zbparse/flask_app/general/截取pdf通用函数.py

#flask_app/general/截取pdf通用函数.py
import concurrent.futures
import os

import regex
from PyPDF2 import PdfReader, PdfWriter

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):
    common_header = extract_common_header(input_path)
    last_begin_index = 0
    begin_pattern = 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*$',
        regex.MULTILINE
    )
    # 新增目录匹配模式
    catalog_pattern = regex.compile(r'\s*目\s*录\s*$', regex.MULTILINE)

    pdf_document = PdfReader(input_path)
    for i, page in enumerate(pdf_document.pages):
        if i > end_page:
            return common_header, 0  # 如果页码大于end_page，直接返回last_begin_index=0
        text = page.extract_text()
        if text:
            cleaned_text = clean_page_content(text, common_header)
            # 检查是否存在"目录"
            if catalog_pattern.search(cleaned_text):
                continue  # 如果存在目录，跳过当前页面
            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 check_pdf_pages(pdf_path, logger):
    try:
        reader = PdfReader(pdf_path)
        num_pages = len(reader.pages)
        logger.info(f"PDF '{pdf_path}' 的总页数为: {num_pages}")
        if num_pages <= 50:
            logger.info("PDF页数小于或等于50页，跳过切分逻辑。")
            return ['', '', '', '', '', '', '']
        # 若页数大于50页，返回None表示继续处理
        return None
    except Exception as 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
        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

def get_invalid_file(file_path,output_folder,common_header):
    pdf_document = PdfReader(file_path)
    total_pages = len(pdf_document.pages)
    begin_pattern=[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',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
    )]
    end_pattern=[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[一二三四五六七八九十百千]+(?:章|部分).*?(?:响应|投标).*?格式.*', regex.MULTILINE),
        regex.compile(r"\s*(投标文件格式|响应文件格式|响应性文件格式)\s*"
    ]