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 def clean_page_numbers(text): # 使用正则表达式删除页码 # 假设页码在文本的最开始，紧跟着文字且无空格分隔 cleaned_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 # 删除结尾的页码 cleaned_text = re.sub(r'\s+\d+\s*$', '', cleaned_text) # 删除形如 /129 的页码 cleaned_text = re.sub(r'\s*\/\s*\d+\\s*', '', cleaned_text) return cleaned_text def save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page): """从原始PDF截取指定范围的页面并保存到新的PDF文件中""" # 获取文件基本名称 base_file_name = os.path.splitext(os.path.basename(pdf_path))[0] # 构建输出文件路径 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) output_doc = PdfWriter() # 检查起始和结束页码是否有效 if start_page is not None and end_page is not None and start_page <= end_page: # 添加指定范围的页面到新的PDF文档中 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_doc.write(f) print(f"已截取并保存页面从 {start_page + 1} 到 {end_page + 1} 为 {output_pdf_path}") else: print("提供的页码范围无效。") return output_pdf_path def extract_pages_twice(pdf_path, output_folder, output_suffix): #第一次截取失败 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)' pdf_document = PdfReader(pdf_path) start_page = None end_page = None for i, page in enumerate(pdf_document.pages): text = page.extract_text() if text: cleaned_text = clean_page_numbers(text) # 如果还未找到起始页，检查当前页是否满足条件作为起始页 if start_page is None and "资格审查" in cleaned_text: if re.search(common_pattern, cleaned_text, re.MULTILINE): start_page = i # 存储符合条件的页码，页码从1开始 # 检查当前页是否满足条件作为结束页 if start_page is not None and re.search(end_pattern, cleaned_text, re.MULTILINE): if i > start_page: end_page = i # 存储符合条件的结束页码，页码从1开始 break # 可选：找到结束页后退出循环 if start_page is None or end_page is None: print(f"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) 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=1 end_page = min(90, total) return save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page) def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix): # 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_numbers(text) # 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 if output_suffix == "qualification": condition = i > start_page else: condition = i > (start_page + 1) 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 "invalid": extract_pages_twice(pdf_path, output_folder, output_suffix) else: print(f"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) 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): 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 "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|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") return None # Process the selected input return process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix) def truncate_pdf_multiple(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 #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。 if __name__ == "__main__": input_path = "C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹" output_folder = "C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹" # truncate_pdf_multiple(input_path,output_folder) selection = 5 # 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-无效标 generated_files = truncate_pdf_main(input_path, output_folder, selection) # # print("生成的文件:", generated_files)