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

12.18 截取pdf

Browse Source
This commit is contained in:
zy123 2024-12-18 10:32:24 +08:00
parent cb153889a4
commit 6fb4f49b13
5 changed files with 430 additions and 418 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
flask_app/general/merge_pdfs.py
View File

@ -118,7 +118,7 @@ def merge_selected_pdfs(output_folder, truncate_files, output_path, base_file_na
required_suffixes = [ required_suffixes = [
f'{base_file_name}_before.pdf', f'{base_file_name}_before.pdf',
f'{base_file_name}_notice.pdf', f'{base_file_name}_notice.pdf',
f'{base_file_name}_tobidders_notice_table.pdf' f'{base_file_name}_tobidders_notice_table.pdf' #tobidders_notice tobidders_notice_table
] ]
optional_suffixes = [] optional_suffixes = []
elif mode == 'goods': elif mode == 'goods':

16
flask_app/general/截取pdf_main.py
View File

@ -34,20 +34,18 @@ def truncate_pdf_multiple(pdf_path, output_folder, logger,mode='goods',selection
return ["", ""] if selection == 4 else [""] return ["", ""] if selection == 4 else [""]
# 设置模式相关的参数和函数 # 设置模式相关的参数和函数
if mode == 'goods': if mode == 'goods':
logger.info("call 货物标截取pdf")
truncate_function = truncate_pdf_main_goods truncate_function = truncate_pdf_main_goods
merge_mode = 'goods' merge_mode = 'goods'
# 根据 'goods' 模式定义异常处理的逻辑 # 根据 'goods' 模式定义异常处理的逻辑
else: # mode == 'engineering' else: # mode == 'engineering'
logger.info("call 工程标标截取pdf")
truncate_function = truncate_pdf_main_engineering truncate_function = truncate_pdf_main_engineering
merge_mode = 'engineering' merge_mode = 'engineering'
mode_flag = 1
num_selections = len(selections) num_selections = len(selections)
if num_selections < 5: res = check_pdf_pages(pdf_path, logger)
mode_flag = 2
res = check_pdf_pages(pdf_path, mode_flag, logger)
if res is not None: if res is not None:
return res # 返回包含空字符串的列表 return res # 返回包含空字符串的列表
@ -63,7 +61,8 @@ def truncate_pdf_multiple(pdf_path, output_folder, logger,mode='goods',selection
pdf_path, pdf_path,
output_folder, output_folder,
selection, selection,
logger logger,
"default"
# 如果 'goods' 模式需要额外参数，如 output_suffix，可以在这里处理 # 如果 'goods' 模式需要额外参数，如 output_suffix，可以在这里处理
) )
for selection in selections for selection in selections
@ -115,8 +114,9 @@ if __name__ == "__main__":
# pdf_path = r"C:\Users\Administrator\Desktop\招标文件\招标02.pdf" # pdf_path = r"C:\Users\Administrator\Desktop\招标文件\招标02.pdf"
# input_path=r"C:\Users\Administrator\Desktop\招标文件\招标test文件夹\zbtest8.pdf" # input_path=r"C:\Users\Administrator\Desktop\招标文件\招标test文件夹\zbtest8.pdf"
output_folder = r"C:\Users\Administrator\Desktop\fsdownload\91399aa4-1ee8-447d-a05b-03cd8d15ced5\tmp" output_folder = r"C:\Users\Administrator\Desktop\fsdownload\91399aa4-1ee8-447d-a05b-03cd8d15ced5\tmp"
# selections = [1, 4] # 仅处理 selection 4、1 selections = [1, 4] # 仅处理 selection 4、1
selections=[5] # selections=[5]
#engineering
files=truncate_pdf_multiple(pdf_path,output_folder,logger,'engineering',selections) files=truncate_pdf_multiple(pdf_path,output_folder,logger,'engineering',selections)
print(files) print(files)
# selection = 1 # 例如：1 - 招标公告, 2 - 评标办法, 3 -资格审查条件 4-投标人须知前附表+正文 5-无效标 # selection = 1 # 例如：1 - 招标公告, 2 - 评标办法, 3 -资格审查条件 4-投标人须知前附表+正文 5-无效标

70
flask_app/general/截取pdf通用函数.py
View File

@ -3,9 +3,11 @@ import concurrent.futures
import os import os
import regex import regex
from PyPDF2 import PdfReader from PyPDF2 import PdfReader, PdfWriter
from flask_app.general.clean_pdf import extract_common_header, clean_page_content from flask_app.general.clean_pdf import extract_common_header, clean_page_content
from flask_app.general.format_change import docx2pdf
def get_start_and_common_header(input_path,end_page): def get_start_and_common_header(input_path,end_page):
common_header = extract_common_header(input_path) common_header = extract_common_header(input_path)
@ -32,26 +34,78 @@ def get_start_and_common_header(input_path,end_page):
return common_header, last_begin_index return common_header, last_begin_index
return common_header, last_begin_index return common_header, last_begin_index
def check_pdf_pages(pdf_path, mode,logger): def check_pdf_pages(pdf_path, logger):
try: try:
reader = PdfReader(pdf_path) reader = PdfReader(pdf_path)
num_pages = len(reader.pages) num_pages = len(reader.pages)
logger.info(f"PDF '{pdf_path}' 的总页数为: {num_pages}") logger.info(f"PDF '{pdf_path}' 的总页数为: {num_pages}")
if num_pages <= 50: if num_pages <= 50:
logger.info("PDF页数小于或等于50页，跳过切分逻辑。") logger.info("PDF页数小于或等于50页，跳过切分逻辑。")
if mode==1:
return ['', '', '', '', '', '', ''] return ['', '', '', '', '', '', '']
else:
return ['','','','']
# 若页数大于50页，返回None表示继续处理 # 若页数大于50页，返回None表示继续处理
return None return None
except Exception as e: except Exception as e:
logger.error(f"无法读取 PDF 页数: {e}") logger.error(f"无法读取 PDF 页数: {e}")
# 返回空列表意味着无法执行后续处理逻辑 # 返回空列表意味着无法执行后续处理逻辑
if mode == 1:
return ['', '', '', '', '', '', ''] return ['', '', '', '', '', '', '']
else:
return ['', '', '', '']
def save_extracted_pages(pdf_path,output_folder,start_page, end_page, output_suffix,common_header):
try:
# 检查 start_page 和 end_page 是否为 None
if start_page is None or end_page is None:
print("Error: start_page 或 end_page 为 None")
return ""
pdf_document = PdfReader(pdf_path)
total_pages = len(pdf_document.pages)
base_file_name = os.path.splitext(os.path.basename(pdf_path))[0]
output_pdf_path = os.path.join(output_folder, f"{base_file_name}_{output_suffix}.pdf")
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 ""
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 regex.search(r'目\s*录', cleaned_text, regex.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)
output_doc = PdfWriter()
for page_num in range(start_page, end_page + 1):
output_doc.add_page(pdf_document.pages[page_num])
with open(output_pdf_path, 'wb') as f:
output_doc.write(f)
print(f"{output_suffix} 已截取并保存页面从 {start_page} 到 {end_page} 为 {output_pdf_path}")
return output_pdf_path
except Exception as e:
print(f"Error in save_extracted_pages: {e}")
return "" # 返回空字符串
def is_pdf_or_doc(filename):
# 判断文件是否为PDF或Word文档
return filename.lower().endswith(('.pdf', '.doc', '.docx'))
def convert_to_pdf(file_path):
# 假设 docx2pdf 函数已经被定义，这里仅根据文件扩展名来决定是否需要转换
if file_path.lower().endswith(('.doc', '.docx')):
return docx2pdf(file_path)
return file_path

248
flask_app/工程标/截取pdf工程标版.py
View File

@ -5,66 +5,9 @@ import time
from PyPDF2 import PdfReader, PdfWriter from PyPDF2 import PdfReader, PdfWriter
from flask_app.general.clean_pdf import clean_page_content from flask_app.general.clean_pdf import clean_page_content
from flask_app.general.截取pdf通用函数 import get_start_and_common_header from flask_app.general.截取pdf通用函数 import get_start_and_common_header,save_extracted_pages
from flask_app.general.通用功能函数 import get_global_logger from flask_app.general.通用功能函数 import get_global_logger
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 regex.search(r'目\s*录', cleaned_text, regex.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, def extract_pages_tobidders_notice(pdf_path, output_folder, begin_pattern, begin_page, common_header,
is_secondary_match): is_secondary_match):
pdf_document = PdfReader(pdf_path) pdf_document = PdfReader(pdf_path)
@ -75,6 +18,8 @@ def extract_pages_tobidders_notice(pdf_path, output_folder, begin_pattern, begin
mid_page = None mid_page = None
end_page = None end_page = None
chapter_type = None # 用于存储“章”或“部分” chapter_type = None # 用于存储“章”或“部分”
combined_mid_pattern= None
end_pattern = None
for i, page in enumerate(pdf_document.pages): for i, page in enumerate(pdf_document.pages):
text = page.extract_text() or "" text = page.extract_text() or ""
@ -87,7 +32,7 @@ def extract_pages_tobidders_notice(pdf_path, output_folder, begin_pattern, begin
match = regex.search(begin_pattern, cleaned_text) match = regex.search(begin_pattern, cleaned_text)
if match and i > begin_page: if match and i > begin_page:
start_page = i start_page = i
matched_text = match.group(0) # 获取整个匹配的文本 matched_text: str = match.group(0) # 获取整个匹配的文本
if '章' in matched_text: if '章' in matched_text:
chapter_type = '章' chapter_type = '章'
elif '部分' in matched_text: elif '部分' in matched_text:
@ -175,14 +120,12 @@ def extract_pages_tobidders_notice(pdf_path, output_folder, begin_pattern, begin
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。") 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 "", "" return "", ""
path1 = save_pages_to_new_pdf(pdf_path, output_folder, "tobidders_notice_table", start_page, mid_page, path1 = save_extracted_pages(pdf_path, output_folder, start_page, mid_page, "tobidders_notice_table", common_header)
common_header) path2 = save_extracted_pages(pdf_path, output_folder, mid_page, end_page, "tobidders_notice", common_header)
path2 = save_pages_to_new_pdf(pdf_path, output_folder, "tobidders_notice", mid_page, end_page, common_header)
return path1, path2 return path1, path2
def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix, common_header, 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 # 打开PDF文件
pdf_document = PdfReader(pdf_path) pdf_document = PdfReader(pdf_path)
start_page = None start_page = None
@ -194,7 +137,6 @@ def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_patter
text = page.extract_text() text = page.extract_text()
if text: if text:
cleaned_text = clean_page_content(text, common_header) cleaned_text = clean_page_content(text, common_header)
# if is_secondary_match and regex.search(exclusion_pattern, cleaned_text): # 跳过投标人须知正文中的"投标文件的组成"
if regex.search(exclusion_pattern, cleaned_text): if regex.search(exclusion_pattern, cleaned_text):
continue continue
if regex.search(begin_pattern, cleaned_text) and i >= begin_page: if regex.search(begin_pattern, cleaned_text) and i >= begin_page:
@ -215,7 +157,7 @@ def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_patter
print(f"{output_suffix} first: 未找到起始或结束页在文件 {pdf_path} 中！") print(f"{output_suffix} first: 未找到起始或结束页在文件 {pdf_path} 中！")
return [""] return [""]
else: else:
return [save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page, common_header)] return [save_extracted_pages(pdf_path, output_folder, start_page, end_page, output_suffix, common_header)]
def extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, last_begin_index): def extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, last_begin_index):
@ -277,7 +219,7 @@ def extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, l
print(f"{output_suffix} twice: 未找到起始或结束页在文件 {pdf_path} 中！") print(f"{output_suffix} twice: 未找到起始或结束页在文件 {pdf_path} 中！")
return [] return []
else: else:
return [save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page, common_header)] return [save_extracted_pages(pdf_path, output_folder, start_page, end_page, output_suffix, common_header)]
elif output_suffix == "invalid": elif output_suffix == "invalid":
pdf_document = PdfReader(pdf_path) pdf_document = PdfReader(pdf_path)
total_pages = len(pdf_document.pages) total_pages = len(pdf_document.pages)
@ -285,7 +227,7 @@ def extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, l
total = int(total_pages * 2 / 3) total = int(total_pages * 2 / 3)
start_page = last_begin_index start_page = last_begin_index
end_page = min(90, total) end_page = min(90, total)
return [save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page, common_header)] return [save_extracted_pages(pdf_path, output_folder, start_page, end_page, output_suffix, common_header)]
else: else:
print(f"{output_suffix} twice: 未定义的输出后缀。") print(f"{output_suffix} twice: 未定义的输出后缀。")
return [] return []
@ -294,32 +236,29 @@ def extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, l
return [] return []
def truncate_pdf_main_engineering(input_path, output_folder, selection,logger): def truncate_pdf_main_engineering(input_path, output_folder, selection,logger,output_suffix="default"):
if os.path.isdir(input_path): try:
generated_files = [] # 内嵌的处理单个文件的函数
for file_name in os.listdir(input_path): def process_single_file(file_path, output_folder, selection):
if file_name.endswith('.pdf'): try:
file_path = os.path.join(input_path, file_name) # 获取起始和通用页眉
files = truncate_pdf_main_engineering(file_path, output_folder, selection) common_header, last_begin_index = get_start_and_common_header(file_path, 20)
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,20)
# print(last_begin_index)
if selection == 1: if selection == 1:
# Selection 1: 招标公告 # Selection 1: 招标公告
pattern_pairs = [ pattern_pairs = [
( (
regex.compile( regex.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'), 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'
regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', regex.MULTILINE) ),
regex.compile(
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', regex.MULTILINE
)
), ),
( (
regex.compile( regex.compile(
r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:招标公告|磋商公告|谈判公告|邀请书|邀请函|投标邀请|磋商邀请|谈判邀请)[\)）]?\s*$', r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:招标公告|磋商公告|谈判公告|邀请书|邀请函|投标邀请|磋商邀请|谈判邀请)[\)）]?\s*$',
regex.MULTILINE), regex.MULTILINE
),
regex.compile( regex.compile(
r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知(?:前附表)?\s*$', r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知(?:前附表)?\s*$',
regex.MULTILINE regex.MULTILINE
@ -331,44 +270,51 @@ def truncate_pdf_main_engineering(input_path, output_folder, selection,logger):
# Selection 2: 评标办法 # Selection 2: 评标办法
pattern_pairs = [ pattern_pairs = [
( (
regex.compile(r'^第[一二三四五六七八九十]+(?:章|部分)\s*(?=.*(?:磋商|谈判|评标|评定|评审))(?=.*(?:办法|方法))',regex.MULTILINE), regex.compile(
# Alternative begin pattern r'^第[一二三四五六七八九十]+(?:章|部分)\s*(?=.*(?:磋商|谈判|评标|评定|评审))(?=.*(?:办法|方法))',
regex.compile(r'^第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+|[：:]清标报告\s*$|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)评标(方法|办法)正文\s*$|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:评标|定标)详细程序\s*$',regex.MULTILINE) regex.MULTILINE
),
# Alternative end pattern # Alternative end pattern
regex.compile(
r'^第[一二三四五六七八九十1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+|[：:]清标报告\s*$|'
r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)评标(方法|办法)正文\s*$|'
r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:评标|定标)详细程序\s*$',
regex.MULTILINE
)
), ),
( (
regex.compile( regex.compile(
r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)' # 确保前面不是“见” r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)'
r'第[一二三四五六七八九十1-9]+(?:章|部分)\s*' # 匹配“第X章”或“第X部分” r'第[一二三四五六七八九十1-9]+(?:章|部分)\s*'
r'[\u4e00-\u9fff、()（）]*?' # 匹配允许的字符（中文、顿号、括号） r'[\u4e00-\u9fff、()（）]*?'
r'(?=.*(?:磋商|谈判|评标|评定|评审))' # 确保包含“磋商”、“谈判”、“评标”、“评定”或“评审” r'(?=.*(?:磋商|谈判|评标|评定|评审))'
r'(?=.*(?:办法|方法))' # 确保包含“办法”或“方法” r'(?=.*(?:办法|方法))'
r'[\u4e00-\u9fff、()（）]*\s*$' # 继续匹配允许的字符直到行尾 r'[\u4e00-\u9fff、()（）]*\s*$|'
r'|\s*评标(办法|方法)前附表\s*$', # 或匹配“评标办法前附表”或“评标方法前附表” r'\s*评标(办法|方法)前附表\s*$',
regex.MULTILINE regex.MULTILINE
), ),
regex.compile(r'第[一二三四五六七八九十1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$', regex.MULTILINE) regex.compile(
r'第[一二三四五六七八九十1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$',
regex.MULTILINE
)
) )
] ]
output_suffix = "evaluation_method" output_suffix = "evaluation_method"
# TODO:exclusion
elif selection == 3: elif selection == 3:
# Selection 3: 资格审查条件 # Selection 3: 资格审查条件
pattern_pairs = [ pattern_pairs = [
# (
# regex.compile(r'^(?:附录(?:[一1])?[：:]|附件(?:[一1])?[：:]|附表(?:[一1])?[：:]).*(?:资质|能力|信誉).*$|^第[一二三四五六七八九十百千]+(?:章|部分).*?(资格).*',
# regex.MULTILINE),
# regex.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)).*$'
# r'^第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+', regex.MULTILINE)
# ),
( (
regex.compile( regex.compile(
r'^(?:附录(?:[一1])?[：:]|附件(?:[一1])?[：:]|附表(?:[一1])?[：:]).*(?:资质|能力|信誉).*$|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]*资格[\u4e00-\u9fff、()（）]*\s*$', r'^(?:附录(?:[一1])?[：:]|附件(?:[一1])?[：:]|附表(?:[一1])?[：:]).*(?:资质|能力|信誉).*$|'
regex.MULTILINE), r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九1-9]+(?:章|部分)\s*'
r'[\u4e00-\u9fff、()（）]*资格[\u4e00-\u9fff、()（）]*\s*$',
regex.MULTILINE
),
regex.compile( regex.compile(
r'^(?:附录[一二三四五六七八九1-9]*[：:]|附件[一二三四五六七八九1-9]*[：:]|附表[一二三四五六七八九1-9]*[：:])(?!.*(?:资质|能力|信誉)).*|' r'^(?:附录[一二三四五六七八九1-9]*[：:]|附件[一二三四五六七八九1-9]*[：:]|附表[一二三四五六七八九1-9]*[：:])(?!.*(?:资质|能力|信誉)).*|'
r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$', regex.MULTILINE) r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+',
regex.MULTILINE
)
) )
] ]
output_suffix = "qualification" output_suffix = "qualification"
@ -377,11 +323,14 @@ def truncate_pdf_main_engineering(input_path, output_folder, selection,logger):
pattern_pairs = [ pattern_pairs = [
( (
regex.compile( regex.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|(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知前附表)\s*$', r'(?:第[一二三四五六七八九十百千]+(?:章|部分)\s*(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知|'
regex.MULTILINE), r'(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知前附表)\s*$',
regex.MULTILINE
),
regex.compile( regex.compile(
r'第[一二三四五六七八九十]+(?:章|部分)\s*[\u4e00-\u9fff]+|^评标(方法|办法)前附表|^附录(?:一)?[：:]|^附件(?:一)?[：:]|^附表(?:一)?[：:]', r'第[一二三四五六七八九十]+(?:章|部分)\s*[\u4e00-\u9fff]+|^评标(方法|办法)前附表|^附录(?:一)?[：:]|^附件(?:一)?[：:]|^附表(?:一)?[：:]',
regex.MULTILINE) regex.MULTILINE
)
), ),
( (
regex.compile( regex.compile(
@ -391,7 +340,8 @@ def truncate_pdf_main_engineering(input_path, output_folder, selection,logger):
), ),
regex.compile( regex.compile(
r'第[一二三四五六七八九十]+(?:章|部分)\s*[\u4e00-\u9fff]+|^评标(方法|办法)前附表|^附录(?:一)?[：:]|^附件(?:一)?[：:]|^附表(?:一)?[：:]', r'第[一二三四五六七八九十]+(?:章|部分)\s*[\u4e00-\u9fff]+|^评标(方法|办法)前附表|^附录(?:一)?[：:]|^附件(?:一)?[：:]|^附表(?:一)?[：:]',
regex.MULTILINE) regex.MULTILINE
)
) )
] ]
output_suffix = "tobidders_notice" output_suffix = "tobidders_notice"
@ -400,16 +350,25 @@ def truncate_pdf_main_engineering(input_path, output_folder, selection,logger):
pattern_pairs = [ pattern_pairs = [
( (
regex.compile( regex.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'), 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'
regex.compile(r'第[一二三四五六七八九十]+章\s*合同|[：:]清标报告|^第二卷', regex.MULTILINE) ),
regex.compile(
r'第[一二三四五六七八九十]+章\s*合同|[：:]清标报告|^第二卷',
regex.MULTILINE
)
), ),
( (
regex.compile(r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:招标公告|磋商公告|谈判公告|邀请书|邀请函|投标邀请|磋商邀请|谈判邀请)[\)）]?\s*$', regex.MULTILINE), regex.compile(
regex.compile(r'第[一二三四五六七八九十]+章\s*合同|[：:]清标报告|^第二卷', regex.MULTILINE) r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:招标公告|磋商公告|谈判公告|邀请书|邀请函|投标邀请|磋商邀请|谈判邀请)[\)）]?\s*$',
regex.MULTILINE
),
regex.compile(
r'第[一二三四五六七八九十]+章\s*合同|[：:]清标报告|^第二卷',
regex.MULTILINE
)
) )
] ]
output_suffix = "invalid" output_suffix = "invalid"
else: else:
print("无效的选择:请选择1-5") print("无效的选择:请选择1-5")
return [""] return [""]
@ -423,35 +382,48 @@ def truncate_pdf_main_engineering(input_path, output_folder, selection,logger):
4: 3, # 前附表 4: 3, # 前附表
5: 0 # 无效标 5: 0 # 无效标
}.get(selection, 0) }.get(selection, 0)
if selection == 4: # 投标人须知 if selection == 4: # 投标人须知
output_paths = list( output_paths = list(
extract_pages_tobidders_notice(input_path, output_folder, begin_pattern, begin_page, common_header, extract_pages_tobidders_notice(
is_secondary_match)) file_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): if output_paths and any(os.path.isfile(f) for f in output_paths):
return output_paths return output_paths
else: else:
# print(f"Selection {selection}: 使用组合提取函数失败。尝试下一个模式对。") # print(f"Selection {selection}: 使用组合提取函数失败。尝试下一个模式对。")
continue continue
output_paths = extract_pages( output_paths = extract_pages(
input_path, file_path,
output_folder, output_folder,
begin_pattern, begin_pattern,
begin_page=begin_page, begin_page=begin_page,
end_pattern=end_pattern, end_pattern=end_pattern,
output_suffix=output_suffix, output_suffix=output_suffix,
common_header=common_header, common_header=common_header
is_secondary_match=is_secondary_match
) )
if output_paths and any(os.path.isfile(f) for f in output_paths): 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。") # print(f"Selection {selection}: 使用模式对 {idx} 成功提取。")
return output_paths # Return immediately upon successful extraction return output_paths # 成功提取后立即返回
else: else:
# print(f"Selection {selection}: 使用模式对 {idx} 失败。尝试下一个模式对。") # print(f"Selection {selection}: 使用模式对 {idx} 失败。尝试下一个模式对。")
continue continue
# If all pattern pairs failed, attempt a fallback # 如果所有模式对都失败，尝试回退
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。") 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) fallback_result = extract_pages_twice(
file_path,
output_folder,
output_suffix,
common_header,
last_begin_index
)
if fallback_result and any(os.path.isfile(f) for f in fallback_result): if fallback_result and any(os.path.isfile(f) for f in fallback_result):
return fallback_result return fallback_result
else: else:
@ -459,9 +431,29 @@ def truncate_pdf_main_engineering(input_path, output_folder, selection,logger):
empty_returns = ["", ""] if selection == 4 else [""] empty_returns = ["", ""] if selection == 4 else [""]
logger.error(f"Selection {selection}: 回退提取失败，返回空字符串。") logger.error(f"Selection {selection}: 回退提取失败，返回空字符串。")
return empty_returns return empty_returns
except Exception as e:
logger.error(f"Error in processing file '{file_path}': {e}")
return [""] * (2 if selection == 4 else 1)
# 检查是否为文件夹
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 = process_single_file(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'):
return process_single_file(input_path, output_folder, selection)
else: else:
print("Invalid input path. It is neither a PDF file nor a directory containing PDF files.") print("提供的路径既不是文件夹也不是PDF文件。")
return [''] return [""] * (2 if selection == 4 else 1)
except Exception as e:
print(f"Error in truncate_pdf_main_goods: {e}")
return [""] * (2 if selection == 4 else 1)
if __name__ == "__main__": if __name__ == "__main__":
logger=get_global_logger("123") logger=get_global_logger("123")
@ -472,10 +464,6 @@ if __name__ == "__main__":
# pdf_path = r"C:\Users\Administrator\Desktop\招标文件\招标02.pdf" # pdf_path = r"C:\Users\Administrator\Desktop\招标文件\招标02.pdf"
# input_path=r"C:\Users\Administrator\Desktop\招标文件\招标test文件夹\zbtest8.pdf" # input_path=r"C:\Users\Administrator\Desktop\招标文件\招标test文件夹\zbtest8.pdf"
output_folder = r"C:\Users\Administrator\Desktop\fsdownload\91399aa4-1ee8-447d-a05b-03cd8d15ced5\tmp" output_folder = r"C:\Users\Administrator\Desktop\fsdownload\91399aa4-1ee8-447d-a05b-03cd8d15ced5\tmp"
# selections = [1, 4] # 仅处理 selection 4、1
selections=[5]
# files=truncate_pdf_multiple(pdf_path,output_folder,logger,'engineering',selections)
# print(files)
# selection = 1 # 例如：1 - 招标公告, 2 - 评标办法, 3 -资格审查条件 4-投标人须知前附表+正文 5-无效标 # selection = 1 # 例如：1 - 招标公告, 2 - 评标办法, 3 -资格审查条件 4-投标人须知前附表+正文 5-无效标
# generated_files = truncate_pdf_main_engineering(pdf_path, output_folder, selection,logger) # generated_files = truncate_pdf_main_engineering(pdf_path, output_folder, selection,logger)
# print(generated_files) # print(generated_files)

234
flask_app/货物标/截取pdf货物标版.py
View File

@ -1,25 +1,12 @@
import logging
from PyPDF2 import PdfReader, PdfWriter from PyPDF2 import PdfReader, PdfWriter
import regex # 导入正则表达式库 import regex # 导入正则表达式库
import os # 用于文件和文件夹操作 import os # 用于文件和文件夹操作
from flask_app.general.clean_pdf import clean_page_content, extract_common_header from flask_app.general.clean_pdf import clean_page_content, extract_common_header
from flask_app.general.format_change import docx2pdf
from flask_app.general.merge_pdfs import merge_and_cleanup from flask_app.general.merge_pdfs import merge_and_cleanup
from flask_app.general.截取pdf通用函数 import get_start_and_common_header from flask_app.general.截取pdf通用函数 import get_start_and_common_header, save_extracted_pages, is_pdf_or_doc, \
convert_to_pdf
from flask_app.general.通用功能函数 import get_global_logger from flask_app.general.通用功能函数 import get_global_logger
def is_pdf_or_doc(filename):
# 判断文件是否为PDF或Word文档
return filename.lower().endswith(('.pdf', '.doc', '.docx'))
def convert_to_pdf(file_path):
# 假设 docx2pdf 函数已经被定义，这里仅根据文件扩展名来决定是否需要转换
if file_path.lower().endswith(('.doc', '.docx')):
return docx2pdf(file_path)
return file_path
def extract_pages_generic(pdf_document, begin_pattern, end_pattern, begin_page, common_header, exclusion_pattern=None, def extract_pages_generic(pdf_document, begin_pattern, end_pattern, begin_page, common_header, exclusion_pattern=None,
output_suffix="normal"): output_suffix="normal"):
start_page = None start_page = None
@ -52,7 +39,7 @@ def extract_pages_generic(pdf_document, begin_pattern, end_pattern, begin_page,
return start_page, end_page return start_page, end_page
def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix): def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix,logger):
try: try:
common_header = extract_common_header(pdf_path) common_header = extract_common_header(pdf_path)
pdf_document = PdfReader(pdf_path) pdf_document = PdfReader(pdf_path)
@ -71,11 +58,9 @@ def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_patter
# if start_page is None or end_page is None or mid_page is None: # if start_page is None or end_page is None or mid_page is None:
# print(f"first: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！尝试备用提取策略。") # print(f"first: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！尝试备用提取策略。")
# return extract_pages_twice_tobidders_notice(pdf_path, output_folder, output_suffix, common_header,begin_page) # return extract_pages_twice_tobidders_notice(pdf_path, output_folder, output_suffix, common_header,begin_page)
path1 = save_extracted_pages(pdf_document, start_page, mid_page, pdf_path, output_folder, path1 = save_extracted_pages(pdf_path,output_folder,start_page, mid_page, "tobidders_notice_part1",common_header)
"tobidders_notice_part1")
if mid_page != end_page: if mid_page != end_page:
path2 = save_extracted_pages(pdf_document, mid_page, end_page, pdf_path, output_folder, path2 = save_extracted_pages(pdf_path,output_folder, mid_page, end_page,"tobidders_notice_part2",common_header)
"tobidders_notice_part2")
else: else:
path2=path1 path2=path1
return path1, path2 return path1, path2
@ -96,13 +81,13 @@ def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_patter
# 如果未匹配到结束页，默认截取到文件末尾 # 如果未匹配到结束页，默认截取到文件末尾
end_page = total_pages end_page = total_pages
print(f"{output_suffix}: 未找到结束页，默认截取到文件末尾。") print(f"{output_suffix}: 未找到结束页，默认截取到文件末尾。")
return save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix) return save_extracted_pages(pdf_path, output_folder,start_page, end_page, output_suffix,common_header)
if start_page is None or end_page is None: if start_page is None or end_page is None:
print(f"first: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！尝试备用提取策略。") print(f"first: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！尝试备用提取策略。")
return extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, begin_page) return extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, begin_page,logger)
elif output_suffix == "qualification1": elif output_suffix == "qualification1":
truncate_pdf_main_goods(pdf_path, output_folder, 2, "qualification3") # 合并'资格审查'章节和'评标办法'章节 truncate_pdf_main_goods(pdf_path, output_folder, 2, logger,"qualification3") # 合并'资格审查'章节和'评标办法'章节
return save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix) return save_extracted_pages(pdf_path, output_folder,start_page, end_page, output_suffix,common_header)
except Exception as e: except Exception as e:
print(f"Error processing {pdf_path}: {e}") print(f"Error processing {pdf_path}: {e}")
return "" return ""
@ -181,7 +166,6 @@ def extract_pages_tobidders_notice(pdf_path, begin_pattern, begin_page, common_h
start_page = None start_page = None
mid_page = None mid_page = None
end_page = None end_page = None
chapter_type = None # 用于存储“章”或“部分”
combined_mid_pattern = None # 中间页的组合模式 combined_mid_pattern = None # 中间页的组合模式
pdf_document = PdfReader(pdf_path) pdf_document = PdfReader(pdf_path)
for i, page in enumerate(pdf_document.pages): for i, page in enumerate(pdf_document.pages):
@ -197,8 +181,7 @@ def extract_pages_tobidders_notice(pdf_path, begin_pattern, begin_page, common_h
match = regex.search(local_begin_pattern, cleaned_text) match = regex.search(local_begin_pattern, cleaned_text)
if match and i > begin_page: if match and i > begin_page:
start_page = i start_page = i
matched_text = match.group(0) # 获取整个匹配的文本 matched_text:str = match.group(0) # 获取整个匹配的文本
# 如果未提供固定的 end_pattern，则根据匹配的章节类型动态生成 # 如果未提供固定的 end_pattern，则根据匹配的章节类型动态生成
if not local_end_pattern: if not local_end_pattern:
if '章' in matched_text: if '章' in matched_text:
@ -426,7 +409,7 @@ def extract_pages_qualification(pdf_document, begin_page, common_header):
return start_page, end_page return start_page, end_page
def extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, begin_page): def extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, begin_page, logger):
try: try:
exclusion_pattern = regex.compile( exclusion_pattern = regex.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') 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')
@ -467,7 +450,7 @@ def extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, b
new_file.write(original_file.read()) new_file.write(original_file.read())
return new_file_path return new_file_path
else: else:
temp = truncate_pdf_main_goods(pdf_path, output_folder, 2, "qualification2") temp = truncate_pdf_main_goods(pdf_path, output_folder, 2,logger, "qualification2")
if len(temp) > 0: if len(temp) > 0:
return temp[0] return temp[0]
else: else:
@ -475,89 +458,29 @@ def extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, b
else: else:
print(f"second: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！") print(f"second: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！")
return "" return ""
return save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix) return save_extracted_pages(pdf_path, output_folder,start_page, end_page, output_suffix,common_header)
except Exception as e: except Exception as e:
print(f"Error in extract_pages_twice: {e}") print(f"Error in extract_pages_twice: {e}")
return "" return ""
def truncate_pdf_main_goods(input_path, output_folder, selection,logger, output_suffix="default"):
def save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix):
try: try:
# 检查 start_page 和 end_page 是否为 None # Function to handle processing of a single file
if start_page is None or end_page is None: def process_single_file(input_path, output_folder, selection, output_suffix):
print("Error: start_page 或 end_page 为 None")
return ""
base_file_name = os.path.splitext(os.path.basename(pdf_path))[0]
output_pdf_path = os.path.join(output_folder, f"{base_file_name}_{output_suffix}.pdf")
if start_page < 0 or end_page >= len(pdf_document.pages) or start_page > end_page:
print(f"无效的页面范围: {start_page} 到 {end_page}")
return ""
if output_suffix == 'notice' and start_page - 1 >= 0:
before_pdf_path = os.path.join(output_folder, f"{base_file_name}_before.pdf")
before_doc = PdfWriter()
for page_num in range(0, start_page):
before_doc.add_page(pdf_document.pages[page_num])
with open(before_pdf_path, 'wb') as f:
before_doc.write(f)
# print(f"已保存页面从 0 到 {start_page - 1} 为 {before_pdf_path}")
output_doc = PdfWriter()
for page_num in range(start_page, end_page + 1):
output_doc.add_page(pdf_document.pages[page_num])
with open(output_pdf_path, 'wb') as f:
output_doc.write(f)
print(f"{output_suffix} 已截取并保存页面从 {start_page} 到 {end_page} 为 {output_pdf_path}")
return output_pdf_path
except Exception as e:
print(f"Error in save_extracted_pages: {e}")
return "" # 返回空字符串
def truncate_pdf_main_goods(input_path, output_folder, selection, output_suffix="default"):
try:
# 检查是否为文件夹
if os.path.isdir(input_path):
generated_files = []
for file_name in os.listdir(input_path):
file_path = os.path.join(input_path, file_name)
if is_pdf_or_doc(file_path):
result = process_input(file_path, output_folder, selection, output_suffix)
if isinstance(result, tuple):
generated_files.extend([f if f else "" for f in result])
else:
generated_files.append(result)
return generated_files
# 单文件情况
elif os.path.isfile(input_path) and is_pdf_or_doc(input_path):
return process_input(input_path, output_folder, selection, output_suffix)
else:
print("提供的路径既不是文件夹也不是PDF文件。")
return ['']
except Exception as e:
print(f"Error in truncate_pdf_main: {e}")
return [''] # 返回空字符串
def process_input(input_path, output_folder, selection, output_suffix):
try: try:
# 创建输出文件夹 # 创建输出文件夹
if not os.path.exists(output_folder): if not os.path.exists(output_folder):
os.makedirs(output_folder) os.makedirs(output_folder)
# 获取起始和通用页眉 # 获取起始和通用页眉
common_header, last_begin_index = get_start_and_common_header(input_path,10) common_header, last_begin_index = get_start_and_common_header(input_path, 10)
begin_page = last_begin_index if last_begin_index != 0 else { begin_page = last_begin_index if last_begin_index != 0 else {
4: 1, 4: 1,
2: 5, 2: 5,
3: 5, 3: 5,
1: 0, 1: 0,
5: 3 5: 3,
6: 0 # Added default for selection 6 if needed
}.get(selection, 0) }.get(selection, 0)
# 根据选择设置对应的模式和结束模式 # 根据选择设置对应的模式和结束模式
@ -566,42 +489,55 @@ def process_input(input_path, output_folder, selection, output_suffix):
r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:招标公告|磋商公告|谈判公告|邀请书|邀请函|投标邀请|磋商邀请|谈判邀请)[\)）]?\s*$', r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:招标公告|磋商公告|谈判公告|邀请书|邀请函|投标邀请|磋商邀请|谈判邀请)[\)）]?\s*$',
regex.MULTILINE regex.MULTILINE
) )
end_pattern = regex.compile(r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九十1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知前附表\s*$', regex.MULTILINE) end_pattern = regex.compile(
r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九十1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$|'
r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知前附表\s*$',
regex.MULTILINE
)
local_output_suffix = "notice" local_output_suffix = "notice"
elif selection == 2: elif selection == 2:
begin_pattern = regex.compile( begin_pattern = regex.compile(
r'^第[一二三四五六七八九十]+(?:章|部分)\s*(?=.*(?:磋商|谈判|评标|评定|评审))(?=.*(?:办法|方法|内容))') r'^第[一二三四五六七八九十]+(?:章|部分)\s*(?=.*(?:磋商|谈判|评标|评定|评审))(?=.*(?:办法|方法|内容))'
end_pattern = regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+') )
end_pattern = regex.compile(
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+'
)
local_output_suffix = "evaluation_method" local_output_suffix = "evaluation_method"
elif selection == 3: elif selection == 3:
begin_pattern = regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(资格审查).*', regex.MULTILINE) begin_pattern = regex.compile(
end_pattern = regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', regex.MULTILINE) r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(资格审查).*', regex.MULTILINE
)
end_pattern = regex.compile(
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', regex.MULTILINE
)
local_output_suffix = "qualification1" local_output_suffix = "qualification1"
elif selection == 4: elif selection == 4:
begin_pattern = regex.compile( begin_pattern = regex.compile(
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知+|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知前附表\s*$', 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+|'
regex.MULTILINE) r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知前附表\s*$',
regex.MULTILINE
)
end_pattern = None end_pattern = None
local_output_suffix = "tobidders_notice" local_output_suffix = "tobidders_notice"
elif selection == 5: elif selection == 5:
begin_pattern = regex.compile( begin_pattern = regex.compile(
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:服务|项目|商务|技术).*?要求|^第[一二三四五六七八九十百千]+(?:章|部分)(?!.*说明).*(?:采购内容|采购要求|需求).*') # 包头中有一章'采购相关说明' r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:服务|项目|商务|技术).*?要求|'
end_pattern = regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+') r'^第[一二三四五六七八九十百千]+(?:章|部分)(?!.*说明).*(?:采购内容|采购要求|需求).*'
)
end_pattern = regex.compile(
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+'
)
local_output_suffix = "procurement" local_output_suffix = "procurement"
# begin_pattern = regex.compile(
# r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:服务|项目|商务).*?要求|'
# r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:采购|技术标准).*|'
# r'^[一二三四五六七八九十百千]+、\s*采购清单', regex.MULTILINE)
# end_pattern = regex.compile(
# r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', regex.MULTILINE)
elif selection == 6: elif selection == 6:
begin_pattern = regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:格式).*') begin_pattern = regex.compile(
end_pattern = regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', regex.MULTILINE) r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:格式).*'
)
end_pattern = regex.compile(
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', regex.MULTILINE
)
local_output_suffix = "format" local_output_suffix = "format"
else: else:
print("无效的选择:请选择1-5") print("无效的选择:请选择1-6")
return [''] return ['']
# 如果传入的 output_suffix 是 'default'，则使用本地生成的 output_suffix # 如果传入的 output_suffix 是 'default'，则使用本地生成的 output_suffix
@ -610,24 +546,61 @@ def process_input(input_path, output_folder, selection, output_suffix):
# 将原先的 process_files 逻辑合并到此处 # 将原先的 process_files 逻辑合并到此处
pdf_path = convert_to_pdf(input_path) pdf_path = convert_to_pdf(input_path)
result = extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix) result = extract_pages(
pdf_path,
output_folder,
begin_pattern,
begin_page,
end_pattern,
output_suffix,
logger
)
# 根据提取结果以及不同的 output_suffix 进行处理 # 根据提取结果以及不同的 output_suffix 进行处理
if result: if result:
if output_suffix == "tobidders_notice": if output_suffix == "tobidders_notice":
# 确保返回的是元组，并将其中的 None 转换为 "" # 确保返回的是元组，并将其中的 None 转换为 ""
if isinstance(result, tuple) and len(result) == 2:
path1, path2 = result path1, path2 = result
return [path1 or "", path2 or ""] return [path1 or "", path2 or ""]
else:
logger.error("Unexpected result format for 'tobidders_notice'")
return ["",""]
elif output_suffix == "qualification1": elif output_suffix == "qualification1":
merge_and_cleanup(result, "qualification3") merge_and_cleanup(result, "qualification3")
return [result or ""] return [result or ""]
else:
return [result or ""] return [result or ""]
return [""] * (2 if selection == 4 else 1)
return [""]
except Exception as e: except Exception as e:
print(f"Error in process_input: {e}") logger.error(f"Error in processing file '{input_path}': {e}")
return [''] return [""] * (2 if selection == 4 else 1)
# 检查是否为文件夹
if os.path.isdir(input_path):
generated_files = []
for file_name in os.listdir(input_path):
file_path = os.path.join(input_path, file_name)
if is_pdf_or_doc(file_path):
result = process_single_file(file_path, output_folder, selection, output_suffix)
if isinstance(result, tuple):
generated_files.extend([f if f else "" for f in result])
else:
generated_files.append(result)
return generated_files
# 单文件情况
elif os.path.isfile(input_path) and is_pdf_or_doc(input_path):
return process_single_file(input_path, output_folder, selection, output_suffix)
else:
logger.error("提供的路径既不是文件夹也不是PDF文件。")
return [""] * (2 if selection == 4 else 1)
except Exception as e:
logger.error(f"Error in truncate_pdf_main_goods: {e}")
return [""] * (2 if selection == 4 else 1) # 返回空字符串
# TODO:交通智能系统和招标(1)(1)文件有问题 包头 绍兴 工程标中，判断是符合性审查之后，可以将它们设为同一章 # TODO:交通智能系统和招标(1)(1)文件有问题 包头 绍兴 工程标中，判断是符合性审查之后，可以将它们设为同一章
@ -636,15 +609,12 @@ def process_input(input_path, output_folder, selection, output_suffix):
if __name__ == "__main__": 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"
# input_path="C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\zbtest4_evaluation_method.pdf" # pdf_path="C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles"
# 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\货物标\zbfiles\zbtest4_evaluation_method.pdf" pdf_path=r"C:\Users\Administrator\Desktop\货物标\zbfiles\zbtest4_evaluation_method.pdf"
output_folder = r"C:\Users\Administrator\Desktop\fsdownload\ff2acdba-3a55-48a7-aa7a-61d9f89b909a\tmp" output_folder = r"C:\Users\Administrator\Desktop\货物标\output33"
# 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"
# selections = [1, 4] selection = 3 # 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
# files = truncate_pdf_multiple(pdf_path, output_folder,logger,selections) generated_files = truncate_pdf_main_goods(pdf_path, output_folder, selection,logger)
# print(files) print(generated_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
# generated_files = truncate_pdf_main_goods(pdf_path, output_folder, selection)
# print(generated_files)