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 from flask_app.main.format_change import docx2pdf def clean_page_content(text, common_header): # 首先删除抬头公共部分 if common_header: # 确保有公共抬头才进行替换 for header_line in common_header.split('\n'): if header_line.strip(): # 只处理非空行 # 替换首次出现的完整行 text = re.sub(r'^' + re.escape(header_line.strip()) + r'\n?', '', text, count=1) # 删除页码 eg:89/129 这个代码分三步走可以把89/129完全删除 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 text = re.sub(r'\s+\d+\s*$', '', text) # 删除结尾的页码 text = re.sub(r'\s*\/\s*\d+\s*', '', text) # 删除形如 /129 的页码 return text def extract_common_header(pdf_path): pdf_document = PdfReader(pdf_path) headers = [] total_pages = len(pdf_document.pages) middle_page = total_pages // 2 # 计算中间页 # 确保中间页前后各一页（共3页），如果不足3页，则尽可能取足 start_page = max(0, middle_page - 1) num_pages_to_read = 3 for i in range(start_page, min(start_page + num_pages_to_read, total_pages)): page = pdf_document.pages[i] text = page.extract_text() or "" if text: # 只取每页的前三行 first_lines = text.strip().split('\n')[:3] headers.append(first_lines) if len(headers) < 2: return "" # 如果没有足够的页来比较，返回空字符串 # 寻找每一行中的公共部分 common_headers = [] for lines in zip(*headers): # 在每一行中寻找公共单词 common_line = set(lines[0].split()).intersection(*[set(line.split()) for line in lines[1:]]) if common_line: common_headers.append(' '.join(common_line)) return '\n'.join(common_headers) 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 process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix): if not os.path.exists(output_folder): os.makedirs(output_folder) generated_files = [] if os.path.isdir(input_path): # 遍历文件夹内的所有PDF文件 for file in os.listdir(input_path): file_path = os.path.join(input_path, file) if is_pdf_or_doc(file): pdf_path = convert_to_pdf(file_path) output_pdf_path = extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix) if output_pdf_path: generated_files.append(output_pdf_path) 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: generated_files.append(output_pdf_path) else: print("提供的路径既不是文件夹也不是PDF文件。") return generated_files def extract_pages_twice(pdf_path, output_folder, output_suffix,common_header): pdf_document = PdfReader(pdf_path) begin_page=5 start_page = None end_page = None # 定义用于检测是否包含"文件的构成"的正则表达式 exclusion_pattern = re.compile(r'文件的构成|文件的组成') if output_suffix == "procurement": begin_pattern = re.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', re.MULTILINE ) end_pattern = re.compile( r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', re.MULTILINE ) for i in range(len(pdf_document.pages)): page = pdf_document.pages[i] text = page.extract_text() or "" cleaned_text = clean_page_content(text,common_header) if re.search(begin_pattern, cleaned_text) and i > begin_page and not re.search(exclusion_pattern, cleaned_text): start_page = i if start_page is not None and re.search(end_pattern, cleaned_text) and i > start_page: end_page = i break if start_page is None or end_page is None: print(f"twice: 未找到起始或结束页在文件 {pdf_path} 中！") return "" else: return save_extracted_pages(pdf_document,start_page, end_page, pdf_path,output_folder, output_suffix) def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix): try: common_header = extract_common_header(pdf_path) pdf_document = PdfReader(pdf_path) start_page = None end_page = None for i in range(len(pdf_document.pages)): page = pdf_document.pages[i] text = page.extract_text() or "" cleaned_text = clean_page_content(text,common_header) if start_page is None and 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: end_page = i break if start_page is None or end_page is None: if output_suffix == "procurement": return extract_pages_twice(pdf_path, output_folder, output_suffix,common_header) else: print(f"未找到起始或结束页在文件 {pdf_path} 中！") return None return save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix) except Exception as e: print(f"Error processing {pdf_path}: {e}") return None def save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix): 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") 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"已截取并保存页面从 {start_page} 到 {end_page} 为 {output_pdf_path}") return output_pdf_path def truncate_pdf_main(input_path, output_folder, selection): if selection == 1: # 更新的正则表达式以匹配"第x章"和"第x部分"，考虑到可能的空格和其他文字 begin_pattern = re.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.*', # r'^[一二三四五六七八九十百千]+、\s*采购清单', ) begin_page = 5 end_pattern = re.compile( r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+' ) output_suffix = "procurement" else: print("无效的选择") return None # 调用相应的处理函数 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\\Desktop\\货物标\\zbfiles\\招标文件(2).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)