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') 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') # 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): 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|评标办法|^第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff]+') # Alternative end pattern ), ( re.compile( r'第[一二三四五六七八九十1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]*?(?=.*(?:磋商|谈判|评标|评定|评审))(?=.*(?:办法|方法))[\u4e00-\u9fff、()（）]*\s*$|\s*评标(办法|方法)前附表\s*$', 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 # 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:目前merged_baseinfo没有包含投标人须知正文。 #TODO:zbtest20有问题 # 投标人须知前附表改为货物标一样的 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\zbtest4_evaluation_method.pdf" output_folder = "C:\\Users\\Administrator\\Desktop\\new招标文件\\output3" # files=truncate_pdf_multiple(input_path,output_folder) selections = [4, 1] # 仅处理 selection 4、1 files=truncate_pdf_specific_engineering(input_path,output_folder,selections) print(files) # selection = 1 # 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))