zbparse/flask_app/货物标/截取pdf货物标版.py

import glob
import logging

from PyPDF2 import PdfReader, PdfWriter
import regex  # 导入正则表达式库
import os  # 用于文件和文件夹操作

from flask_app.general.clean_pdf import clean_page_content, extract_common_header
from flask_app.general.format_change import docx2pdf
from flask_app.general.merge_pdfs import merge_and_cleanup, merge_selected_pdfs_for_goods
import concurrent.futures


def get_global_logger(unique_id):
    if unique_id is None:
        return logging.getLogger()  # 获取默认的日志器
    logger = logging.getLogger(unique_id)
    return logger

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_files(file_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
    pdf_path = convert_to_pdf(file_path)
    result = extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix)
    if result:
        if output_suffix == "tobidders_notice":
            # 确保返回的是元组，并将其中的 None 转换为 ""
            path1, path2 = result
            return [path1 or "", path2 or ""]
        elif output_suffix == "qualification1":
            merge_and_cleanup(result, "qualification3")
            return [result or ""]
        return [result or ""]
    return [""]  # 返回空字符串

def extract_pages_generic(pdf_document, begin_pattern, end_pattern, begin_page, common_header, exclusion_pattern=None,
                          output_suffix="normal"):
    start_page = None
    end_page = None
    flag=True
    for i, page in enumerate(pdf_document.pages[begin_page:], start=begin_page):
        text = page.extract_text() or ""
        cleaned_text = clean_page_content(text, common_header)
        if output_suffix == "tobidders_notice":
            if exclusion_pattern and flag and (start_page is not None) and regex.search(exclusion_pattern, cleaned_text):
                flag=False
                continue
        else:
            if exclusion_pattern and flag 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 == "tobidders_notice":
                if regex.search(end_pattern, cleaned_text) and i > start_page:
                    end_page = i
                    break
            else:
                if regex.search(end_pattern, cleaned_text) and i > start_page and not regex.search(begin_pattern,cleaned_text):
                    end_page = i
                    break
    return start_page, end_page


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)
        exclusion_pattern = None
        total_pages = len(pdf_document.pages) - 1  # 获取总页数

        if output_suffix == "tobidders_notice":
            exclusion_pattern = regex.compile(
                r'文件的构成|文件的组成|文件构成|文件组成')
            start_page, mid_page, end_page = extract_pages_tobidders_notice(
                pdf_path, begin_pattern, begin_page, common_header, exclusion_pattern
            )
            if not start_page or not mid_page or not end_page:
                print(f"三次提取tobidders_notice均失败!!{pdf_path}")
                return "", ""
            # if start_page is None or end_page is None or mid_page is None:
            #     print(f"first: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！尝试备用提取策略。")
            #     return extract_pages_twice_tobidders_notice(pdf_path, output_folder, output_suffix, common_header,begin_page)
            path1 = save_extracted_pages(pdf_document, start_page, mid_page, pdf_path, output_folder,
                                         "tobidders_notice_part1")
            if mid_page != end_page:
                path2 = save_extracted_pages(pdf_document, mid_page, end_page, pdf_path, output_folder,
                                         "tobidders_notice_part2")
            else:
                path2=path1
            return path1, path2

        else:
            # 原有的处理逻辑保持不变
            if output_suffix == "qualification1" or output_suffix == "procurement" or output_suffix == "evaluation_method":
                exclusion_pattern = regex.compile(
                    r'文件的构成|文件的组成|文件构成|文件组成')
            start_page, end_page = extract_pages_generic(pdf_document, begin_pattern, end_pattern, begin_page,
                                                         common_header, exclusion_pattern, output_suffix)
            # 针对 selection = 6 的特殊处理
            if output_suffix == "format":
                if start_page is None:
                    print(f"{output_suffix}: 未找到起始页，提取失败！")
                    return ""
                if end_page is None:
                    # 如果未匹配到结束页，默认截取到文件末尾
                    end_page = total_pages
                    print(f"{output_suffix}: 未找到结束页，默认截取到文件末尾。")
                return save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix)
            if start_page is None or end_page is None:
                print(f"first: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！尝试备用提取策略。")
                return extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, begin_page)
            elif output_suffix == "qualification1":
                truncate_pdf_main(pdf_path, output_folder, 2, "qualification3")  # 合并'资格审查'章节和'评标办法'章节
            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 ""


def get_patterns_for_procurement():
    # begin_pattern = regex.compile(
    #     r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:服务|项目|商务|技术).*?要求|^第[一二三四五六七八九十1-9]+(?:章|部分).*(?:采购|需求).*',
    #     regex.MULTILINE)
    begin_pattern = regex.compile(
        r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)'
        r'第[一二三四五六七八九十1-9]+(?:章|部分)\s*'  # 匹配“第X章”或“第X部分”
        r'[\u4e00-\u9fff、()（）]*?'  # 匹配允许的字符
        r'(?:(?:服务|项目|商务|技术)[\u4e00-\u9fff、()（）]*?要求[\u4e00-\u9fff、()（）]*?\s*$|'  # 匹配“服务”、“项目”、“商务”或“技术”后跟“要求”
        r'(?:采购|需求)[\u4e00-\u9fff、()（）]*?)\s*$',  # 或者匹配“采购”或“需求”
        regex.MULTILINE
    )
    end_pattern = regex.compile(r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$', regex.MULTILINE)
    return begin_pattern, end_pattern


def get_patterns_for_evaluation_method():
    begin_pattern = regex.compile(
        r'(?:(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九十1-9]+(?:章|部分)\s*'  # 第一种模式
        r'(?:[\u4e00-\u9fff、()（）]*?)'
        r'(?=.*(?:磋商|谈判|评标|评定|评审))'
        r'(?=.*(?:办法|方法|内容))'
        r'[\u4e00-\u9fff、()（）]*\s*$|'
        r'^\s*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)评标(方法|办法)前附表\s*$)',  # 第二种模式
        regex.MULTILINE
    )
    end_pattern = regex.compile(
        r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$', regex.MULTILINE)
    return begin_pattern, end_pattern


def get_patterns_for_notice():
    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).*')
    end_pattern = regex.compile(
        # r'^(?:第[一二三四五六七八九十百千]+(?:章|部分)\s*(?:投标人须知|磋商须知|供应商须知)+|(?:一\s*、\s*)?(?:投标人须知|磋商须知|供应商须知)前附表)',
        r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+',
        regex.MULTILINE
    )
    return begin_pattern, end_pattern

# def extract_pages_tobidders_notice(pdf_document, begin_pattern, end_pattern, begin_page, common_header,
#                                    exclusion_pattern):
#     start_page = None
#     mid_page = None
#     end_page = None
#     for i, page in enumerate(pdf_document.pages):
#         text = page.extract_text() or ""
#         cleaned_text = clean_page_content(text, common_header)
#         if exclusion_pattern and regex.search(exclusion_pattern, cleaned_text) and mid_page is not None:
#             continue
#         if start_page is None and regex.search(begin_pattern, cleaned_text) and i > begin_page:
#             start_page = i
#         if start_page is not None and mid_page is None and regex.search(
#                 r'^\s*[（(]?\s*[一1]\s*[)）]?\s*[、．.]*\s*(说\s*明|总\s*则)', cleaned_text):
#             mid_page = i
#         if start_page is not None and mid_page is not None and regex.search(end_pattern, cleaned_text) and i > mid_page:
#             end_page = i
#             break
#     return start_page, mid_page, end_page

def extract_pages_tobidders_notice(pdf_path, begin_pattern, begin_page, common_header, exclusion_pattern):
    """
    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。

    参数:
        pdf_document (PDFDocument): 要处理的PDF文档对象。
        begin_pattern (str 或 regex.Pattern): 用于识别起始的正则表达式模式。
        begin_page (int): 开始搜索的页码。
        common_header (str): 每页需要清理的公共头部文本。
        exclusion_pattern (str 或 regex.Pattern): 用于排除某些页的模式。

    返回:
        tuple: (start_page, mid_page, end_page) 如果成功，否则 (None, None, None)
    """

    def run_extraction(local_begin_pattern, local_end_pattern=None):
        """
        使用提供的 begin 和 end 模式运行提取过程。

        如果未提供 local_end_pattern，则根据匹配的章节类型动态生成 end_pattern。

        参数:
            local_begin_pattern (str 或 regex.Pattern): 用于识别起始的正则表达式模式。
            local_end_pattern (str 或 regex.Pattern, 可选): 用于识别结束的正则表达式模式。

        返回:
            tuple: (start_page, mid_page, end_page)
        """
        start_page = None
        mid_page = None
        end_page = None
        chapter_type = None  # 用于存储“章”或“部分”
        combined_mid_pattern = None  # 中间页的组合模式
        pdf_document = PdfReader(pdf_path)
        for i, page in enumerate(pdf_document.pages):
            text = page.extract_text() or ""
            cleaned_text = clean_page_content(text, common_header)

            # 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 regex.search(exclusion_pattern, cleaned_text) and mid_page is not None:
                continue

            # 识别起始页
            if start_page is None:
                match = regex.search(local_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

                    # 如果未提供固定的 end_pattern，则根据匹配的章节类型动态生成
                    if not local_end_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”

                        if chapter_type:
                            # 根据 chapter_type 动态生成 end_pattern
                            end_pattern_dynamic = regex.compile(
                                rf'^第[一二三四五六七八九十百千]+?(?:{chapter_type})\s*[\u4e00-\u9fff]+|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)评标(方法|办法)前附表\s*$|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)评标(方法|办法)正文\s*$',
                                regex.MULTILINE
                            )

                            # 根据 chapter_type 动态生成 additional_mid_pattern
                            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)'
                            else:
                                additional_mid_pattern = ''

                            # 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)' \
                                               r'|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)\s*须知正文\s*$'

                            # 合并基础模式和额外模式
                            if additional_mid_pattern:
                                combined_mid_pattern = regex.compile(
                                    rf'(?:{base_mid_pattern})|(?:{additional_mid_pattern})',
                                    regex.MULTILINE
                                )
                            else:
                                combined_mid_pattern = regex.compile(
                                    rf'{base_mid_pattern}',
                                    regex.MULTILINE
                                )
                        else:
                            # 如果未匹配到“章”或“部分”，使用默认的 end_pattern 和 mid_pattern
                            end_pattern_dynamic = regex.compile(
                                r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)评标(方法|办法)前附表\s*$|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)评标(方法|办法)正文\s*$',
                                regex.MULTILINE
                            )

                            # 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)'
                            combined_mid_pattern = regex.compile(
                                rf'{base_mid_pattern}',
                                regex.MULTILINE
                            )
                    else:
                        # 如果提供了固定的 end_pattern，则使用默认的 mid_pattern
                        base_mid_pattern = r'.*[（(]?\s*[一二12]?[)）]?\s*[、．.]*\s*(说\s*明|总\s*则|名\s*词\s*解\s*释)\s*$'  # 可以匹配"东莞市粤隆招标有限公司编制 46一、说明"
                        combined_mid_pattern = regex.compile(
                            rf'{base_mid_pattern}',
                            regex.MULTILINE
                        )
                    continue

            # 识别中间页
            if start_page is not None and mid_page is None and combined_mid_pattern:
                if (start_page + 1 == i) and regex.search(local_begin_pattern, cleaned_text):
                    continue
                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:
                # 使用提供的 end_pattern 或动态生成的 end_pattern
                current_end_pattern = local_end_pattern if local_end_pattern else end_pattern_dynamic
                if regex.search(current_end_pattern, cleaned_text):
                    if i > mid_page:
                        end_page = i
                        break

        return start_page, mid_page, end_page

    # 第一次提取尝试，使用初始的 begin_pattern
    start_page, mid_page, end_page = run_extraction(begin_pattern)

    # 如果第一次提取失败，则使用新的 begin_pattern 和 end_pattern 重新提取
    if not (start_page and mid_page and end_page):
        print(f"第二次尝试 tobidders_notice!")
        pdf_document = PdfReader(pdf_path)
        start_page, mid_page, end_page = extract_pages_twice_tobidders_notice(pdf_document, common_header, begin_page)
        if start_page and end_page and mid_page:
            return start_page, mid_page, end_page
        else:
            # 定义新的 begin_pattern 和 end_pattern
            new_begin_pattern = regex.compile(
                r'.*(?:投标人|磋商|供应商|谈判供应商|磋商供应商)须知\s*$|'
                r'(?:一\s*、\s*)?(?:投标人?|磋商|供应商)须知前附表',
                regex.MULTILINE
            )
            new_end_pattern = regex.compile(
                r'第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$',
                regex.MULTILINE
            )
            print("第三次尝试 tobidders_notice! ")
            # 第二次提取尝试，使用新的模式
            start_page, mid_page, end_page = run_extraction(new_begin_pattern, new_end_pattern)

    return start_page, mid_page, end_page


def extract_pages_twice_tobidders_notice(pdf_document, common_header, begin_page):
    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)\s*(?:(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知)+',
        regex.MULTILINE
    )
    end_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
    )
    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|文件构成|文件组成')

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

    # 提取第二部分
    start_page2 = end_page1

    # 检查end_page1页面的内容
    text = pdf_document.pages[end_page1].extract_text() or ""
    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)
        # 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
            return start_page1, end_page1, end_page1

    # 如果不包含排除关键词，继续提取第二部分
    _, end_page2 = extract_pages_generic(pdf_document, end_pattern, end_pattern, start_page2 - 1, common_header,
                                         exclusion_pattern, output_suffix)

    if end_page2 is None:
        return start_page1, end_page1, ""

    return start_page1, end_page1, end_page2


def extract_pages_qualification(pdf_document, begin_page, common_header):
    # 开始匹配模式，仅匹配“附录”、“附件”或“附表”
    begin_pattern = regex.compile(
        r'^(?:附录(?:一|1)?[：:]?|附件(?:一|1)?[：:]?|附表(?:一|1)?[：:]?)',
        regex.MULTILINE
    )

    # 优先匹配模式，匹配以“资格性检查”、“资格审查”或“符合性审查”开头
    priority_pattern = regex.compile(
        r'^(资格性检查|资格审查|符合性审查)',
        regex.MULTILINE
    )

    # 结束匹配模式 - 附录、附件、附表等
    end_pattern_attachment = regex.compile(
        r'^(?:附录.*?[：:]|附件.*?[：:]|附表.*?[：:]|附件\s*\d+).*$',
        regex.MULTILINE
    )
    # 结束匹配模式 - 章节标题
    end_pattern_chapter = regex.compile(
        r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$',
        regex.MULTILINE
    )

    print("第二次尝试 qualification:匹配附件")
    start_page = None
    end_page = None
    include_keywords = ["资格审查", "资质审查", "符合性审查", "资格性检查", "符合性检查", "资格检查"]
    exclude_keywords = ["声明函", "承诺函"]

    # 从指定的开始页开始遍历
    for i, page in enumerate(pdf_document.pages[begin_page:], start=begin_page):
        text = page.extract_text()
        if text:
            cleaned_text = clean_page_content(text, common_header)

            # 优先检查是否匹配优先模式
            priority_match = priority_pattern.search(cleaned_text)
            if priority_match and start_page is None:
                start_page = i
                # print(f"匹配到优先模式，设置起始页为: {start_page}")
                continue
            else:
                # 如果未匹配优先模式，则按照一般模式进行判断
                if (
                        any(keyword in cleaned_text for keyword in include_keywords) and
                        all(keyword not in cleaned_text for keyword in exclude_keywords) and
                        start_page is None
                ):
                    if begin_pattern.search(cleaned_text):
                        start_page = i
                        continue
                        # print(f"匹配到附录等模式，设置起始页为: {start_page}")

            # 确定结束页 - 附录、附件、附表等
            if start_page is not None and end_pattern_attachment.search(cleaned_text):
                # 额外检查当前页面是否不包含任何 include_keywords
                if not any(keyword in cleaned_text for keyword in include_keywords):
                    if i > start_page:
                        end_page = i
                        # print(f"找到结束页 (附件类): {end_page}")
                        break  # 找到结束页后退出循环
                else:
                    print(f"当前页面匹配附件结束模式但包含 include_keywords，继续查找。页面: {i}")

            # 确定结束页 - 章节标题
            elif start_page is not None and end_pattern_chapter.search(cleaned_text):
                if i > start_page:
                    end_page = i
                    print(f"找到结束页 (章节标题): {end_page}")
                    break  # 找到结束页后退出循环
    return start_page, end_page


def extract_pages_twice(pdf_path, output_folder, output_suffix, common_header, begin_page):
    try:
        exclusion_pattern = regex.compile(
            r'文件的构成|文件的组成|须对应|需对应|须按照|需按照|须根据|需根据|文件组成|文件构成')
        pdf_document = PdfReader(pdf_path)
        patterns = None
        start_page = None
        end_page = None

        if output_suffix == "procurement":
            patterns = [get_patterns_for_procurement()]
        elif output_suffix == "evaluation_method" or output_suffix == "qualification2" or output_suffix == "qualification3":
            patterns = [get_patterns_for_evaluation_method()]
        elif output_suffix == "notice":
            patterns = [get_patterns_for_notice()]
        elif output_suffix == "qualification1":
            start_page, end_page = extract_pages_qualification(pdf_document, begin_page, common_header)
        if patterns:
            for pattern_pair in patterns:
                start_page, end_page = extract_pages_generic(pdf_document, pattern_pair[0], pattern_pair[1], begin_page,
                                                             common_header, exclusion_pattern, output_suffix)
                if start_page is not None and end_page is not None:
                    break

        if start_page is None or end_page is None:
            if output_suffix == "qualification1":
                # print(f"second: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！")
                print("第三次尝试资格审查:尝试提取评分办法章节...")
                base_file_name = os.path.splitext(os.path.basename(pdf_path))[0]
                evaluation_method_file = os.path.join(output_folder, f"{base_file_name}_evaluation_method.pdf")
                if os.path.isfile(evaluation_method_file):
                    print(f"找到评分办法章节文件: {evaluation_method_file}，生成新文件。")
                    # 获取文件路径和文件名
                    new_file_name = f"{base_file_name}_qualification2.pdf"
                    new_file_path = os.path.join(output_folder, new_file_name)
                    # 复制文件
                    with open(evaluation_method_file, 'rb') as original_file:
                        with open(new_file_path, 'wb') as new_file:
                            new_file.write(original_file.read())
                    return new_file_path
                else:
                    temp = truncate_pdf_main(pdf_path, output_folder, 2, "qualification2")
                    if len(temp) > 0:
                        return temp[0]
                    else:
                        return ""
            else:
                print(f"second: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！")
                return ""
        return save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix)
    except Exception as e:
        print(f"Error in extract_pages_twice: {e}")
        return ""


def save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix):
    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 ""

        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 >= len(pdf_document.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 - 1 >= 0:
            before_pdf_path = os.path.join(output_folder, f"{base_file_name}_before.pdf")
            before_doc = PdfWriter()
            for page_num in range(0, start_page):
                before_doc.add_page(pdf_document.pages[page_num])
            with open(before_pdf_path, 'wb') as f:
                before_doc.write(f)
            # print(f"已保存页面从 0 到 {start_page - 1} 为 {before_pdf_path}")

        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 get_start_and_common_header(input_path):
    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 > 10:
            return common_header, 0  # 如果页码大于10，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 truncate_pdf_main(input_path, output_folder, selection, output_suffix="default"):
    try:
        # 检查是否为文件夹
        if os.path.isdir(input_path):
            generated_files = []
            for file_name in os.listdir(input_path):
                file_path = os.path.join(input_path, file_name)
                if is_pdf_or_doc(file_path):
                    result = process_input(file_path, output_folder, selection, output_suffix)
                    if isinstance(result, tuple):
                        generated_files.extend([f if f else "" for f in result])
                    else:
                        generated_files.append(result)
            return generated_files

        # 单文件情况
        elif os.path.isfile(input_path) and is_pdf_or_doc(input_path):
            return process_input(input_path, output_folder, selection, output_suffix)

        else:
            print("提供的路径既不是文件夹也不是PDF文件。")
            return ['']

    except Exception as e:
        print(f"Error in truncate_pdf_main: {e}")
        return ['']  # 返回空字符串


def process_input(input_path, output_folder, selection, output_suffix):
    try:
        # 创建输出文件夹
        if not os.path.exists(output_folder):
            os.makedirs(output_folder)

        # 获取起始和通用页眉
        common_header, last_begin_index = get_start_and_common_header(input_path)
        begin_page = last_begin_index if last_begin_index != 0 else {
            4: 1,
            2: 5,
            3: 5,
            1: 0,
            5: 3
        }.get(selection, 0)

        # 根据选择设置对应的模式和结束模式
        if selection == 1:
            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*$',
                regex.MULTILINE
            )
            end_pattern = regex.compile(r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九十1-9]+(?:章|部分)\s*[\u4e00-\u9fff、()（）]+\s*$|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知前附表\s*$', regex.MULTILINE)
            local_output_suffix = "notice"
        elif selection == 2:
            begin_pattern = regex.compile(
                r'^第[一二三四五六七八九十]+(?:章|部分)\s*(?=.*(?:磋商|谈判|评标|评定|评审))(?=.*(?:办法|方法|内容))')
            end_pattern = regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+')
            local_output_suffix = "evaluation_method"
        elif selection == 3:
            begin_pattern = regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(资格审查).*', regex.MULTILINE)
            end_pattern = regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', regex.MULTILINE)
            local_output_suffix = "qualification1"
        elif selection == 4:
            begin_pattern = regex.compile(
                r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知+|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|供应商|谈判供应商|磋商供应商)须知前附表\s*$',
                regex.MULTILINE)
            end_pattern = None
            local_output_suffix = "tobidders_notice"
        elif selection == 5:
            begin_pattern = regex.compile(
                r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:服务|项目|商务|技术).*?要求|^第[一二三四五六七八九十百千]+(?:章|部分)(?!.*说明).*(?:采购内容|采购要求|需求).*')  # 包头中有一章'采购相关说明'
            end_pattern = regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+')
            local_output_suffix = "procurement"

            # begin_pattern = regex.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', regex.MULTILINE)
            # end_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)

        elif selection == 6:
            begin_pattern = regex.compile(r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:格式).*')
            end_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)
            local_output_suffix = "format"
        else:
            print("无效的选择:请选择1-5")
            return ['']

        # 如果传入的 output_suffix 是 'default'，则使用本地生成的 output_suffix
        if output_suffix == "default":
            output_suffix = local_output_suffix

        # 调用实际处理文件内容的函数
        return process_files(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix)

    except Exception as e:
        print(f"Error in process_input: {e}")
        return ['']


def truncate_pdf_multiple(pdf_path, output_folder, logger):
    # 新增逻辑：检查 PDF 总页数
    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(f"PDF页数小于或等于50页，跳过切分逻辑。")
            return ['', '', '', '', '', '', '']
    except Exception as e:
        logger.error(f"无法读取 PDF 页数: {e}")
        return ['', '', '', '', '', '', '']

    base_file_name = os.path.splitext(os.path.basename(pdf_path))[0]
    truncate_files = []

    # 定义要处理的选择范围
    selections = range(1, 6)

    # 使用 ThreadPoolExecutor 进行多线程处理
    with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor:
        # 提交所有任务并保持 selection 顺序
        future_to_selection = {
            selection: executor.submit(truncate_pdf_main, pdf_path, output_folder, selection, output_suffix="default")
            for selection in selections}

        # 按 selection 顺序收集结果
        for selection in selections:
            future = future_to_selection.get(selection)
            try:
                files = future.result()
                if files:
                    truncate_files.extend(files)
            except Exception as e:
                logger.error(f"Selection {selection} 生成了一个异常: {e}")

    # 定义合并后的输出路径
    merged_output_path = os.path.join(output_folder, f"{base_file_name}_merged_baseinfo.pdf")
    # 调用 merge_selected_pdfs 并获取返回值
    merged_path = merge_selected_pdfs_for_goods(output_folder, truncate_files, merged_output_path, base_file_name)
    if merged_path:
        # 合并成功，添加合并后的文件路径
        truncate_files.append(merged_path)
        # logger.info(f"已生成合并文件: {merged_output_path}")
    else:
        # 合并失败，添加空字符串
        truncate_files.append("")
        logger.warning(f"合并失败，没有生成合并文件 for {pdf_path}")
    logger.info("已截取文件路径" + str(truncate_files))
    return truncate_files


# 小解析，只需要前三章内容
def truncate_pdf_specific_goods(pdf_path, output_folder, selections, unique_id="123"):
    """
    处理 PDF 文件，选择指定的 selections，并合并结果。

    Args:
        pdf_path (str): 要处理的 PDF 文件路径。
        output_folder (str): 截取后的文件保存文件夹路径。
        selections (iterable): 要处理的 selection 列表。

    Returns:
        list: 截取的文件路径列表，包括合并后的文件路径（如果有）。
    """
    logger = get_global_logger(unique_id)
    # 新增逻辑：检查 PDF 总页数
    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(f"PDF页数小于或等于50页，跳过切分逻辑。")
            return ['', '', '', '']
    except Exception as e:
        logger.error(f"无法读取 PDF 页数: {e}")
        return ['', '', '', '']
    base_file_name = os.path.splitext(os.path.basename(pdf_path))[0]
    truncate_files = []

    # 使用 ThreadPoolExecutor 进行多线程处理
    with concurrent.futures.ThreadPoolExecutor(max_workers=len(selections)) as executor:
        # 提交所有任务并保持 selection 顺序
        future_to_selection = {
            selection: executor.submit(truncate_pdf_main, pdf_path, output_folder, selection, output_suffix="default")
            for selection in selections}

        # 按 selection 顺序收集结果
        for selection in selections:
            future = future_to_selection.get(selection)
            try:
                files = future.result()
                if files:
                    if isinstance(files, list):
                        truncate_files.extend(files)
                    elif isinstance(files, str):
                        truncate_files.append(files)
            except Exception as e:
                logger.error(f"Selection {selection} 生成了一个异常: {e}")

    # 定义合并后的输出路径
    merged_output_path = os.path.join(output_folder, f"{base_file_name}_merged_baseinfo.pdf")
    # 调用 merge_selected_pdfs 并获取返回值
    merged_path = merge_selected_pdfs_for_goods(output_folder, truncate_files, merged_output_path, base_file_name)
    if merged_path:
        # 合并成功，添加合并后的文件路径
        truncate_files.append(merged_path)
        # logger.info(f"已生成合并文件: {merged_output_path}")
    else:
        # 合并失败，添加空字符串
        truncate_files.append("")
        logger.warning(f"合并失败，没有生成merged_baseinfo for {pdf_path}")
    return truncate_files


# TODO:交通智能系统和招标(1)(1)文件有问题  包头 绍兴     工程标中，判断是符合性审查之后，可以将它们设为同一章

# ztbfile.pdf少资格评审  包头少符合性评审
if __name__ == "__main__":
    logger = get_global_logger("123")
    # input_path = r"C:\Users\Administrator\Desktop\new招标文件\货物标"
    # input_path = r"C:\Users\Administrator\Desktop\招标文件-采购类\2024-贵州-贵州医科大学附属医院导视系统零星制作安装项目.pdf"
    # input_path="C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\zbtest4_evaluation_method.pdf"
    # input_path = r"C:\Users\Administrator\Desktop\货物标\zbfiles\2-招标文件（广水市教育局封闭管理）.pdf"
    input_path=r"C:\Users\Administrator\Desktop\fsdownload\ff2acdba-3a55-48a7-aa7a-61d9f89b909a\ztbfile.pdf"
    output_folder = r"C:\Users\Administrator\Desktop\fsdownload\ff2acdba-3a55-48a7-aa7a-61d9f89b909a\tmp"
    # output_folder = r"C:\Users\Administrator\Desktop\new招标文件\output2"
    # files = truncate_pdf_multiple(input_path, output_folder,logger)
    # selections = [1,4]
    # files=truncate_pdf_specific_goods(input_path,output_folder,selections)
    # print(files)
    selection = 4  # 例如：1 - 公告, 2 - 评标办法, 3 - 资格审查后缀有qualification1或qualification2（与评标办法一致）  4.投标人须知前附表part1 投标人须知正文part2   5-采购需求
    generated_files = truncate_pdf_main(input_path, output_folder, selection)
    print(generated_files)