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 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) if re.search(begin_pattern, cleaned_text) and i > begin_page: start_page = i if start_page is not None and re.search(end_pattern, cleaned_text) and i > (start_page+1): 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: print(f"未找到起始或结束页在文件 {pdf_path} 中！") return None # 创建一个新的PDF文档保存截取的页面 base_file_name = os.path.splitext(os.path.basename(pdf_path))[0] # Get the base name without extension output_pdf_path = os.path.join(output_folder, f"{base_file_name}_{output_suffix}.pdf") output_doc = PdfWriter() # 添加需要的页面，从 start_page 开始，包括 end_page 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} 到 {end_page} 为 {output_pdf_path}") return output_pdf_path 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[一二三四五六七八九十百千]+章.*?(?:项目|服务|商务).*?要求') begin_page = 5 end_pattern = re.compile(r'第[一二三四五六七八九十百千]+章\s*(资格审查|评标方法|评审办法)') # 示例文本进行测试 output_suffix = "tobidders_notice_table" 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, 2): files = truncate_pdf_main(input_path, output_folder, selection) truncate_files.extend(files) return truncate_files if __name__ == "__main__": input_path = "C:\\Users\\Administrator\\WPSDrive\\292826853\\WPS云盘\\应用\\输出为PDF\\公安局音视频监控系统设备采购项目(定稿）_20240829133603.pdf" output_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\output1" # truncate_pdf_multiple(input_path,output_folder) selection = 1 # 例如：1 - 投标人须知前附表, 2 - 评标办法, 3 - 投标人须知正文 4-招标公告-合同条款前 generated_files = truncate_pdf_main(input_path, output_folder, selection) # print("生成的文件:", generated_files)