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 io
import os

import fitz
import regex
from PyPDF2 import PdfReader, PdfWriter
from flask_app.general.读取文件.clean_pdf import extract_common_header, clean_page_content
from flask_app.general.format_change import docx2pdf
import concurrent.futures


# 定义一个函数用于提取文本
def get_text_pypdf2(pdf, page_num):
    return pdf.pages[page_num].extract_text() or ""

def get_text_fitz(pdf, page_num):
    return pdf.load_page(page_num).get_text() or ""
# 定义一个内部函数来绑定 pdf_document 对象
def create_get_text_function(pdf_lib, pdf_doc):
    if pdf_lib == 'pypdf2':
        return lambda page_num: get_text_pypdf2(pdf_doc, page_num)
    elif pdf_lib == 'fitz':
        return lambda page_num: get_text_fitz(pdf_doc, page_num)
    else:
        raise ValueError("不支持的 PDF 库。")

def get_start_and_common_header(input_path, end_page):
    """
    提取 PDF 文件的公共页眉和起始页索引。

    参数：
    - input_path: PDF 文件路径。
    - end_page: 遍历的结束页码。

    返回：
    - common_header: 公共页眉内容。
    - last_begin_index: 起始页的页码索引。
    """
    pdf_document = None
    try:
        # 提取公共页眉

        common_header = extract_common_header(input_path)  # 假设该函数已定义

        last_begin_index = -1
        begin_pattern = regex.compile(
            r'.*(?<!对应\s*)(?<!根据\s*)(?<!按照\s*)(?<!见\s*)(?<!与\s*)(?<!同\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|采购公告)[\)）]?\s*$',
            regex.MULTILINE
        )
        # 新增目录匹配模式
        catalog_pattern = regex.compile(r'\s*目\s*录\s*$', regex.MULTILINE)
        try:
            # 尝试使用 PyPDF2 读取 PDF
            pdf_document = PdfReader(input_path)
            total_pages = len(pdf_document.pages)
            get_text = create_get_text_function('pypdf2', pdf_document)
            # print("使用 PyPDF2 成功读取 PDF 文件。")
        except Exception as e_pypdf2:
            print(f"get_start_and_common_header:使用 PyPDF2 读取 PDF 失败: {e_pypdf2}")
            try:
                # 如果 PyPDF2 失败，尝试使用 PyMuPDF 读取 PDF
                pdf_document = fitz.open(input_path)
                total_pages = pdf_document.page_count
                get_text = create_get_text_function('fitz', pdf_document)
                # print("使用 PyMuPDF 成功读取 PDF 文件。")
            except Exception as e_fitz:
                print(f"使用 PyMuPDF 读取 PDF 也失败: {e_fitz}")
                return common_header, -1  # 或者根据需求抛出异常

        # 遍历页面
        for i in range(total_pages):
            if i > end_page:
                return common_header, -1  # 如果页码大于 end_page，直接返回 last_begin_index=0
            text = get_text(i)
            if text:
                cleaned_text = clean_page_content(text, common_header)
                # 检查是否存在"目录"
                if catalog_pattern.search(cleaned_text):
                    # print(f"页面 {i} 包含目录，跳过。")
                    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
                    # print(f"匹配到起始模式，设置 last_begin_index 为: {last_begin_index}")
                    return common_header, last_begin_index
        return common_header, last_begin_index
    except Exception as e:
        print(f"Error in get_start_and_common_header: {e}")
        return "", -1  # 根据需求调整返回值
    finally:
        # 如果使用的是 PyMuPDF，记得关闭文档
        if pdf_document and hasattr(pdf_document, "close"):
            pdf_document.close()


def check_pdf_pages(pdf_path, mode, logger):
    pdf_document = None
    try:
        try:
            # 尝试使用 PyPDF2 读取 PDF（新版可直接传入文件路径）
            pdf_document = PdfReader(pdf_path)
            num_pages = len(pdf_document.pages)
            # logger.info(f"使用 PyPDF2 成功读取 PDF '{pdf_path}' 的总页数为: {num_pages}")
        except Exception as e_pypdf2:
            logger.warning(f"check_pdf_pages: 使用 PyPDF2 读取 PDF 失败: {e_pypdf2}")
            # 如果 PyPDF2 读取失败，尝试使用 PyMuPDF 读取 PDF
            pdf_document = fitz.open(pdf_path)
            num_pages = pdf_document.page_count

        if num_pages <= 30:
            logger.info("PDF（invalid_path）页数小于或等于30页，跳过切分逻辑。")
            if mode == 'goods':
                return True, ['', '', '', '', '', '', pdf_path, '']
            else:
                return True, ['', '', '', '', '', pdf_path, '']

        # 若页数大于30页，返回 False 表示继续处理
        return False, []

    except Exception as e:
        logger.error(f"无法读取 PDF 页数: {e}")
        if mode == 'goods':
            return True, ['', '', '', '', '', '', pdf_path, '']
        else:
            return True, ['', '', '', '', '', pdf_path, '']

    finally:
        # 如果使用的是 PyMuPDF 或其他需要关闭的对象，确保关闭资源
        if pdf_document and hasattr(pdf_document, "close"):
            pdf_document.close()


def save_extracted_pages(pdf_path, output_folder, start_page, end_page, output_suffix, common_header):
    pdf_document = None
    using_pypdf2 = False

    try:
        if start_page is None or end_page is None:
            print("错误: start_page 或 end_page 为 None")
            return ""

        # 尝试使用 PyPDF2 读取 PDF（新版可以直接传入路径）
        try:
            pdf_document = PdfReader(pdf_path)
            total_pages = len(pdf_document.pages)
                # 定义提取文本函数
            get_text = create_get_text_function('pypdf2', pdf_document)
            using_pypdf2 = True
                # print("使用 PyPDF2 成功读取 PDF 文件。")
        except Exception as e_pypdf2:
            print(f"save_extracted_pages: 使用 PyPDF2 读取 PDF 失败: {e_pypdf2}")
            # 如果 PyPDF2 失败，尝试使用 PyMuPDF 读取 PDF
            try:
                pdf_document = fitz.open(pdf_path)
                total_pages = pdf_document.page_count
                get_text = create_get_text_function('fitz', pdf_document)
                using_pypdf2 = False
                # print("使用 PyMuPDF 成功读取 PDF 文件。")
            except Exception as e_fitz:
                print(f"save_extracted_pages: 使用 PyMuPDF 读取 PDF 也失败: {e_fitz}")
                return ""

        # 检查页面范围的有效性
        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 ""

        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")

        # 如果 output_suffix 为 'notice' 并且 start_page > 0，则另存“目录前”的页面
        if output_suffix == 'notice' and start_page > 0:
            before_pdf_path = os.path.join(output_folder, f"{base_file_name}_before.pdf")
            toc_page = -1

            for page_num in range(min(start_page, total_pages)):
                try:
                    text = get_text(page_num)
                except Exception as e_extract:
                    print(f"提取第 {page_num} 页文本时出错: {e_extract}")
                    continue

                cleaned_text = clean_page_content(text, common_header)
                if regex.search(r'目\s*录', cleaned_text, regex.MULTILINE):
                    toc_page = page_num
                    break

            pages_to_extract = toc_page + 1 if toc_page != -1 else start_page

            if using_pypdf2:
                before_doc = PdfWriter()
                for page_num in range(pages_to_extract):
                    try:
                        before_doc.add_page(pdf_document.pages[page_num])
                    except Exception as e_page:
                        print(f"添加第 {page_num} 页到 before_doc 时出错: {e_page}")
                        continue
                try:
                    with open(before_pdf_path, 'wb') as f_before:
                        before_doc.write(f_before)
                    print(f"目录前的页面已保存到 {before_pdf_path}")
                except Exception as e_write_before:
                    print(f"保存目录前的页面时出错: {e_write_before}")
            else:
                before_doc = fitz.open()
                for page_num in range(pages_to_extract):
                    try:
                        before_doc.insert_pdf(pdf_document, from_page=page_num, to_page=page_num)
                    except Exception as e_page:
                        print(f"添加第 {page_num} 页到 before_doc 时出错: {e_page}")
                        continue
                try:
                    before_doc.save(before_pdf_path)
                    before_doc.close()
                    print(f"目录前的页面已保存到 {before_pdf_path}")
                except Exception as e_write_before:
                    print(f"保存目录前的页面时出错: {e_write_before}")

        # 提取并保存目标页面
        if using_pypdf2:
            output_doc = PdfWriter()
            for page_num in range(start_page, end_page + 1):
                try:
                    output_doc.add_page(pdf_document.pages[page_num])
                except Exception as e_page:
                    print(f"添加第 {page_num} 页到 output_doc 时出错: {e_page}")
                    continue
            try:
                with open(output_pdf_path, 'wb') as f_out:
                    output_doc.write(f_out)
                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_write:
                print(f"保存截取的页面时出错: {e_write}")
                return ""
        else:
            output_doc = fitz.open()
            try:
                for page_num in range(start_page, end_page + 1):
                    try:
                        output_doc.insert_pdf(pdf_document, from_page=page_num, to_page=page_num)
                    except Exception as e_page:
                        print(f"添加第 {page_num} 页到 output_doc 时出错: {e_page}")
                        continue
                output_doc.save(output_pdf_path)
                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_write:
                print(f"保存截取的页面时出错: {e_write}")
                return ""
            finally:
                output_doc.close()
    except Exception as e:
        print(f"发生未知错误: {e}")
        return ""
    finally:
        # 如果使用的是 PyMuPDF 或其他需要关闭的对象，确保关闭资源
        if pdf_document and not using_pypdf2 and hasattr(pdf_document, "close"):
            pdf_document.close()

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(pdf_path, output_folder, common_header, begin_page):
    """
    从指定的PDF文件中提取无效部分并保存到输出文件夹中。
    begin_pattern匹配开头  end_pattern匹配结尾
    页数小于100不进行begin_pattern，默认start_page=0
    页数大于200时end_pattern从前往后匹配
    Args:
        pdf_path (str): 输入的PDF文件路径。
        output_folder (str): 提取后文件的输出文件夹路径。
        common_header (str): 公共头部文本，用于清理每页的内容。

    Returns:
        list: 包含保存的文件路径的列表，如果提取失败则返回包含空字符串的列表。
    """
    # 定义开始模式
    begin_patterns = [
        regex.compile(
            r'.*(?<!对应\s*)(?<!根据\s*)(?<!按照\s*)(?<!见\s*)(?<!与\s*)(?<!同\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|采购公告)[\)）]?\s*$',
            regex.MULTILINE
        ),
        regex.compile(
            r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:公告|邀请书|邀请函|邀请).*|^第一卷|^投标邀请',
            regex.MULTILINE
        )
    ]
    # 定义结束模式
    end_patterns = [
        regex.compile(
            r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:响应|投标|应答).*?(?:(?:文件|书)(?:的)?(?:组成|构成|编制)|格式).*|'
            r'第[一二三四五六七八九十]+(?:章|部分).*?合同|[：:]清标报告',
            regex.MULTILINE
        ),
        regex.compile(
            r"\s*(投标文件|响应文件|响应性文件|应答文件)(?:的)?格式(?:及相关附件)?\s*$",
            regex.MULTILINE
        ),
    ]

    # 定义排除模式
    exclusion_pattern = regex.compile(
        r'(文件的构成|文件的组成|文件组成|文件构成|文件的编制|文件编制)\s*$', regex.MULTILINE)

    pdf_document = None
    try:
        # 尝试使用 PyPDF2 读取 PDF
        try:
            pdf_document = PdfReader(pdf_path)
            get_text = create_get_text_function('pypdf2', pdf_document)
            total_pages = len(pdf_document.pages)
        except Exception as e:
            pdf_document = fitz.open(pdf_path)
            get_text = create_get_text_function('fitz', pdf_document)
            total_pages = pdf_document.page_count

        if total_pages <= 50:
            print(f"PDF页数({total_pages}) <= 50，直接返回文件路径: {pdf_path}")
            return pdf_path, 0

        # 提取并清理每页的文本内容
        page_texts = []
        for i in range(total_pages):
            text = get_text(i)
            cleaned_text = clean_page_content(text, common_header) if text else ""
            page_texts.append(cleaned_text)

        # 内部函数：查找起始页
        def find_start_page(begin_page):
            for pattern in begin_patterns:  # 需提前定义好
                for i in range(begin_page, min(begin_page + 30, total_pages)):
                    text = page_texts[i]
                    # 若存在排除模式则跳过
                    if regex.search(exclusion_pattern, text):
                        continue
                    if regex.search(pattern, text):
                        # print(f"起始模式在第 {i + 1} 页匹配: {pattern.pattern}")
                        return i
                # print(f"未在前30页找到模式: {pattern.pattern}")
            return 0  # 默认从第一页开始

        # 内部函数：查找结束页
        def find_end_page():
            if total_pages > 200:
                # 当页数较多时，从第31页开始正向查找结束模式
                for pattern in end_patterns:  # 需提前定义好
                    for i in range(30, total_pages):
                        text = page_texts[i]
                        # 定义局部的排除模式
                        exclusion_pat = regex.compile(
                            r'(文件的构成|文件的组成|文件组成|文件构成|文件的编制|文件编制|评审要素|评审标准)\s*$',
                            regex.MULTILINE
                        )
                        if regex.search(exclusion_pat, text):
                            continue
                        if regex.search(pattern, text):
                            # print(f"结束模式在第 {i + 1} 页匹配: {pattern.pattern}")
                            return i
            else:
                # 当页数较少时，从后向前查找（至少保留前30页）
                for pattern in end_patterns:
                    for i in range(total_pages - 1, 29, -1):
                        text = page_texts[i]
                        if regex.search(pattern, text):
                            # print(f"结束模式在第 {i + 1} 页匹配: {pattern.pattern}")
                            return i

            # 若未匹配到结束模式，设置默认结束页
            if total_pages > 200:
                print(f"未找到结束模式，总页数大于200，平滑调整结束页为 {max(100, int(total_pages * 1 / 2))}。{pdf_path}")
                return max(100, int(total_pages * 1 / 2))
            elif 100 < total_pages <= 200:
                print("未找到结束模式，总页数在100到200之间，设置结束页为总页数的三分之二。 " + pdf_path)
                return max(100, int(total_pages * 2 / 3))
            else:
                print("未找到结束模式，设置结束页为最后一页。 " + pdf_path)
                return total_pages - 1

        # 根据总页数决定是否并发查找起始页与结束页
        if total_pages < 100:
            start_page_found = 0
            with concurrent.futures.ThreadPoolExecutor() as executor:
                future_end = executor.submit(find_end_page)
                end_page_found = future_end.result()
        else:
            with concurrent.futures.ThreadPoolExecutor() as executor:
                future_start = executor.submit(find_start_page, begin_page)
                future_end = executor.submit(find_end_page)
                start_page_found = future_start.result()
                end_page_found = future_end.result()

        # 检查页码范围是否有效
        if start_page_found > end_page_found:
            print(f"无效的页码范围: 起始页 ({start_page_found + 1}) > 结束页 ({end_page_found + 1})")
            return "", 0

        # 调用已实现的保存函数，保存提取的页面
        output_path = save_extracted_pages(
            pdf_path=pdf_path,
            output_folder=output_folder,
            start_page=start_page_found,
            end_page=end_page_found,
            output_suffix="invalid",
            common_header=common_header
        )
        return output_path, end_page_found

    except Exception as e:
        print(f"处理文件 {pdf_path} 时发生错误: {e}")
        return "", 0

    finally:
        # 确保释放资源（对 fitz 的 pdf_document 需要关闭）
        if pdf_document and hasattr(pdf_document, "close"):
            pdf_document.close()


def extract_pages_generic(pdf_path, begin_pattern, end_pattern, begin_page, common_header, exclusion_pattern=None,
                          output_suffix="normal", invalid_endpage=-1):
    start_page = None
    end_page = None
    flag = True
    # 先尝试使用 PyPDF2
    try:
        pdf_document = PdfReader(pdf_path)
        total_pages = len(pdf_document.pages)
        get_text = create_get_text_function('pypdf2', pdf_document)
    except Exception as e_pypdf2:
        print(f"extract_pages_generic:使用 PyPDF2 读取 PDF 失败: {e_pypdf2}")
        # 如果 PyPDF2 失败，就再试 PyMuPDF
        try:
            pdf_document = fitz.open(pdf_path)
            total_pages = pdf_document.page_count
            get_text = create_get_text_function('fitz', pdf_document)
        except Exception as e_fitz:
            print(f"使用 PyMuPDF 读取 PDF 也失败: {e_fitz}")
            return None, None
    end_limit = total_pages if invalid_endpage == -1 else min(invalid_endpage, total_pages)
    for i in range(begin_page, end_limit):
        text = get_text(i)
        if text:
            cleaned_text = clean_page_content(text, common_header)
            if output_suffix == "tobidders_notice2":    #extract_pages_twice_tobidders_notice会调用该代码
                catalog_pattern = regex.compile(r'\s*目\s*录\s*$', regex.MULTILINE)
                if exclusion_pattern and flag and (start_page is not None) and regex.search(exclusion_pattern,cleaned_text):
                    flag = False
                    continue
                if begin_page == 0 and catalog_pattern.search(cleaned_text):
                    continue  # 如果存在目录，跳过当前页面
            else:
                # 一般投标文件的编制、组成在'投标人须知前附表/正文'中，需要防止begin_pattern匹配到这部分内容，所以在start_page is None的时候使用该exclusion_pattern
                if exclusion_pattern and flag and (start_page is None) and regex.search(exclusion_pattern, cleaned_text):
                    flag = False
                    continue
            if start_page is None and regex.search(begin_pattern, cleaned_text):
                if (output_suffix == "notice" and i >= begin_page) or (output_suffix != "notice" and i > begin_page):
                    start_page = i
                    continue
            if start_page is not None:
                if output_suffix in ["tobidders_notice", "notice", "tobidders_notice2"]:  # 使用列表判断多个匹配项
                    # 判断 end_pattern 是否匹配且当前页大于起始页
                    if regex.search(end_pattern, cleaned_text) and i > start_page:
                        end_page = i
                        break
                else:
                    # 如果 end_pattern 匹配且 begin_pattern 不匹配
                    if regex.search(end_pattern, cleaned_text) and not regex.search(begin_pattern, cleaned_text):
                        end_page = i
                        break
        # 如果使用的是 PyMuPDF，需要手动关闭文档
    if pdf_document and isinstance(pdf_document, fitz.Document):
        pdf_document.close()
    return start_page, end_page


def generate_mid_pattern(chapter_type=None):
    """
    根据章节类型动态生成 mid_pattern。

    参数:
        chapter_type (str, optional): 章节类型，如 '章' 或 '部分'。

    返回:
        regex.Pattern: 编译后的正则表达式模式。
    """
    # 定义基础的 mid_pattern
    base_mid_pattern = (
        r'^\s*(?:[（(]\s*[一二12]?\s*[)）]\s*[、．.]*|'
        r'[一二12][、．.]+|[、．.]+)\s*(说\s*明|总\s*则|名\s*词\s*解\s*释|定\s*义)|'
        r'(?<!对应\s*)(?<!根据\s*)(?<!按照\s*)(?<!见\s*)(?<!与\s*)(?<!同\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|应答人).*须知正文\s*$'
    )

    additional_mid_pattern = ''
    if chapter_type:
        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)'

    if additional_mid_pattern:
        combined_pattern = rf'(?:{base_mid_pattern})|(?:{additional_mid_pattern})'
    else:
        combined_pattern = base_mid_pattern

    return regex.compile(combined_pattern, regex.MULTILINE)


def generate_end_pattern(extraction_stage, chapter_type=None):
    """
    根据提取阶段和章节类型动态生成 end_pattern。

    参数:
        extraction_stage (str): 提取阶段标记，如 'first' 表示第一次，'third' 表示第三次。
        chapter_type (str, optional): 章节类型，如 '章' 或 '部分'。

    返回:
        regex.Pattern: 编译后的正则表达式模式。
    """
    # 定义公共匹配模式
    common_patterns = (
        r'^附录(?:一)?[：:]|'
        r'^附件(?:一)?[：:]|'
        r'^附表(?:一)?[：:]'
    )

    # 定义 end_pattern 模板
    end_pattern_template_first = (
            r'^第[一二三四五六七八九十百千]+(?:{chapter_type})\s*[\u4e00-\u9fff]+'
            r'|' + common_patterns
    )


    end_pattern_template_third = (
            r'(?<!对应\s*)(?<!根据\s*)(?<!按照\s*)(?<!见\s*)(?<!与\s*)(?<!同\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九十百千]+(?:{chapter_type})\s*[\u4e00-\u9fff、()（）/]+\s*$'
            r'|' + common_patterns
    )

    # 选择模板并替换 {chapter_type}
    if extraction_stage == 'third':
        template = end_pattern_template_third
    else:
        template = end_pattern_template_first

    if chapter_type:
        pattern_str = template.format(chapter_type=chapter_type)
    else:
        pattern_str = template.format(chapter_type='章|部分')

    return regex.compile(pattern_str, regex.MULTILINE)


def extract_pages_tobidders_notice(pdf_path, output_folder, begin_page, common_header, invalid_endpage=-1):
    """
    从PDF文档中提取起始页、中间页和结束页。
    如果第一次提取失败，则使用新的 begin_pattern 和 end_pattern 重新提取。
    """
    exclusion_pattern = regex.compile(
        r'(文件的构成|文件的组成|文件组成|文件构成|文件的编制|文件编制)\s*$', regex.MULTILINE)
    def run_extraction(begin_pattern, extraction_stage='first'):
        """
        使用提供的 begin_pattern 运行提取过程。
        根据 extraction_stage 判断是“第一次提取”还是“第三次提取”，
        从而选择对应的默认 end_pattern（动态生成）。

        参数:
            begin_pattern (regex.Pattern): 用于识别起始的正则表达式模式。
            extraction_stage (str): 提取阶段标记，如 'first' 表示第一次，'third' 表示第三次。

        返回:
            tuple: (start_page, mid_page, end_page)
        """

        # ===== 函数内部变量 =====
        start_page = None
        mid_page = None
        end_page = None
        combined_mid_pattern = None  # 中间页的组合模式
        catalog_pattern = regex.compile(r'\s*目\s*录\s*$', regex.MULTILINE)
        end_limit = total_pages if invalid_endpage == -1 else min(invalid_endpage, total_pages)
        # ===== 遍历每一页，执行提取逻辑 =====
        for i in range(end_limit):
            try:
                text = get_text(i)
                cleaned_text = clean_page_content(text, common_header)
            except Exception as e:
                print(f"提取第 {i} 页文本时出错: {e}")
                continue

            # 如果已经找到中间页，且当前页匹配排除模式，则跳过
            if exclusion_pattern and mid_page is not None and regex.search(exclusion_pattern, cleaned_text):
                continue

            # 如果为第 0 页之后的目录，直接跳过
            if begin_page == 0 and catalog_pattern.search(cleaned_text):
                continue

            # ========== 识别起始页 ==========
            if start_page is None:
                match = regex.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
                    # 根据匹配到的内容识别是“章”还是“部分”，用于后续组合 mid_pattern
                    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”

                    # ===== 动态生成 end_pattern_dynamic =====
                    end_pattern_dynamic = generate_end_pattern(extraction_stage, chapter_type)
                    # ========== 动态生成 mid_pattern ==========
                    combined_mid_pattern = generate_mid_pattern(chapter_type)
                    # 找到 start_page 后，继续循环，进入下一页
                    continue

            # ========== 识别中间页 ==========
            if start_page is not None and mid_page is None and combined_mid_pattern:
                if regex.search(combined_mid_pattern, cleaned_text):
                    mid_page = i

            # ========== 识别结束页 ==========
            if start_page is not None and mid_page is not None:
                # 当前使用的 end_pattern（上面根据 extraction_stage 和 chapter_type 选择好了）
                if regex.search(end_pattern_dynamic, cleaned_text):
                    if i > mid_page:
                        end_page = i
                        break

        return start_page, mid_page, end_page

    def perform_extraction_and_save(start_page, mid_page, end_page):
        path1 = save_extracted_pages(pdf_path, output_folder, start_page, mid_page, "tobidders_notice_part1",
                                     common_header)
        if mid_page != end_page:
            path2 = save_extracted_pages(pdf_path, output_folder, mid_page, end_page, "tobidders_notice_part2",
                                         common_header)
        else:
            path2 = path1
        return path1, path2

    pdf_document = None
    try:
        try:
            pdf_document = PdfReader(pdf_path)
            get_text = create_get_text_function('pypdf2', pdf_document)
            total_pages = len(pdf_document.pages)
        except Exception as e_pypdf2:
            print(f"extract_pages_tobidders_notice:使用 PyPDF2 读取 PDF 失败: {e_pypdf2}")
            try:
                pdf_document = fitz.open(pdf_path)
                get_text = create_get_text_function('fitz', pdf_document)
                total_pages = pdf_document.page_count
                # print("使用 PyMuPDF 成功读取 PDF 文件。")
            except Exception as e_fitz:
                print(f"使用 PyMuPDF 读取 PDF 也失败: {e_fitz}")
                return "", ""  # 或者根据需求抛出异常

        # 第一次提取尝试，使用初始的 begin_pattern
        begin_pattern = regex.compile(
            r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:投标人?|磋商|谈判|供应商|应答人|比选申请人).*须知+|'
            r'(?<!对应\s*)(?<!根据\s*)(?<!按照\s*)(?<!见\s*)(?<!与\s*)(?<!同\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|应答人|比选申请人).*须知前附表\s*$|'
            r'(?:投标人?|磋商|谈判|供应商|应答人|比选申请人).*须知+\s*$',
            regex.MULTILINE
        )
        start_page, mid_page, end_page = run_extraction(begin_pattern, extraction_stage='first')
        # 如果第一次提取成功，保存并返回路径
        if start_page is not None and mid_page is not None and end_page is not None:
            return perform_extraction_and_save(start_page, mid_page, end_page)

        print(f"第一次提取tobidders_notice失败，尝试第二次提取: {pdf_path}")
        start_page1, end_page1, start_page2, end_page2 = extract_pages_twice_tobidders_notice(pdf_path, common_header, begin_page)

        if start_page1 is not None and end_page1 is not None and start_page2 is not None and end_page2 is not None:
            if end_page1==start_page2:
                mid_page=end_page1
                return perform_extraction_and_save(start_page1, mid_page, end_page2)
            else:
                path1=save_extracted_pages(pdf_path,output_folder,start_page1,end_page1,"tobidders_notice_part1",common_header)
                path2=save_extracted_pages(pdf_path,output_folder,start_page2,end_page2,"tobidders_notice_part2",common_header)
                return path1,path2

        print("第二次提取tobidders_notice失败，尝试第三次提取!")
        new_begin_pattern = regex.compile(
            r'.*(?:投标人|磋商|谈判|供应商|应答人|比选申请人).*须知\s*$|'
            r'(?<!对应\s*)(?<!根据\s*)(?<!按照\s*)(?<!见\s*)(?<!与\s*)(?<!同\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|应答人|比选申请人).*须知前附表\s*$',
            regex.MULTILINE
        )
        start_page, mid_page, end_page = run_extraction(new_begin_pattern, extraction_stage='third')
        if start_page is not None and mid_page is not None and end_page is not None:
            return perform_extraction_and_save(start_page, mid_page, end_page)
        else:
            # 所有提取尝试均失败
            print(f"三次提取tobidders_notice均失败!! {pdf_path}")
            return "", ""
    except Exception as e:
        print(f"处理文件 {pdf_path} 时发生错误: {e}")
        return "", ""
    finally:
        # 无论如何都关闭 pdf_document（对于 fitz 对象）
        if pdf_document and hasattr(pdf_document, "close"):
            pdf_document.close()



def extract_pages_twice_tobidders_notice(pdf_path, common_header, begin_page):
    # 使用 with open 确保文件流在读取后关闭，避免文件句柄泄露
    try:
        pdf_document = PdfReader(pdf_path)
    except Exception as e:
        print(f"读取 PDF 文件失败: {e}")
        return None, None, None, None
    # 投标须知前附表占一章、投标须知正文占一章
    output_suffix = "tobidders_notice"
    begin_pattern = regex.compile(
        r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:(?:投标人?|磋商|谈判|供应商|应答人|比选申请人).*须知)+',
        regex.MULTILINE
    )
    second_begin_pattern = regex.compile(
        r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*([\u4e00-\u9fff]+)', regex.MULTILINE  # 捕获中文部分
    )
    end_pattern = second_begin_pattern
    exclusion_words = ["合同", "评标", "开标", "评审", "采购", "资格"]  # 在这里添加需要排除的关键词

    exclusion_pattern = regex.compile(
        r'(文件的构成|文件的组成|文件组成|文件构成|文件的编制|文件编制)\s*$', regex.MULTILINE)

    # 提取第一部分
    start_page1, end_page1 = extract_pages_generic(pdf_path, begin_pattern, end_pattern, begin_page, common_header,
                                                   exclusion_pattern, output_suffix)
    if start_page1 is None or end_page1 is None:
        return None, None, None,None

    # 提取第二部分 先检查end_page1页面的内容
    text = get_text_pypdf2(pdf_document,end_page1)
    cleaned_text = clean_page_content(text, common_header)
    match = end_pattern.search(cleaned_text)
    if match:
        # 获取匹配到的中文部分
        chapter_title = match.group(1) if match.groups() else ""
        # 检查是否包含排除关键词
        if any(word in chapter_title for word in exclusion_words):
            # 如果包含排除关键词，直接返回相同的路径
            second_begin_pattern=begin_pattern     #投标人须知前附表和投标人须知正文不是紧挨着的！eg:（发布稿）恒丰理财有限责任公司智能投研终端项目竞争性磋商

    # 如果不包含排除关键词，继续提取第二部分
    output_suffix='tobidders_notice2'
    begin_page=end_page1-1   #传入start_page2-1是因为非notice截取->start_page>begin_page
    start_page2, end_page2 = extract_pages_generic(pdf_path, second_begin_pattern, end_pattern, begin_page, common_header,
                                         exclusion_pattern, output_suffix)

    if start_page2 is None or end_page2 is None:
        return start_page1, end_page1, end_page1,end_page1

    return start_page1, end_page1, start_page2,end_page2

def get_notice(pdf_path, output_folder, begin_page, common_header,invalid_endpage):
    begin_pattern = regex.compile(
        r'.*(?<!对应\s*)(?<!根据\s*)(?<!按照\s*)(?<!见\s*)(?<!同\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|采购公告)[\)）]?\s*$',
        regex.MULTILINE
    )
    end_pattern = regex.compile(
        r'^第[一二三四五六七八九十]+(?:章|部分)\s*[\u4e00-\u9fff]+|'  # 第一部分
        r'(?<!对应\s*)(?<!根据\s*)(?<!按照\s*)(?<!见\s*)(?<!同\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)'  # 否定前瞻部分
        r'第[一二三四五六七八九十1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$|'  # 第二部分
        r'(?<!对应\s*)(?<!根据\s*)(?<!按照\s*)(?<!见\s*)(?<!同\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)'
        r'(?:投标人?|磋商|谈判|供应商|应答人|比选申请人).*须知+\s*$',  # 新增部分
        regex.MULTILINE
    )
    exclusion_pattern = regex.compile(
        r'(文件的构成|文件的组成|文件组成|文件构成|文件的编制|文件编制)\s*$', regex.MULTILINE)
    output_suffix = 'notice'
    start_page, end_page = extract_pages_generic(pdf_path, begin_pattern, end_pattern, begin_page, common_header,
                                                 exclusion_pattern, output_suffix, invalid_endpage)
    if start_page is None or end_page is None:
        print(f"{output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！")
    return save_extracted_pages(pdf_path, output_folder, start_page, end_page, output_suffix, common_header)


if __name__ == "__main__":
    file_path = r'D:\flask_project\flask_app\static\output\output1\2c4be864-bdab-405d-95cb-9d945d8627b3\ztbfile.pdf'
    output_folder = r'D:\flask_project\flask_app\static\output\output1\2c4be864-bdab-405d-95cb-9d945d8627b3\tmp'
    # res=get_invalid_file(file_path,output_folder,"",0)