的位置。我已在原文中打上若干待插入位置的标记，形如'[$$第5个待插入位置$$]'，它的标记与它上面的小节内容关联。你需要返回给我{target}应该插入位置的标记序号，即'[$$第5个待插入位置$$]'中的'5'，而不是页码，若有多个位置需要插入，可以返回多个序号，你的回答以数组返回，如[17, 19]，若插入位置不明确，那么返回[-1]。
|
||||
"""
|
||||
return template3
|
||||
template2 = f"""你是一个专业撰写投标文件的专家，这是投标文件模板，作为投标人，你需要把不同的投标材料填充到对应位置，请你根据该文件回答：{target}应该插入在该文件哪个地方？你可能需要查找以下关键词出现的地方：{', '.join([f"'{kw}'" for kw in keywords])}，或者根据文中'备注'或'附'内的信息确认插入的位置。目前原文中各章节末尾已打上待插入位置的标记，标记格式为'[$$当前章节名：第x个待插入位置$$]'形如'[$$四、投标保证金：第4个待插入位置$$]'，每个标记与它紧跟着的上面的这一章内容关联。你需要返回给我{target}应该插入位置的标记序号，即'[$$四、投标保证金：第4个待插入位置$$]'中的'4'，而不是当前页码，若有多个位置需要插入，可以返回多个序号，你的回答以数组返回，如[4, 5]，若插入位置不明确，那么返回[-1]。
|
||||
"""
|
||||
template1 = f"""这是投标文件模板，作为投标人，我需要把不同的投标材料填充到对应位置，请你根据该文件回答：{target}应该插入在该文件哪个地方？你可能需要查找以下关键词出现的地方：{', '.join([f"'{kw}'" for kw in keywords])}，并确认插入的位置。我已在原文中各章节末尾打上待插入位置的标记，标记格式为'[$$当前章节名：第x个待插入位置$$]'形如'[$$四、投标保证金：第4个待插入位置$$]'，每个标记与它紧跟着的上面的这一章内容关联。你需要返回给我{target}应该插入位置的标记数字序号，即'[$$四、投标保证金：第4个待插入位置$$]'中的'4'，而不是当前页码，若有多个位置需要插入，可以返回多个序号，你的回答以数组返回，如[4, 5]，若插入位置不明确，那么返回[-1]。
|
||||
"""
|
||||
|
||||
return template1
|
||||
|
||||
|
||||
def generate_user_queries(target_names, data_dict):
|
||||
@ -140,8 +234,8 @@ def main():
|
||||
queries = [item['query'] for item in user_query_list]
|
||||
|
||||
# 定义文件路径
|
||||
format_part = "C:\\Users\\Administrator\\Desktop\\outzb2 (2).pdf"
|
||||
|
||||
format_part = "C:\\Users\\Administrator\\Desktop\\bid_format.pdf"
|
||||
# format_part="C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\新建文件夹\\bid_format.docx"
|
||||
# 检查文件是否存在
|
||||
if not os.path.isfile(format_part):
|
||||
print(f"错误：文件未找到 - {format_part}")
|
||||
@ -165,8 +259,8 @@ def main():
|
||||
baseinfo_list = [process_string_list(res) for _, res in results]
|
||||
|
||||
# 输出结果
|
||||
for info in baseinfo_list:
|
||||
print(f'{target_names}:{info}')
|
||||
for i, info in enumerate(baseinfo_list):
|
||||
print(f'{target_names[i]}:{info}')
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
@ -293,8 +293,8 @@ def truncate_pdf_main(input_path, output_folder, selection,begin_page=10):
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 定义输入和输出路径
|
||||
input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles"
|
||||
# input_path="C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest13.pdf"
|
||||
# input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles"
|
||||
input_path="C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest2.pdf"
|
||||
output_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\新建文件夹"
|
||||
selection = 1 # 1 - 投标文件格式
|
||||
# 执行截取
|
||||
|
||||
@ -1,9 +1,10 @@
|
||||
import re
|
||||
import os
|
||||
from PyPDF2 import PdfReader, PdfWriter
|
||||
import re # 导入正则表达式库
|
||||
import os # 用于文件和文件夹操作
|
||||
from flask_app.general.merge_pdfs import merge_pdfs
|
||||
import concurrent.futures
|
||||
import logging
|
||||
|
||||
def get_global_logger(unique_id):
|
||||
if unique_id is None:
|
||||
return logging.getLogger() # 获取默认的日志器
|
||||
@ -11,6 +12,7 @@ def get_global_logger(unique_id):
|
||||
return logger
|
||||
|
||||
logger = None
|
||||
|
||||
def clean_page_content(text, common_header):
|
||||
# 首先删除抬头公共部分
|
||||
if common_header: # 确保有公共抬头才进行替换
|
||||
@ -26,10 +28,7 @@ def clean_page_content(text, common_header):
|
||||
text = re.sub(r'\s*[—-]\s*\d+\s*[—-]\s*', '', text) # 删除形如 '—2—' 或 '-2-' 的页码
|
||||
return text
|
||||
|
||||
#PYPDF2库
|
||||
def extract_common_header(pdf_path):
|
||||
from PyPDF2 import PdfReader
|
||||
|
||||
pdf_document = PdfReader(pdf_path)
|
||||
headers = []
|
||||
total_pages = len(pdf_document.pages)
|
||||
@ -66,22 +65,7 @@ def extract_common_header(pdf_path):
|
||||
|
||||
return '\n'.join(common_headers)
|
||||
|
||||
|
||||
def save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page, common_header):
|
||||
"""
|
||||
从原始PDF截取指定范围的页面并保存到新的PDF文件中。
|
||||
如果 output_suffix 是 'notice'，则额外保存 start_page 之前的页面。
|
||||
|
||||
参数:
|
||||
pdf_path (str): 原始PDF文件路径。
|
||||
output_folder (str): 输出文件夹路径。
|
||||
output_suffix (str): 输出文件的后缀，用于区分不同的提取。
|
||||
start_page (int): 起始页码（0基）。
|
||||
end_page (int): 结束页码（0基）。
|
||||
|
||||
返回:
|
||||
str: 保存的PDF文件路径。如果提取失败，返回空字符串。
|
||||
"""
|
||||
try:
|
||||
# 获取文件基本名称
|
||||
base_file_name = os.path.splitext(os.path.basename(pdf_path))[0]
|
||||
@ -138,8 +122,288 @@ def save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, en
|
||||
print(f"Error in save_pages_to_new_pdf: {e}")
|
||||
return "" # 返回空字符串
|
||||
|
||||
def extract_pages_tobidders_notice(pdf_document, begin_pattern, begin_page, common_header, exclusion_pattern):
|
||||
def run_extraction():
|
||||
start_page = None
|
||||
mid_page = None
|
||||
end_page = None
|
||||
chapter_type = None # 用于存储“章”或“部分”
|
||||
|
||||
for i, page in enumerate(pdf_document.pages):
|
||||
text = page.extract_text() or ""
|
||||
cleaned_text = clean_page_content(text, common_header)
|
||||
|
||||
if exclusion_pattern and re.search(exclusion_pattern, cleaned_text) and mid_page is not None:
|
||||
continue
|
||||
|
||||
if start_page is None:
|
||||
match = re.search(begin_pattern, cleaned_text)
|
||||
if match and i > begin_page:
|
||||
start_page = i
|
||||
matched_text = match.group(0) # 获取整个匹配的文本
|
||||
if '章' in matched_text:
|
||||
chapter_type = '章'
|
||||
elif '部分' in matched_text:
|
||||
chapter_type = '部分'
|
||||
else:
|
||||
chapter_type = None # 未匹配到“章”或“部分”
|
||||
|
||||
if chapter_type:
|
||||
# 根据 chapter_type 动态生成 end_pattern
|
||||
end_pattern = re.compile(
|
||||
rf'^第[一二三四五六七八九十百千]+?(?:{chapter_type})\s*[\u4e00-\u9fff]+',
|
||||
re.MULTILINE
|
||||
)
|
||||
# print(f"动态生成的 end_pattern: {end_pattern.pattern}") # 打印生成的 end_pattern
|
||||
|
||||
# 根据 chapter_type 动态生成 additional_mid_pattern
|
||||
if chapter_type == '章':
|
||||
additional_mid_pattern = r'^第[一二三四五六七八九十百千]+?(?:部分)'
|
||||
elif chapter_type == '部分':
|
||||
additional_mid_pattern = r'^第[一二三四五六七八九十百千]+?(?:章)'
|
||||
else:
|
||||
additional_mid_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)'
|
||||
|
||||
# 合并基础模式和额外模式
|
||||
if additional_mid_pattern:
|
||||
combined_mid_pattern = re.compile(
|
||||
rf'(?:{base_mid_pattern})|(?:{additional_mid_pattern})',
|
||||
re.MULTILINE
|
||||
)
|
||||
else:
|
||||
combined_mid_pattern = re.compile(
|
||||
rf'{base_mid_pattern}',
|
||||
re.MULTILINE
|
||||
)
|
||||
# print(f"生成的 combined_mid_pattern: {combined_mid_pattern.pattern}") # 打印 combined_mid_pattern
|
||||
else:
|
||||
# 如果未匹配到“章”或“部分”，使用默认的 end_pattern 和 mid_pattern
|
||||
end_pattern = re.compile(
|
||||
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+',
|
||||
re.MULTILINE
|
||||
)
|
||||
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)'
|
||||
combined_mid_pattern = re.compile(
|
||||
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:
|
||||
if re.search(combined_mid_pattern, cleaned_text):
|
||||
mid_page = i
|
||||
if start_page is not None and mid_page is not None and chapter_type:
|
||||
if re.search(end_pattern, cleaned_text):
|
||||
if mid_page is None:
|
||||
if i > start_page:
|
||||
end_page = i
|
||||
break
|
||||
else:
|
||||
if i > mid_page:
|
||||
end_page = i
|
||||
break
|
||||
|
||||
return start_page, mid_page, end_page
|
||||
|
||||
# 运行提取
|
||||
start_page, mid_page, end_page = run_extraction()
|
||||
|
||||
return start_page, mid_page, end_page
|
||||
|
||||
def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
|
||||
# 打开PDF文件
|
||||
common_header = extract_common_header(pdf_path)
|
||||
pdf_document = PdfReader(pdf_path)
|
||||
start_page = None
|
||||
end_page = None
|
||||
|
||||
# 遍历文档的每一页，查找开始和结束短语的位置
|
||||
for i in range(len(pdf_document.pages)):
|
||||
page = pdf_document.pages[i]
|
||||
text = page.extract_text()
|
||||
if text:
|
||||
cleaned_text = clean_page_content(text, common_header)
|
||||
if re.search(begin_pattern, cleaned_text) and i > begin_page:
|
||||
if output_suffix == "invalid" and start_page:
|
||||
continue
|
||||
else:
|
||||
start_page = i
|
||||
if start_page is not None and re.search(end_pattern, cleaned_text):
|
||||
condition = i > start_page
|
||||
if condition:
|
||||
is_invalid_condition = output_suffix == "invalid" and i > 30 # 这边默认无效投标至少有30页
|
||||
if is_invalid_condition or output_suffix != "invalid":
|
||||
end_page = i
|
||||
break # 找到结束页后退出循环
|
||||
|
||||
# 移除对 extract_pages_twice 的调用
|
||||
if start_page is None or end_page is None:
|
||||
print(f"{output_suffix} first: 未找到起始或结束页在文件 {pdf_path} 中！")
|
||||
return []
|
||||
else:
|
||||
return save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page, common_header)
|
||||
|
||||
def process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
|
||||
# 确保输出文件夹存在
|
||||
if not os.path.exists(output_folder):
|
||||
os.makedirs(output_folder)
|
||||
if os.path.isdir(input_path):
|
||||
generated_files = []
|
||||
# 遍历文件夹内的所有PDF文件
|
||||
for file in os.listdir(input_path):
|
||||
if file.endswith(".pdf"):
|
||||
pdf_path = os.path.join(input_path, file)
|
||||
output_pdf_path = extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix)
|
||||
if output_pdf_path and os.path.isfile(output_pdf_path):
|
||||
generated_files.append(output_pdf_path)
|
||||
return generated_files
|
||||
elif os.path.isfile(input_path) and input_path.endswith(".pdf"):
|
||||
# 处理单个PDF文件
|
||||
output_pdf_path = extract_pages(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix)
|
||||
if output_pdf_path and os.path.isfile(output_pdf_path):
|
||||
return [output_pdf_path] # 以列表形式返回，以保持一致性
|
||||
else:
|
||||
print("提供的路径既不是文件夹也不是PDF文件。")
|
||||
return []
|
||||
|
||||
|
||||
def truncate_pdf_main(input_path, output_folder, selection):
|
||||
# Define a list to hold all possible (begin_pattern, end_pattern) pairs for the given selection
|
||||
pattern_pairs = []
|
||||
output_suffix = ""
|
||||
|
||||
# Define pattern pairs for each selection
|
||||
if selection == 1:
|
||||
# Selection 1: 投标人须知前附表
|
||||
pattern_pairs = [
|
||||
(
|
||||
re.compile(r'第[一二三四五六七八九十]+章\s*投标人须知'),
|
||||
re.compile(
|
||||
r'第[一二三四五六七八九十]+章\s*评标办法|^评标办法前附表|^附录(?:一)?[：:]|^附件(?:一)?[：:]|^附表(?:一)?[：:]',
|
||||
re.MULTILINE)
|
||||
)
|
||||
]
|
||||
output_suffix = "tobidders_notice_table"
|
||||
|
||||
elif selection == 2:
|
||||
# Selection 2: 评标办法
|
||||
pattern_pairs = [
|
||||
(
|
||||
re.compile(r'^第[一二三四五六七八九十]+章\s*评标办法'),
|
||||
re.compile(r'^评标办法正文|评标办法')
|
||||
),
|
||||
(
|
||||
re.compile(r'第[一二三四五六七八九十]+章\s*评标办法'), # Alternative begin pattern
|
||||
re.compile(r'评标办法正文|评标办法') # Alternative end pattern
|
||||
)
|
||||
]
|
||||
output_suffix = "evaluation_method"
|
||||
|
||||
elif selection == 3:
|
||||
# Selection 3: 投标人须知正文
|
||||
pattern_pairs = [
|
||||
(
|
||||
re.compile(r'投标人须知正文'),
|
||||
re.compile(
|
||||
r'^第[一二三四五六七八九十]+章\s*评标办法|^评标办法前附表|^附录(?:一)?[：:]|^附件(?:一)?[：:]|^附表(?:一)?[：:]',
|
||||
re.MULTILINE)
|
||||
)
|
||||
]
|
||||
output_suffix = "tobidders_notice"
|
||||
|
||||
elif selection == 4:
|
||||
# Selection 4: 资格审查条件
|
||||
pattern_pairs = [
|
||||
(
|
||||
re.compile(r'^(?:附录(?:一)?[：:]|附件(?:一)?[：:]|附表(?:一)?[：:]).*(?:资质|能力|信誉).*$',
|
||||
re.MULTILINE),
|
||||
re.compile(
|
||||
r'^(?:附录(?:一)?[：:]|附件(?:一)?[：:]|附表(?:一)?[：:])(?!.*(?:资质|能力|信誉)).*$|' # Exclude specific terms
|
||||
r'^(第[一二三四五六七八九十]+章\s*评标办法|评标办法前附表)', # Additional end patterns
|
||||
re.MULTILINE
|
||||
)
|
||||
)
|
||||
]
|
||||
output_suffix = "qualification"
|
||||
|
||||
elif selection == 5:
|
||||
# Selection 5: 招标公告
|
||||
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|^投标邀请书'),
|
||||
re.compile(r'第[一二三四五六七八九十]+章\s*投标人须知')
|
||||
)
|
||||
]
|
||||
output_suffix = "notice"
|
||||
|
||||
elif selection == 6:
|
||||
# Selection 6: 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]+章\s*合同|[：:]清标报告|^第二卷', re.MULTILINE)
|
||||
)
|
||||
]
|
||||
output_suffix = "invalid"
|
||||
|
||||
else:
|
||||
print("无效的选择:请选择1-6")
|
||||
return [""]
|
||||
|
||||
# Iterate through each pattern pair and attempt extraction
|
||||
for idx, (begin_pattern, end_pattern) in enumerate(pattern_pairs, start=1):
|
||||
print(f"Selection {selection}: 尝试使用模式对 {idx}/{len(pattern_pairs)}")
|
||||
# Determine begin_page based on selection
|
||||
if selection == 1:
|
||||
begin_page = 3
|
||||
elif selection == 2:
|
||||
begin_page = 10
|
||||
elif selection in [3, 4]:
|
||||
begin_page = 5
|
||||
else:
|
||||
begin_page = 0
|
||||
if selection == 1:
|
||||
output_paths=extract_pages_tobidders_notice()
|
||||
output_paths = process_input(
|
||||
input_path,
|
||||
output_folder,
|
||||
begin_pattern,
|
||||
begin_page=begin_page,
|
||||
end_pattern=end_pattern,
|
||||
output_suffix=output_suffix
|
||||
)
|
||||
|
||||
# Check if extraction was successful
|
||||
if output_paths and any(os.path.isfile(f) for f in output_paths):
|
||||
print(f"Selection {selection}: 使用模式对 {idx} 成功提取。")
|
||||
return output_paths # Return immediately upon successful extraction
|
||||
else:
|
||||
print(f"Selection {selection}: 使用模式对 {idx} 失败。尝试下一个模式对。")
|
||||
|
||||
# If all pattern pairs failed, attempt a fallback
|
||||
print(f"Selection {selection}: 所有模式对都未匹配成功。尝试执行 extract_pages_twice 或返回空。")
|
||||
fallback_result = extract_pages_twice(input_path, output_folder, output_suffix)
|
||||
if fallback_result and any(os.path.isfile(f) for f in fallback_result):
|
||||
return fallback_result
|
||||
else:
|
||||
print(f"{output_suffix} first: 未找到起始或结束页在文件 {input_path} 中！")
|
||||
return ['']
|
||||
|
||||
def extract_pages_twice(pdf_path, output_folder, output_suffix):
|
||||
"""
|
||||
处理 PDF 文件，作为 truncate_pdf_main 的后备方法。
|
||||
此函数将在所有模式对都失败后调用。
|
||||
"""
|
||||
try:
|
||||
common_header = extract_common_header(pdf_path)
|
||||
last_begin_index = 0
|
||||
begin_pattern = re.compile(r'第[一二三四五六七八九十]+章\s*招标公告|第一卷|投标邀请书')
|
||||
@ -148,15 +412,14 @@ def extract_pages_twice(pdf_path, output_folder, output_suffix):
|
||||
text = page.extract_text()
|
||||
if text:
|
||||
cleaned_text = clean_page_content(text, common_header)
|
||||
# 检查“第一章”开始的位置
|
||||
if begin_pattern.search(cleaned_text):
|
||||
last_begin_index = i # 更新最后匹配的索引，页码从0开始
|
||||
|
||||
if output_suffix == "qualification":
|
||||
common_pattern = r'^(?:附录(?:一)?[：:]|附件(?:一)?[：:]|附表(?:一)?[：:])'
|
||||
# end_pattern = r'^(第[一二三四五六七八九十]+章\s*投标人须知|评标办法|评标办法前附表)'
|
||||
end_pattern = re.compile(
|
||||
common_pattern + r'(?!.*(?:资质|能力|信誉)).*$|' # 排除资质、能力、信誉的描述
|
||||
r'^(第[一二三四五六七八九十]+章\s*评标办法|评标办法前附表|投标人须知)', # 新增的匹配项
|
||||
r'^(第[一二三四五六七八九十]+章\s*评标办法|评标办法前附表|投标人须知)',
|
||||
re.MULTILINE
|
||||
)
|
||||
start_page = None
|
||||
@ -180,7 +443,7 @@ def extract_pages_twice(pdf_path, output_folder, output_suffix):
|
||||
|
||||
if start_page is None or end_page is None:
|
||||
print(f"{output_suffix} twice: 未找到起始或结束页在文件 {pdf_path} 中！")
|
||||
return ""
|
||||
return []
|
||||
else:
|
||||
return save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page, common_header)
|
||||
elif output_suffix == "invalid":
|
||||
@ -191,137 +454,12 @@ def extract_pages_twice(pdf_path, output_folder, output_suffix):
|
||||
start_page = last_begin_index
|
||||
end_page = min(90, total)
|
||||
return save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page, common_header)
|
||||
|
||||
|
||||
def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
|
||||
common_header=extract_common_header(pdf_path)
|
||||
# 打开PDF文件
|
||||
pdf_document = PdfReader(pdf_path)
|
||||
start_page = None
|
||||
end_page = None
|
||||
# 遍历文档的每一页，查找开始和结束短语的位置
|
||||
for i in range(len(pdf_document.pages)):
|
||||
page = pdf_document.pages[i]
|
||||
text = page.extract_text()
|
||||
if text:
|
||||
cleaned_text = clean_page_content(text,common_header)
|
||||
# print(cleaned_text)
|
||||
if re.search(begin_pattern, cleaned_text) and i > begin_page:
|
||||
if output_suffix == "invalid" and start_page: # 仅当提取Invalid的时候，判断初始页码是第一个匹配到的页码，因为招标编号可能存在多个，后面的覆盖前面
|
||||
continue
|
||||
else:
|
||||
start_page = i
|
||||
if start_page is not None and re.search(end_pattern, cleaned_text):
|
||||
# 如果output_suffix是"qualification"，调整条件检查
|
||||
condition = i > start_page
|
||||
if condition:
|
||||
is_invalid_condition = output_suffix == "invalid" and i > 30 # 这边默认无效投标至少有30页
|
||||
if is_invalid_condition or output_suffix != "invalid":
|
||||
end_page = i
|
||||
break
|
||||
|
||||
# 确保找到了起始和结束页面
|
||||
if start_page is None or end_page is None:
|
||||
if output_suffix == "qualification" or output_suffix =="invalid":
|
||||
return extract_pages_twice(pdf_path, output_folder, output_suffix)
|
||||
else:
|
||||
print(f"{output_suffix} first: 未找到起始或结束页在文件 {pdf_path} 中！")
|
||||
return ""
|
||||
else:
|
||||
return save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page,common_header)
|
||||
|
||||
|
||||
def process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
|
||||
# 确保输出文件夹存在
|
||||
if not os.path.exists(output_folder):
|
||||
os.makedirs(output_folder)
|
||||
if os.path.isdir(input_path):
|
||||
generated_files = []
|
||||
# 遍历文件夹内的所有PDF文件
|
||||
for file in os.listdir(input_path):
|
||||
if file.endswith(".pdf"):
|
||||
pdf_path = os.path.join(input_path, file)
|
||||
output_pdf_path = extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern,
|
||||
output_suffix)
|
||||
if output_pdf_path and os.path.isfile(output_pdf_path):
|
||||
generated_files.append(output_pdf_path)
|
||||
return generated_files
|
||||
elif os.path.isfile(input_path) and input_path.endswith(".pdf"):
|
||||
# 处理单个PDF文件
|
||||
output_pdf_path = extract_pages(input_path, output_folder, begin_pattern, begin_page, end_pattern,
|
||||
output_suffix)
|
||||
if output_pdf_path and os.path.isfile(output_pdf_path):
|
||||
return [output_pdf_path] # 以列表形式返回，以保持一致性
|
||||
else:
|
||||
print("提供的路径既不是文件夹也不是PDF文件。")
|
||||
print(f"{output_suffix} twice: 未定义的输出后缀。")
|
||||
return []
|
||||
|
||||
def truncate_pdf_main(input_path, output_folder, selection):
|
||||
try:
|
||||
if selection == 1:
|
||||
# Configure patterns and phrases for "投标人须知前附表"
|
||||
begin_pattern = re.compile(r'第[一二三四五六七八九十]+章\s*投标人须知')
|
||||
begin_page = 3
|
||||
end_pattern = re.compile(r'投标人须知正文')
|
||||
output_suffix = "tobidders_notice_table"
|
||||
elif selection == 2:
|
||||
# Configure patterns and phrases for "评标办法"
|
||||
begin_pattern = re.compile(
|
||||
r'第[一二三四五六七八九十]+章\s*评标办法') # 考虑到这种情况 '第三章 第三章 第三章 第三章 评标办法 评标办法 评标办法 评标办法'
|
||||
begin_page = 10
|
||||
end_pattern = re.compile(r'评标办法正文|评标办法')
|
||||
output_suffix = "evaluation_method"
|
||||
elif selection == 3:
|
||||
# Configure patterns and phrases for "投标人须知正文"
|
||||
begin_pattern = re.compile(r'投标人须知正文')
|
||||
begin_page = 5
|
||||
end_pattern = re.compile(
|
||||
r'^第[一二三四五六七八九十]+章\s*评标办法|^评标办法前附表|^附录(?:一)?[：:]|^附件(?:一)?[：:]|^附表(?:一)?[：:]',
|
||||
re.MULTILINE)
|
||||
output_suffix = "tobidders_notice"
|
||||
elif selection == 4:
|
||||
# 配置用于 "资格审查条件" 的正则表达式模式和短语
|
||||
common_pattern = r'^(?:附录(?:一)?[：:]|附件(?:一)?[：:]|附表(?:一)?[：:])'
|
||||
begin_pattern = re.compile(common_pattern + r'.*(?:资质|能力|信誉).*$', re.MULTILINE)
|
||||
begin_page = 5
|
||||
end_pattern = re.compile(
|
||||
common_pattern + r'(?!.*(?:资质|能力|信誉)).*$|' # 原有的模式
|
||||
r'^(第[一二三四五六七八九十]+章\s*评标办法|评标办法前附表)', # 新增的匹配项
|
||||
re.MULTILINE
|
||||
)
|
||||
output_suffix = "qualification"
|
||||
elif selection == 5:
|
||||
# 配置用于 "招标公告" 的正则表达式模式和短语
|
||||
begin_pattern = 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|^投标邀请书')
|
||||
begin_page = 0
|
||||
end_pattern = re.compile(r'第[一二三四五六七八九十]+章\s*投标人须知')
|
||||
output_suffix = "notice"
|
||||
elif selection == 6:
|
||||
# 配置用于 "无效标" 的正则表达式模式和短语
|
||||
begin_pattern = 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：')
|
||||
begin_page = 0
|
||||
end_pattern = 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)
|
||||
output_suffix = "invalid"
|
||||
else:
|
||||
print("无效的选择:请选择1-6")
|
||||
return [""]
|
||||
# 调用 process_input 进行截取
|
||||
output_paths = process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix)
|
||||
if not output_paths:
|
||||
return [""] # 截取失败时返回空字符串
|
||||
return output_paths
|
||||
except Exception as e:
|
||||
print(f"Error in truncate_pdf_main for selection {selection}: {e}")
|
||||
return [""] # 捕获异常时返回空字符串
|
||||
|
||||
|
||||
|
||||
def truncate_pdf_multiple_old(input_path, output_folder):
|
||||
truncate_files = []
|
||||
for selection in range(1, 5):
|
||||
files = truncate_pdf_main(input_path, output_folder, selection)
|
||||
truncate_files.extend(files)
|
||||
return truncate_files
|
||||
print(f"Error in extract_pages_twice: {e}")
|
||||
return []
|
||||
|
||||
def merge_selected_pdfs(output_folder, truncate_files, output_path, base_file_name):
|
||||
"""
|
||||
@ -399,7 +537,6 @@ def merge_selected_pdfs(output_folder, truncate_files, output_path, base_file_na
|
||||
print(f"合并 PDF 文件时出错: {e}")
|
||||
return ""
|
||||
|
||||
|
||||
def truncate_pdf_multiple(input_path, output_folder, unique_id="123"):
|
||||
"""
|
||||
处理 PDF 文件，选择 selection 1-6 的部分，并合并结果。
|
||||
@ -453,7 +590,6 @@ def truncate_pdf_multiple(input_path, output_folder, unique_id="123"):
|
||||
|
||||
return truncate_files
|
||||
|
||||
|
||||
def truncate_pdf_specific_engineering(pdf_path, output_folder, selections, unique_id="123"):
|
||||
"""
|
||||
处理 PDF 文件，选择指定的 selections，并合并结果。
|
||||
@ -514,19 +650,19 @@ def truncate_pdf_specific_engineering(pdf_path, output_folder, selections, uniqu
|
||||
logger.error(f"Error in truncate_pdf_specific_engineering: {e}")
|
||||
return [""] * len(selections) # 返回与 selections 数量相同的空字符串列表
|
||||
|
||||
|
||||
# TODO:需要完善二次请求。目前invalid一定能返回 前附表 须知正文如果为空的话要额外处理一下，比如说就不进行跳转（见xx表） 开评定标这里也要考虑 如果评分表为空，也要处理。
|
||||
#TODO:zbtest8 zbtest18有问题 后期需要完善，截取需要截两次，第一次严格第二次宽松
|
||||
#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\\zbtest4_evaluation_method.pdf" # 可以是单个PDF文件路径或文件夹路径
|
||||
input_path = "C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest3.pdf" # 可以是单个PDF文件路径或文件夹路径
|
||||
# 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\\output6"
|
||||
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 和 3
|
||||
# files=truncate_pdf_specific_engineering(input_path,output_folder,selections)
|
||||
print(files)
|
||||
# selection = 6 # 例如：1 - 投标人须知前附表, 2 - 评标办法, 3 - 投标人须知正文 4-资格审查条件 5-招标公告 6-无效标
|
||||
# generated_files = truncate_pdf_main(input_path, output_folder, selection)
|
||||
# print(files)
|
||||
selection = 1 # 例如：1 - 投标人须知前附表, 2 - 评标办法, 3 - 投标人须知正文 4-资格审查条件 5-招标公告 6-无效标
|
||||
generated_files = truncate_pdf_main(input_path, output_folder, selection)
|
||||
# print(generated_files)
|
||||
# print("生成的文件:", generated_files)
|
||||
532
flask_app/main/截取pdf_old.py
Normal file
532
flask_app/main/截取pdf_old.py
Normal file
@ -0,0 +1,532 @@
|
||||
from PyPDF2 import PdfReader, PdfWriter
|
||||
import re # 导入正则表达式库
|
||||
import os # 用于文件和文件夹操作
|
||||
from flask_app.general.merge_pdfs import merge_pdfs
|
||||
import concurrent.futures
|
||||
import logging
|
||||
def get_global_logger(unique_id):
|
||||
if unique_id is None:
|
||||
return logging.getLogger() # 获取默认的日志器
|
||||
logger = logging.getLogger(unique_id)
|
||||
return logger
|
||||
|
||||
logger=None
|
||||
def clean_page_content(text, common_header):
|
||||
# 首先删除抬头公共部分
|
||||
if common_header: # 确保有公共抬头才进行替换
|
||||
for header_line in common_header.split('\n'):
|
||||
if header_line.strip(): # 只处理非空行
|
||||
# 替换首次出现的完整行
|
||||
text = re.sub(r'^' + re.escape(header_line.strip()) + r'\n?', '', text, count=1)
|
||||
|
||||
# 删除页码 eg:89/129 这个代码分三步走可以把89/129完全删除
|
||||
text = re.sub(r'^\s*\d+\s*(?=\D)', '', text) # 删除开头的页码，仅当紧跟非数字字符时
|
||||
text = re.sub(r'\s+\d+\s*$', '', text) # 删除结尾的页码
|
||||
text = re.sub(r'\s*\/\s*\d+\s*', '', text) # 删除形如 /129 的页码
|
||||
text = re.sub(r'\s*[—-]\s*\d+\s*[—-]\s*', '', text) # 删除形如 '—2—' 或 '-2-' 的页码
|
||||
return text
|
||||
|
||||
#PYPDF2库
|
||||
def extract_common_header(pdf_path):
|
||||
from PyPDF2 import PdfReader
|
||||
|
||||
pdf_document = PdfReader(pdf_path)
|
||||
headers = []
|
||||
total_pages = len(pdf_document.pages)
|
||||
|
||||
# 确定要读取的页数和起始页
|
||||
if total_pages == 2:
|
||||
pages_to_read = 2
|
||||
start_page = 0
|
||||
else:
|
||||
pages_to_read = 3
|
||||
middle_page = total_pages // 2
|
||||
start_page = max(0, middle_page - 1)
|
||||
|
||||
for i in range(start_page, min(start_page + pages_to_read, total_pages)):
|
||||
page = pdf_document.pages[i]
|
||||
text = page.extract_text() or ""
|
||||
if text:
|
||||
# 只取每页的前三行
|
||||
first_lines = text.strip().split('\n')[:3]
|
||||
headers.append(first_lines)
|
||||
|
||||
if len(headers) < 2:
|
||||
return "" # 如果没有足够的页来比较，返回空字符串
|
||||
|
||||
# 寻找每一行中的公共部分，按顺序保留
|
||||
common_headers = []
|
||||
for lines in zip(*headers):
|
||||
# 提取第一行的词汇顺序
|
||||
first_words = lines[0].split()
|
||||
# 筛选所有页面都包含的词汇，保持顺序
|
||||
common_line = [word for word in first_words if all(word in line.split() for line in lines[1:])]
|
||||
if common_line:
|
||||
common_headers.append(' '.join(common_line))
|
||||
|
||||
return '\n'.join(common_headers)
|
||||
|
||||
|
||||
def save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page,common_header):
|
||||
"""
|
||||
从原始PDF截取指定范围的页面并保存到新的PDF文件中。
|
||||
如果 output_suffix 是 'notice'，则额外保存 start_page 之前的页面。
|
||||
|
||||
参数:
|
||||
pdf_path (str): 原始PDF文件路径。
|
||||
output_folder (str): 输出文件夹路径。
|
||||
output_suffix (str): 输出文件的后缀，用于区分不同的提取。
|
||||
start_page (int): 起始页码（0基）。
|
||||
end_page (int): 结束页码（0基）。
|
||||
|
||||
返回:
|
||||
str: 保存的PDF文件路径。如果提取失败，返回空字符串。
|
||||
"""
|
||||
try:
|
||||
# 获取文件基本名称
|
||||
base_file_name = os.path.splitext(os.path.basename(pdf_path))[0]
|
||||
|
||||
# 构建主要输出文件路径
|
||||
output_pdf_path = os.path.join(output_folder, f"{base_file_name}_{output_suffix}.pdf")
|
||||
|
||||
# 读取PDF文件
|
||||
pdf_document = PdfReader(pdf_path)
|
||||
total_pages = len(pdf_document.pages)
|
||||
|
||||
# 检查起始和结束页码是否有效
|
||||
if start_page < 0 or end_page >= total_pages or start_page > end_page:
|
||||
print(f"无效的页面范围: {start_page} 到 {end_page}")
|
||||
return ""
|
||||
|
||||
# 如果 output_suffix 是 'notice'，保存 start_page 之前的页面(若遇到'目录'，则截取到'目录')
|
||||
if output_suffix == 'notice' and start_page > 0:
|
||||
before_pdf_path = os.path.join(output_folder, f"{base_file_name}_before.pdf")
|
||||
before_doc = PdfWriter()
|
||||
toc_page = -1
|
||||
|
||||
# 查找目录页
|
||||
for page_num in range(min(start_page, total_pages)):
|
||||
page_text = pdf_document.pages[page_num].extract_text()
|
||||
cleaned_text = clean_page_content(page_text, common_header)
|
||||
if re.search(r'目\s*录', cleaned_text, re.MULTILINE):
|
||||
toc_page = page_num
|
||||
break
|
||||
|
||||
# 确定截取的页数
|
||||
pages_to_extract = toc_page + 1 if toc_page != -1 else start_page
|
||||
|
||||
# 提取页面
|
||||
for page_num in range(pages_to_extract):
|
||||
before_doc.add_page(pdf_document.pages[page_num])
|
||||
with open(before_pdf_path, 'wb') as f_before:
|
||||
before_doc.write(f_before)
|
||||
print(f"已保存页面从 0 到 {pages_to_extract} 为 {before_pdf_path}")
|
||||
|
||||
# 提取指定范围的页面
|
||||
output_doc = PdfWriter()
|
||||
for page_num in range(start_page, end_page + 1):
|
||||
output_doc.add_page(pdf_document.pages[page_num])
|
||||
|
||||
# 保存新的PDF文件
|
||||
with open(output_pdf_path, 'wb') as f_output:
|
||||
output_doc.write(f_output)
|
||||
|
||||
print(f"{output_suffix} 已截取并保存页面从 {start_page + 1} 到 {end_page + 1} 为 {output_pdf_path}")
|
||||
return output_pdf_path
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error in save_pages_to_new_pdf: {e}")
|
||||
return "" # 返回空字符串
|
||||
|
||||
|
||||
def extract_pages_twice(pdf_path, output_folder, output_suffix):
|
||||
common_header = extract_common_header(pdf_path)
|
||||
last_begin_index = 0
|
||||
begin_pattern = re.compile(r'第[一二三四五六七八九十]+章\s*招标公告|第一卷|投标邀请书')
|
||||
pdf_document = PdfReader(pdf_path)
|
||||
for i, page in enumerate(pdf_document.pages):
|
||||
text = page.extract_text()
|
||||
if text:
|
||||
cleaned_text = clean_page_content(text,common_header)
|
||||
# 检查“第一章”开始的位置
|
||||
if begin_pattern.search(cleaned_text):
|
||||
last_begin_index = i # 更新最后匹配的索引，页码从0开始
|
||||
if output_suffix == "qualification":
|
||||
common_pattern = r'^(?:附录(?:一)?[：:]|附件(?:一)?[：:]|附表(?:一)?[：:])'
|
||||
# end_pattern = r'^(第[一二三四五六七八九十]+章\s*投标人须知|评标办法|评标办法前附表)'
|
||||
end_pattern = re.compile(
|
||||
common_pattern + r'(?!.*(?:资质|能力|信誉)).*$|' # 排除资质、能力、信誉的描述
|
||||
r'^(第[一二三四五六七八九十]+章\s*评标办法|评标办法前附表|投标人须知)', # 新增的匹配项
|
||||
re.MULTILINE
|
||||
)
|
||||
start_page = None
|
||||
end_page = None
|
||||
|
||||
# 从章节开始后的位置进行检查
|
||||
for i, page in enumerate(pdf_document.pages[last_begin_index:], start=last_begin_index):
|
||||
text = page.extract_text()
|
||||
if text:
|
||||
cleaned_text = clean_page_content(text,common_header)
|
||||
# 确定起始页，需在last_begin_index之后
|
||||
if ("资格审查" in cleaned_text or "资质条件" in cleaned_text):
|
||||
if re.search(common_pattern, cleaned_text, re.MULTILINE):
|
||||
if start_page is None:
|
||||
start_page = i # 确保起始页不小于章节的开始页码
|
||||
# 确定结束页
|
||||
if start_page is not None and re.search(end_pattern, cleaned_text):
|
||||
if i > start_page:
|
||||
end_page = i
|
||||
break # 找到结束页后退出循环
|
||||
|
||||
if start_page is None or end_page is None:
|
||||
print(f"{output_suffix} twice: 未找到起始或结束页在文件 {pdf_path} 中！")
|
||||
return ""
|
||||
else:
|
||||
return save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page,common_header)
|
||||
elif output_suffix == "invalid":
|
||||
pdf_document = PdfReader(pdf_path)
|
||||
total_pages = len(pdf_document.pages)
|
||||
# 计算总页数的三分之二
|
||||
total = int(total_pages * 2 / 3)
|
||||
start_page = last_begin_index
|
||||
end_page = min(90, total)
|
||||
return save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page,common_header)
|
||||
|
||||
|
||||
def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
|
||||
common_header=extract_common_header(pdf_path)
|
||||
# 打开PDF文件
|
||||
pdf_document = PdfReader(pdf_path)
|
||||
start_page = None
|
||||
end_page = None
|
||||
# 遍历文档的每一页，查找开始和结束短语的位置
|
||||
for i in range(len(pdf_document.pages)):
|
||||
page = pdf_document.pages[i]
|
||||
text = page.extract_text()
|
||||
if text:
|
||||
cleaned_text = clean_page_content(text,common_header)
|
||||
# print(cleaned_text)
|
||||
if re.search(begin_pattern, cleaned_text) and i > begin_page:
|
||||
if output_suffix == "invalid" and start_page: # 仅当提取Invalid的时候，判断初始页码是第一个匹配到的页码，因为招标编号可能存在多个，后面的覆盖前面
|
||||
continue
|
||||
else:
|
||||
start_page = i
|
||||
if start_page is not None and re.search(end_pattern, cleaned_text):
|
||||
# 如果output_suffix是"qualification"，调整条件检查
|
||||
condition = i > start_page
|
||||
if condition:
|
||||
is_invalid_condition = output_suffix == "invalid" and i > 30 # 这边默认无效投标至少有30页
|
||||
if is_invalid_condition or output_suffix != "invalid":
|
||||
end_page = i
|
||||
break
|
||||
|
||||
# 确保找到了起始和结束页面
|
||||
if start_page is None or end_page is None:
|
||||
if output_suffix == "qualification" or output_suffix =="invalid":
|
||||
return extract_pages_twice(pdf_path, output_folder, output_suffix)
|
||||
else:
|
||||
print(f"{output_suffix} first: 未找到起始或结束页在文件 {pdf_path} 中！")
|
||||
return ""
|
||||
else:
|
||||
return save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page,common_header)
|
||||
|
||||
|
||||
def process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
|
||||
# 确保输出文件夹存在
|
||||
if not os.path.exists(output_folder):
|
||||
os.makedirs(output_folder)
|
||||
if os.path.isdir(input_path):
|
||||
generated_files = []
|
||||
# 遍历文件夹内的所有PDF文件
|
||||
for file in os.listdir(input_path):
|
||||
if file.endswith(".pdf"):
|
||||
pdf_path = os.path.join(input_path, file)
|
||||
output_pdf_path = extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern,
|
||||
output_suffix)
|
||||
if output_pdf_path and os.path.isfile(output_pdf_path):
|
||||
generated_files.append(output_pdf_path)
|
||||
return generated_files
|
||||
elif os.path.isfile(input_path) and input_path.endswith(".pdf"):
|
||||
# 处理单个PDF文件
|
||||
output_pdf_path = extract_pages(input_path, output_folder, begin_pattern, begin_page, end_pattern,
|
||||
output_suffix)
|
||||
if output_pdf_path and os.path.isfile(output_pdf_path):
|
||||
return [output_pdf_path] # 以列表形式返回，以保持一致性
|
||||
else:
|
||||
print("提供的路径既不是文件夹也不是PDF文件。")
|
||||
return []
|
||||
|
||||
def truncate_pdf_main(input_path, output_folder, selection):
|
||||
try:
|
||||
if selection == 1:
|
||||
# Configure patterns and phrases for "投标人须知前附表"
|
||||
begin_pattern = re.compile(r'第[一二三四五六七八九十]+章\s*投标人须知')
|
||||
begin_page = 3
|
||||
end_pattern = re.compile(r'投标人须知正文')
|
||||
output_suffix = "tobidders_notice_table"
|
||||
elif selection == 2:
|
||||
# Configure patterns and phrases for "评标办法"
|
||||
begin_pattern = re.compile(
|
||||
r'第[一二三四五六七八九十]+章\s*评标办法') # 考虑到这种情况 '第三章 第三章 第三章 第三章 评标办法 评标办法 评标办法 评标办法'
|
||||
begin_page = 10
|
||||
end_pattern = re.compile(r'评标办法正文|评标办法')
|
||||
output_suffix = "evaluation_method"
|
||||
elif selection == 3:
|
||||
# Configure patterns and phrases for "投标人须知正文"
|
||||
begin_pattern = re.compile(r'投标人须知正文')
|
||||
begin_page = 5
|
||||
end_pattern = re.compile(
|
||||
r'^第[一二三四五六七八九十]+章\s*评标办法|^评标办法前附表|^附录(?:一)?[：:]|^附件(?:一)?[：:]|^附表(?:一)?[：:]',
|
||||
re.MULTILINE)
|
||||
output_suffix = "tobidders_notice"
|
||||
elif selection == 4:
|
||||
# 配置用于 "资格审查条件" 的正则表达式模式和短语
|
||||
common_pattern = r'^(?:附录(?:一)?[：:]|附件(?:一)?[：:]|附表(?:一)?[：:])'
|
||||
begin_pattern = re.compile(common_pattern + r'.*(?:资质|能力|信誉).*$', re.MULTILINE)
|
||||
begin_page = 5
|
||||
end_pattern = re.compile(
|
||||
common_pattern + r'(?!.*(?:资质|能力|信誉)).*$|' # 原有的模式
|
||||
r'^(第[一二三四五六七八九十]+章\s*评标办法|评标办法前附表)', # 新增的匹配项
|
||||
re.MULTILINE
|
||||
)
|
||||
output_suffix = "qualification"
|
||||
elif selection == 5:
|
||||
# 配置用于 "招标公告" 的正则表达式模式和短语
|
||||
begin_pattern = 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|^投标邀请书')
|
||||
begin_page = 0
|
||||
end_pattern = re.compile(r'第[一二三四五六七八九十]+章\s*投标人须知')
|
||||
output_suffix = "notice"
|
||||
elif selection == 6:
|
||||
# 配置用于 "无效标" 的正则表达式模式和短语
|
||||
begin_pattern = 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：')
|
||||
begin_page = 0
|
||||
end_pattern = 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)
|
||||
output_suffix = "invalid"
|
||||
else:
|
||||
print("无效的选择:请选择1-6")
|
||||
return [""]
|
||||
# 调用 process_input 进行截取
|
||||
output_paths = process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix)
|
||||
if not output_paths:
|
||||
return [""] # 截取失败时返回空字符串
|
||||
return output_paths
|
||||
except Exception as e:
|
||||
print(f"Error in truncate_pdf_main for selection {selection}: {e}")
|
||||
return [""] # 捕获异常时返回空字符串
|
||||
|
||||
|
||||
|
||||
def truncate_pdf_multiple_old(input_path, output_folder):
|
||||
truncate_files = []
|
||||
for selection in range(1, 5):
|
||||
files = truncate_pdf_main(input_path, output_folder, selection)
|
||||
truncate_files.extend(files)
|
||||
return truncate_files
|
||||
|
||||
def merge_selected_pdfs(output_folder, truncate_files, output_path, base_file_name):
|
||||
"""
|
||||
合并 output_folder 中以 {base_file_name}_before.pdf 结尾的 PDF 文件，
|
||||
以及 truncate_files 中以指定后缀结尾的文件，按照指定顺序合并。
|
||||
|
||||
参数：
|
||||
- output_folder (str): 包含以 {base_file_name}_before.pdf 结尾的 PDF 文件的文件夹路径。
|
||||
- truncate_files (list): 包含 PDF 文件路径的列表。
|
||||
- output_path (str): 合并后的 PDF 文件保存路径。
|
||||
- base_file_name (str): 用于匹配文件名的基础名称。
|
||||
|
||||
返回:
|
||||
- str: 合并后的 PDF 文件路径，如果没有合并则返回 ""。
|
||||
"""
|
||||
# 1. 获取 output_folder 中所有文件
|
||||
try:
|
||||
all_output_files = os.listdir(output_folder)
|
||||
except FileNotFoundError:
|
||||
print(f"输出文件夹 '{output_folder}' 未找到。")
|
||||
return ""
|
||||
except PermissionError:
|
||||
print(f"没有权限访问输出文件夹 '{output_folder}'。")
|
||||
return ""
|
||||
|
||||
# 2. 定义要选择的文件后缀及合并顺序，包括 before 文件
|
||||
desired_suffixes = [
|
||||
f'{base_file_name}_before.pdf',
|
||||
f'{base_file_name}_notice.pdf',
|
||||
f'{base_file_name}_tobidders_notice_table.pdf'
|
||||
]
|
||||
|
||||
all_pdfs_to_merge = []
|
||||
|
||||
for suffix in desired_suffixes:
|
||||
if suffix == f'{base_file_name}_before.pdf':
|
||||
# 从 output_folder 中选择以 {base_file_name}_before.pdf 结尾的文件
|
||||
matching_files = [
|
||||
os.path.join(output_folder, f)
|
||||
for f in all_output_files
|
||||
if f.endswith(suffix)
|
||||
]
|
||||
else:
|
||||
# 从 truncate_files 中选择以指定后缀结尾的文件
|
||||
matching_files = [f for f in truncate_files if f.endswith(suffix)]
|
||||
|
||||
if matching_files:
|
||||
# 如果找到多个匹配的文件，按名称排序并添加
|
||||
matching_files_sorted = sorted(matching_files)
|
||||
all_pdfs_to_merge.extend(matching_files_sorted)
|
||||
for f in matching_files_sorted:
|
||||
print(f"选中文件: {f}")
|
||||
else:
|
||||
print(f"没有找到以 '{suffix}' 结尾的文件。")
|
||||
|
||||
print(f"总共将要合并的 PDF 文件数量: {len(all_pdfs_to_merge)}")
|
||||
|
||||
if not all_pdfs_to_merge:
|
||||
print("没有找到要合并的 PDF 文件。")
|
||||
return ""
|
||||
|
||||
# 过滤掉不存在或为空的文件路径
|
||||
all_pdfs_to_merge = [f for f in all_pdfs_to_merge if os.path.isfile(f)]
|
||||
|
||||
if not all_pdfs_to_merge:
|
||||
print("没有有效的 PDF 文件需要合并。")
|
||||
return ""
|
||||
|
||||
# 调用 merge_pdfs 函数进行合并
|
||||
try:
|
||||
merge_pdfs(all_pdfs_to_merge, output_path)
|
||||
print(f"已成功合并 PDF 文件到 '{output_path}'。")
|
||||
return output_path
|
||||
except Exception as e:
|
||||
print(f"合并 PDF 文件时出错: {e}")
|
||||
return ""
|
||||
|
||||
|
||||
def truncate_pdf_multiple(input_path, output_folder, unique_id="123"):
|
||||
"""
|
||||
处理 PDF 文件，选择 selection 1-6 的部分，并合并结果。
|
||||
|
||||
Args:
|
||||
input_path (str): 要处理的 PDF 文件路径。
|
||||
output_folder (str): 截取后的文件保存文件夹路径。
|
||||
|
||||
Returns:
|
||||
list: 截取的文件路径列表，包括合并后的文件路径（如果有）。
|
||||
"""
|
||||
global logger
|
||||
logger = get_global_logger(unique_id)
|
||||
base_file_name = os.path.splitext(os.path.basename(input_path))[0] # 纯文件名
|
||||
truncate_files = []
|
||||
selections = range(1, 7) # 选择 1 到 6
|
||||
|
||||
# 使用 ThreadPoolExecutor 进行多线程处理
|
||||
with concurrent.futures.ThreadPoolExecutor(max_workers=len(selections)) as executor:
|
||||
# 提交所有任务并保持 selection 顺序
|
||||
future_to_selection = {selection: executor.submit(truncate_pdf_main, input_path, output_folder, selection) for selection in selections}
|
||||
|
||||
# 按 selection 顺序收集结果
|
||||
for selection in selections:
|
||||
future = future_to_selection.get(selection)
|
||||
try:
|
||||
files = future.result()
|
||||
if files and any(f for f in files):
|
||||
# 过滤空字符串
|
||||
valid_files = [f for f in files if f]
|
||||
truncate_files.extend(valid_files)
|
||||
else:
|
||||
logger.error(f"Selection {selection}: 截取失败，已添加空字符串。")
|
||||
truncate_files.append("") # 截取失败时添加空字符串
|
||||
except Exception as e:
|
||||
logger.error(f"Selection {selection} 生成了一个异常: {e}")
|
||||
truncate_files.append("") # 发生异常时添加空字符串
|
||||
|
||||
if any(f for f in truncate_files if f): # 检查是否有有效的文件路径
|
||||
merged_output_path = os.path.join(output_folder, f"{base_file_name}_merged_baseinfo.pdf")
|
||||
merged_result = merge_selected_pdfs(output_folder, truncate_files, merged_output_path, base_file_name)
|
||||
if merged_result:
|
||||
truncate_files.append(merged_result)
|
||||
logger.info(f"merged_baseinfo: 已生成合并文件: {merged_output_path}")
|
||||
else:
|
||||
truncate_files.append("") # 如果merged_result未生成，添加空字符串
|
||||
logger.warning("merged_baseinfo: 未生成合并文件，因为没有找到需要合并的 PDF 文件。")
|
||||
else:
|
||||
truncate_files.append("") # 如果没有文件需要合并，也添加空字符串
|
||||
logger.warning(f"merged_baseinfo: 没有文件需要合并 for {input_path}")
|
||||
|
||||
return truncate_files
|
||||
|
||||
|
||||
def truncate_pdf_specific_engineering(pdf_path, output_folder, selections, unique_id="123"):
|
||||
"""
|
||||
处理 PDF 文件，选择指定的 selections，并合并结果。
|
||||
|
||||
Args:
|
||||
pdf_path (str): 要处理的 PDF 文件路径。
|
||||
output_folder (str): 截取后的文件保存文件夹路径。
|
||||
selections (list): 需要截取的部分（例如 [4, 5]）。
|
||||
unique_id (str): 用于日志记录的唯一标识符。
|
||||
|
||||
Returns:
|
||||
list: 截取的文件路径列表，包括合并后的文件路径（如果有）。
|
||||
"""
|
||||
try:
|
||||
global logger
|
||||
logger = get_global_logger(unique_id)
|
||||
base_file_name = os.path.splitext(os.path.basename(pdf_path))[0]
|
||||
truncate_files = []
|
||||
|
||||
# 使用 ThreadPoolExecutor 进行多线程处理
|
||||
with concurrent.futures.ThreadPoolExecutor(max_workers=len(selections)) as executor:
|
||||
# 提交所有任务并保持 selection 顺序
|
||||
future_to_selection = {selection: executor.submit(truncate_pdf_main, pdf_path, output_folder, selection) for selection in selections}
|
||||
|
||||
# 按 selection 顺序收集结果
|
||||
for selection in selections:
|
||||
future = future_to_selection.get(selection)
|
||||
try:
|
||||
files = future.result()
|
||||
if files and any(f for f in files):
|
||||
# 过滤空字符串
|
||||
valid_files = [f for f in files if f]
|
||||
truncate_files.extend(valid_files)
|
||||
else:
|
||||
logger.error(f"Selection {selection}: 截取失败，已添加空字符串。")
|
||||
truncate_files.append("") # 截取失败时添加空字符串
|
||||
except Exception as e:
|
||||
logger.error(f"Selection {selection} 生成了一个异常: {e}")
|
||||
truncate_files.append("") # 发生异常时添加空字符串
|
||||
|
||||
if any(f for f in truncate_files if f): # 检查是否有有效的文件路径
|
||||
merged_output_path = os.path.join(output_folder, f"{base_file_name}_merged_specific.pdf")
|
||||
merged_result = merge_selected_pdfs(output_folder, truncate_files, merged_output_path, base_file_name)
|
||||
if merged_result:
|
||||
truncate_files.append(merged_result)
|
||||
logger.info(f"merged_specific: 已生成合并文件: {merged_output_path}")
|
||||
else:
|
||||
truncate_files.append("") # 如果 merged_result 未生成，添加空字符串
|
||||
logger.warning("merged_specific: 未生成合并文件，因为没有找到需要合并的 PDF 文件。")
|
||||
else:
|
||||
truncate_files.append("") # 如果没有文件需要合并，也添加空字符串
|
||||
logger.warning(f"merged_specific: 没有文件需要合并 for {pdf_path}")
|
||||
|
||||
return truncate_files
|
||||
|
||||
except Exception as e:
|
||||
# 假设 selections 的长度是已知的，可以通过传递参数或其他方式获取
|
||||
logger.error(f"Error in truncate_pdf_specific_engineering: {e}")
|
||||
return [""] * len(selections) # 返回与 selections 数量相同的空字符串列表
|
||||
|
||||
|
||||
# TODO:需要完善二次请求。目前invalid一定能返回 前附表 须知正文如果为空的话要额外处理一下，比如说就不进行跳转（见xx表） 开评定标这里也要考虑 如果评分表为空，也要处理。
|
||||
#TODO:zbtest8 zbtest18有问题 后期需要完善，截取需要截两次，第一次严格第二次宽松
|
||||
if __name__ == "__main__":
|
||||
input_path = "C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest4_evaluation_method.pdf" # 可以是单个PDF文件路径或文件夹路径
|
||||
# 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\\output6"
|
||||
files=truncate_pdf_multiple(input_path,output_folder)
|
||||
# selections = [5, 1] # 仅处理 selection 5、1 和 3
|
||||
# files=truncate_pdf_specific_engineering(input_path,output_folder,selections)
|
||||
print(files)
|
||||
# selection = 6 # 例如：1 - 投标人须知前附表, 2 - 评标办法, 3 - 投标人须知正文 4-资格审查条件 5-招标公告 6-无效标
|
||||
# generated_files = truncate_pdf_main(input_path, output_folder, selection)
|
||||
# print(generated_files)
|
||||
# print("生成的文件:", generated_files)
|
||||
@ -217,7 +217,7 @@ def combine_evaluation_standards(truncate_file):
|
||||
# user_query = "根据该文档中的评标办法前附表或者评分标准表，请你列出该文件的技术评分，商务评分，投标报价评审标准以及它们对应的具体评分要求，外层键名分别为'技术评分','商务评分','投标报价'。如果评分内容不是这3个，则返回文档中给定的评分内容以及它的评分要求，都以json的格式返回结果，如果该采购活动有多个包，则最外层键名为对应的包名。请不要回答有关资格审查的内容"
|
||||
user_query = (
|
||||
"""
|
||||
根据该文档中的评标办法前附表，请你列出该文件的技术评分，商务评分，投标报价评审以及它们对应的具体评分要求，请以json格式返回结果，请在这三大块评分中分别用若干键值对表示具体要求，请精确到具体的评审项，内层的键名为'评分'及'要求'，若这三大块评分中存在其他信息，则在相应评分大块中新增键名'备注'存放该信息，键值为具体的要求，否则不需要。如果评分内容（因素）不是这3个，则返回文档中给定的评分内容（因素）以及它们的具体评分要求，如果该采购活动有多个包，则最外层键名为对应的包名,否则不需要。不要回答有关资格审查的内容，若存在未知信息，填充'未知'。以下为示例输出：
|
||||
根据该文档中的评标办法前附表，请你列出该文件的技术评分，商务评分，投标报价评审以及它们对应的具体评分要求，请以json格式返回结果，请在这三大块评分中分别用若干键值对表示具体要求，请精确到具体的评审项，内层的键名为'评分'及'要求'，若这三大块评分中存在其他信息，则在相应评分大块内部新增键名'备注'存放该信息，键值为具体的要求，否则不需要。如果评分内容（因素）不是这3个，则返回文档中给定的评分内容（因素）以及它们的具体评分要求，如果该采购活动有多个包，则最外层键名为对应的包名,否则不需要。不要回答有关资格审查的内容，若存在未知信息，填充'未知'。以下为示例输出：
|
||||
{
|
||||
"一包": {
|
||||
"技术评分": {
|
||||
@ -255,7 +255,7 @@ def combine_evaluation_standards(truncate_file):
|
||||
)
|
||||
# 执行第二个查询
|
||||
evaluation_res = qianwen_long(file_id, user_query)
|
||||
|
||||
print(evaluation_res)
|
||||
# 清理和处理响应
|
||||
cleaned_evaluation_res = parse_json_with_duplicates(evaluation_res) #处理重复键名的情况
|
||||
result_data = process_data_based_on_key(cleaned_evaluation_res) #处理不知名外键的情况
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user