606 lines
32 KiB
Python
606 lines
32 KiB
Python
import re
|
||
import os
|
||
import time
|
||
from PyPDF2 import PdfReader, PdfWriter
|
||
from flask_app.general.clean_pdf import clean_page_content, extract_common_header
|
||
from flask_app.general.merge_pdfs import merge_selected_pdfs_for_engineering
|
||
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 save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page, common_header):
|
||
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])
|
||
print(before_pdf_path)
|
||
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_tobidders_notice(pdf_path, output_folder, begin_pattern, begin_page, common_header,
|
||
is_secondary_match):
|
||
pdf_document = PdfReader(pdf_path)
|
||
exclusion_pattern = re.compile(r'文件的构成|文件的组成|须对应|需对应|须按照|需按照|须根据|需根据|文件组成|文件构成')
|
||
|
||
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
|
||
if not is_secondary_match:
|
||
end_pattern = re.compile(
|
||
rf'^第[一二三四五六七八九十百千]+?(?:{chapter_type})\s*[\u4e00-\u9fff]+|'
|
||
r'^评标办法前附表|'
|
||
r'^附录(?:一)?[：:]|'
|
||
r'^附件(?:一)?[：:]|'
|
||
r'^附表(?:一)?[：:]',
|
||
re.MULTILINE
|
||
)
|
||
else:
|
||
end_pattern = re.compile(
|
||
rf'第[一二三四五六七八九十百千]+?(?:{chapter_type})\s*[\u4e00 -\u9fff]+\s*$'
|
||
)
|
||
# 根据 chapter_type 动态生成 additional_mid_pattern
|
||
if chapter_type == '章':
|
||
additional_mid_pattern = r'^第[一二三四五六七八九十百千]+?(?:部分)'
|
||
elif chapter_type == '部分':
|
||
additional_mid_pattern = r'^第[一二三四五六七八九十百千]+?(?:章)'
|
||
else:
|
||
additional_mid_pattern = ''
|
||
|
||
# 定义基础的 mid_pattern
|
||
base_mid_pattern = (
|
||
r'^\s*(?:[（(]\s*[一1]?\s*[)）]\s*[、．.]*|[一1][、．.]+|[、．.]+)\s*(说\s*明|总\s*则)'
|
||
r'|^((投标人?|磋商|供应商|谈判供应商|磋商供应商)\s*须知正文部分)'
|
||
)
|
||
# 合并基础模式和额外模式
|
||
if additional_mid_pattern:
|
||
combined_mid_pattern = re.compile(
|
||
rf'(?:{base_mid_pattern})|(?:{additional_mid_pattern})',
|
||
re.MULTILINE
|
||
)
|
||
else:
|
||
combined_mid_pattern = re.compile(
|
||
rf'{base_mid_pattern}',
|
||
re.MULTILINE
|
||
)
|
||
# print(f"生成的 combined_mid_pattern: {combined_mid_pattern.pattern}") # 打印 combined_mid_pattern
|
||
else:
|
||
# 如果未匹配到“章”或“部分”，使用默认的 end_pattern 和 mid_pattern
|
||
if not is_secondary_match:
|
||
end_pattern = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+|'
|
||
r'^评标办法前附表|' # Match "评标办法前附表" at the beginning of a line
|
||
r'^附录(?:一)?[：:]|' # Match "附录一" with optional "一" and colon
|
||
r'^附件(?:一)?[：:]|' # Match "附件一" with optional "一" and colon
|
||
r'^附表(?:一)?[：:]', # Match "附表一" with optional "一" and colon
|
||
re.MULTILINE
|
||
)
|
||
else:
|
||
end_pattern = re.compile(
|
||
rf'第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+\s*$'
|
||
)
|
||
# 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
|
||
)
|
||
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 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()
|
||
if start_page is None or end_page is None or mid_page is None:
|
||
print(f"first: tobidders_notice 未找到起始或结束页在文件 {pdf_path} 中！尝试备用提取策略。")
|
||
return "", ""
|
||
|
||
path1 = save_pages_to_new_pdf(pdf_path, output_folder, "tobidders_notice_table", start_page, mid_page,
|
||
common_header)
|
||
path2 = save_pages_to_new_pdf(pdf_path, output_folder, "tobidders_notice", mid_page, end_page, common_header)
|
||
return path1, path2
|
||
|
||
|
||
def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix, common_header,
|
||
is_secondary_match=False):
|
||
# 打开PDF文件
|
||
pdf_document = PdfReader(pdf_path)
|
||
start_page = None
|
||
end_page = None
|
||
exclusion_pattern = re.compile(r'文件的构成|文件的组成|须对应|需对应|须按照|需按照|须根据|需根据|文件组成|文件构成')
|
||
# 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 is_secondary_match and re.search(exclusion_pattern, cleaned_text): # 跳过投标人须知正文中的"投标文件的组成"
|
||
if re.search(exclusion_pattern, cleaned_text):
|
||
continue
|
||
if re.search(begin_pattern, cleaned_text) and i >= begin_page:
|
||
if start_page and (output_suffix == "notice" or output_suffix == "invalid"):
|
||
pass
|
||
else:
|
||
start_page = i
|
||
if start_page is not None and re.search(end_pattern, cleaned_text) and not re.search(begin_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 extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, last_begin_index):
|
||
"""
|
||
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:
|
||
pdf_document = PdfReader(pdf_path)
|
||
if output_suffix == "qualification":
|
||
print("twice:qualificaiton!")
|
||
# 动态设置 include_keys
|
||
include_keys = ["资格审查", "资质审查", "符合性审查", "资格性检查", "符合性检查","资格检查","能力","信誉"]
|
||
# 定义起始匹配模式，仅匹配“附录”、“附件”或“附表”
|
||
begin_pattern = r'^(?:附录(?:[一1])?[：:]|附件(?:[一1])?[：:]|附表(?:[一1])?[：:])'
|
||
# 定义结束匹配模式 - 附录、附件、附表等（移除负向前瞻）
|
||
end_pattern_attachment = re.compile(
|
||
r'^(?:附录[一二三四五六七八九1-9]*[：:]|附件[一二三四五六七八九1-9]*[：:]|附表[一二三四五六七八九1-9]*[：:]).*$',
|
||
re.MULTILINE
|
||
)
|
||
# 定义结束匹配模式 - 章节标题、评标附表、投标人须知等
|
||
end_pattern_chapter = re.compile(
|
||
r'第[一二三四五六七八九]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$|'
|
||
r'\s*评标(?:办法|方法)前附表\s*$|'
|
||
r'投标人须知',
|
||
re.MULTILINE
|
||
)
|
||
start_page = None
|
||
end_page = None
|
||
# 从指定的开始页开始遍历
|
||
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 any(key in cleaned_text for key in include_keys):
|
||
if re.search(begin_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
|
||
continue
|
||
# print(f"匹配到附录/附件/附表，设置起始页为: {start_page}")
|
||
# 确定结束页 - 附录、附件、附表等
|
||
if start_page is not None and end_pattern_attachment.search(cleaned_text):
|
||
# 额外检查当前页面是否不包含任何 include_keys
|
||
if not any(key in cleaned_text for key in include_keys):
|
||
if i > start_page:
|
||
end_page = i
|
||
# print(f"找到结束页 (附件类): {end_page}")
|
||
break # 找到结束页后退出循环
|
||
else:
|
||
print(f"当前页面匹配附件结束模式但包含 include_keys，继续查找。页面: {i}")
|
||
# 确定结束页 - 章节标题、评标附表、投标人须知等
|
||
elif start_page is not None and end_pattern_chapter.search(cleaned_text):
|
||
if i > start_page:
|
||
end_page = i
|
||
# print(f"找到结束页 (章节标题等): {end_page}")
|
||
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)]
|
||
else:
|
||
print(f"{output_suffix} twice: 未定义的输出后缀。")
|
||
return []
|
||
except Exception as e:
|
||
print(f"Error in extract_pages_twice: {e}")
|
||
return []
|
||
|
||
|
||
def get_start_and_common_header(input_path):
|
||
common_header = extract_common_header(input_path)
|
||
last_begin_index = 0
|
||
begin_pattern = re.compile(
|
||
r'.*(?:招标公告|投标邀请书|投标邀请函|投标邀请)[\)）]?\s*$',
|
||
re.MULTILINE
|
||
)
|
||
pdf_document = PdfReader(input_path)
|
||
for i, page in enumerate(pdf_document.pages):
|
||
if i > 25:
|
||
return common_header, 0 # 如果页码大于25，直接返回last_begin_index=0
|
||
text = page.extract_text()
|
||
if text:
|
||
cleaned_text = clean_page_content(text, common_header)
|
||
if begin_pattern.search(cleaned_text):
|
||
last_begin_index = i # 更新第一个匹配的索引，页码从0开始
|
||
return common_header, last_begin_index
|
||
return common_header, last_begin_index
|
||
|
||
|
||
def truncate_pdf_main(input_path, output_folder, selection):
|
||
if os.path.isdir(input_path):
|
||
generated_files = []
|
||
for file_name in os.listdir(input_path):
|
||
if file_name.endswith('.pdf'):
|
||
file_path = os.path.join(input_path, file_name)
|
||
files = truncate_pdf_main(file_path, output_folder, selection)
|
||
if files:
|
||
generated_files.extend(files)
|
||
return generated_files
|
||
elif os.path.isfile(input_path) and input_path.endswith('.pdf'):
|
||
# base_file_name = os.path.splitext(os.path.basename(input_path))[0]
|
||
common_header, last_begin_index = get_start_and_common_header(input_path)
|
||
# print(last_begin_index)
|
||
if selection == 1:
|
||
# Selection 1: 投标人须知前附表
|
||
pattern_pairs = [
|
||
(
|
||
re.compile(
|
||
r'(?:第[一二三四五六七八九十百千]+(?:章|部分)\s*(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知+|(?:一\s*、\s*)?(?:投标人?|磋商|供应商)须知前附表)'),
|
||
re.compile(
|
||
r'第[一二三四五六七八九十]+(?:章|部分)\s*[\u4e00-\u9fff]+|^评标办法前附表|^附录(?:一)?[：:]|^附件(?:一)?[：:]|^附表(?:一)?[：:]',
|
||
re.MULTILINE)
|
||
),
|
||
(
|
||
re.compile(
|
||
r'.*(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知\s*$|(?:一\s*、\s*)?(?:投标人?|磋商|供应商)须知前附表',
|
||
re.MULTILINE),
|
||
re.compile(
|
||
r'第[一二三四五六七八九十]+(?:章|部分)\s*[\u4e00-\u9fff]+|^评标办法前附表|^附录(?:一)?[：:]|^附件(?:一)?[：:]|^附表(?:一)?[：:]',
|
||
re.MULTILINE)
|
||
)
|
||
]
|
||
output_suffix = "tobidders_notice"
|
||
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|部分)\s*(?=.*(?:磋商|谈判|评标|评定|评审))(?=.*(?:办法|方法))'),
|
||
# Alternative begin pattern
|
||
re.compile(r'评标办法正文|评标方法正文|^第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+')
|
||
# Alternative end pattern
|
||
),
|
||
(
|
||
re.compile(
|
||
r'(?<!见)' # 确保前面不是“见”
|
||
r'第[一二三四五六七八九十1-9]+(?: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*$' # 继续匹配允许的字符直到行尾
|
||
r'|\s*评标(办法|方法)前附表\s*$', # 或匹配“评标办法前附表”或“评标方法前附表”
|
||
re.MULTILINE
|
||
),
|
||
re.compile(r'第[一二三四五六七八九十1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$', re.MULTILINE)
|
||
)
|
||
]
|
||
output_suffix = "evaluation_method"
|
||
# TODO:exclusion
|
||
elif selection == 3:
|
||
# Selection 3: 资格审查条件
|
||
pattern_pairs = [
|
||
# (
|
||
# re.compile(r'^(?:附录(?:[一1])?[：:]|附件(?:[一1])?[：:]|附表(?:[一1])?[：:]).*(?:资质|能力|信誉).*$|^第[一二三四五六七八九十百千]+(?:章|部分).*?(资格).*',
|
||
# re.MULTILINE),
|
||
# re.compile(
|
||
# r'^(?:附录[一二三四五六七八九1-9]*[：:]|附件[一二三四五六七八九1-9]*[：:]|附表[一二三四五六七八九1-9]*[：:])(?!.*(?:资质|能力|信誉)).*$'
|
||
# r'^第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+', re.MULTILINE)
|
||
# ),
|
||
(
|
||
re.compile(
|
||
r'^(?:附录(?:[一1])?[：:]|附件(?:[一1])?[：:]|附表(?:[一1])?[：:]).*(?:资质|能力|信誉).*$|第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]*资格[\u4e00-\u9fff、()（）]*\s*$',
|
||
re.MULTILINE),
|
||
re.compile(
|
||
r'^(?:附录[一二三四五六七八九1-9]*[：:]|附件[一二三四五六七八九1-9]*[：:]|附表[一二三四五六七八九1-9]*[：:])(?!.*(?:资质|能力|信誉)).*|'
|
||
r'第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$', re.MULTILINE)
|
||
)
|
||
]
|
||
output_suffix = "qualification"
|
||
elif selection == 4:
|
||
# Selection 4: 招标公告
|
||
pattern_pairs = [
|
||
(
|
||
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|邀请).*|^第一卷|^投标邀请书|^投标邀请函|^投标邀请'),
|
||
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|投标邀请)[\)）]?\s*$', re.MULTILINE),
|
||
re.compile(r".*(?:投标人须知|投标人须知前附表)\s*$", re.MULTILINE)
|
||
)
|
||
]
|
||
output_suffix = "notice"
|
||
|
||
elif selection == 5:
|
||
# Selection 5: 无效标
|
||
pattern_pairs = [
|
||
(
|
||
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|邀请).*|^第一卷|^投标邀请书|^投标邀请函|^投标邀请'),
|
||
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|投标邀请)[\)）]?\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)
|
||
)
|
||
]
|
||
output_suffix = "invalid"
|
||
|
||
else:
|
||
print("无效的选择:请选择1-5")
|
||
return [""]
|
||
|
||
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
|
||
output_paths = list(
|
||
extract_pages_tobidders_notice(input_path, output_folder, begin_pattern, begin_page, common_header,
|
||
is_secondary_match))
|
||
if output_paths and any(os.path.isfile(f) for f in output_paths):
|
||
return output_paths
|
||
else:
|
||
# print(f"Selection {selection}: 使用组合提取函数失败。尝试下一个模式对。")
|
||
continue
|
||
output_paths = extract_pages(
|
||
input_path,
|
||
output_folder,
|
||
begin_pattern,
|
||
begin_page=begin_page,
|
||
end_pattern=end_pattern,
|
||
output_suffix=output_suffix,
|
||
common_header=common_header,
|
||
is_secondary_match=is_secondary_match
|
||
)
|
||
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。")
|
||
continue
|
||
|
||
# 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, common_header, last_begin_index)
|
||
if fallback_result and any(os.path.isfile(f) for f in fallback_result):
|
||
return fallback_result
|
||
else:
|
||
if selection == 1:
|
||
return ["", ""]
|
||
else:
|
||
return ['']
|
||
else:
|
||
print("Invalid input path. It is neither a PDF file nor a directory containing PDF files.")
|
||
return ['']
|
||
|
||
|
||
def truncate_pdf_multiple(input_path, output_folder, unique_id="123"):
|
||
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, 6) # 选择 1 到 5
|
||
|
||
# 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。")
|
||
# Append two empty strings for selection=1; otherwise, one empty string
|
||
truncate_files.extend(["", ""] if selection == 1 else [""])
|
||
except Exception as e:
|
||
logger.error(f"Selection {selection} 生成了一个异常: {e}")
|
||
# Append two empty strings for selection=1; otherwise, one empty string
|
||
truncate_files.extend(["", ""] if selection == 1 else [""])
|
||
|
||
# Proceed with merging logic as before...
|
||
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_for_engineering(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"):
|
||
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。")
|
||
# Append two empty strings for selection=1; otherwise, one empty string
|
||
truncate_files.extend(["", ""] if selection == 1 else [""])
|
||
except Exception as e:
|
||
logger.error(f"Selection {selection} 生成了一个异常: {e}")
|
||
# Append two empty strings for selection=1; otherwise, one empty string
|
||
truncate_files.extend(["", ""] if selection == 1 else [""])
|
||
|
||
# Proceed with merging logic as before...
|
||
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_for_engineering(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:
|
||
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
|
||
|
||
if __name__ == "__main__":
|
||
start_time = time.time()
|
||
# input_path = "C:\\Users\\Administrator\\Desktop\\new招标文件\\工程标"
|
||
# 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=r"C:\Users\Administrator\Desktop\招标文件\招标test文件夹\zbtest20.pdf"
|
||
output_folder = r"C:\Users\Administrator\Desktop\招标文件\招标test文件夹\all"
|
||
# files=truncate_pdf_multiple(input_path,output_folder)
|
||
# print(files)
|
||
# selections = [4, 1] # 仅处理 selection 4、1
|
||
# files=truncate_pdf_specific_engineering(input_path,output_folder,selections)
|
||
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)
|
||
print(generated_files)
|
||
# print("生成的文件:", generated_files)
|
||
end_time = time.time()
|
||
print("耗时：" + str(end_time - start_time))
|