zbparse/flask_app/testdir/截取文件格式.py

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.general.format_change import docx2pdf  # 确保此模块可用

def clean_page_content(text, common_header):
    """
    清理页面内容，通过删除公共抬头和页码。
    """
    if common_header:
        for header_line in common_header.split('\n'):
            if header_line.strip():
                # 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，合并多个正则表达式为一个
    text = re.sub(
        r'(^\s*\d+\s*(?=\D))|(\s+\d+\s*$)|(\s*/\s*\d+\s*)|(\s*[—-]\s*\d+\s*[—-]\s*)',
        '',
        text,
        flags=re.MULTILINE
    )
    return text
def extract_common_header(pdf_path):
    """
    从PDF的前几页提取公共抬头。
    """
    pdf_document = PdfReader(pdf_path)
    headers = []
    total_pages = len(pdf_document.pages)

    # 确定要读取的页数和起始页
    pages_to_read = 2 if total_pages == 2 else 3
    start_page = 0 if total_pages == 2 else max(0, (total_pages // 2) - 1)

    for i in range(start_page, min(start_page + 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(set(line.strip() for line in first_lines if line.strip()))

    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，按顺序保留
    common_headers = set.intersection(*headers)
    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):
#     """
#     如果是Word文档，则转换为PDF。
#     """
#     if file_path.lower().endswith(('.doc', '.docx')):
#         return docx2pdf(file_path)
#     return file_path


def save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix):
    """
    将提取的页面保存为新的PDF文件。
    """
    try:
        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 is None or end_page is None or start_page > end_page:
            print(f"无效的页面范围: {start_page} 到 {end_page} 文件: {pdf_path}")
            return ""

        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 for file {pdf_path}: {e}")
        return ""  # 返回空字符串


def find_page_indices(pdf_document, begin_pattern, end_pattern, begin_page, common_header):
    """
    查找起始页和结束页的索引。
    """
    start_page = None
    end_page = None
    total_pages = len(pdf_document.pages)

    for i, page in enumerate(pdf_document.pages):
        if i <= begin_page:
            continue
        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):
            start_page = i
            continue
        if start_page is not None and re.search(end_pattern, cleaned_text):
            end_page = i
            break

    return start_page, end_page if end_page else total_pages - 1


def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
    """
    根据开始和结束模式提取PDF页面。
    """
    try:
        common_header = extract_common_header(pdf_path)
        pdf_document = PdfReader(pdf_path)

        start_page, end_page = find_page_indices(pdf_document, begin_pattern, end_pattern, begin_page, common_header)

        if output_suffix == "format" and start_page is None:
            print(f"{output_suffix}: 未找到起始页，尝试二次提取！ 文件: {pdf_path}")
            # 二次提取逻辑，保留原有功能
            start_page, end_page = find_page_indices(
                pdf_document,
                re.compile(r'^(?:响应|投标).*?格式.*', re.MULTILINE),
                end_pattern,
                begin_page,
                common_header
            )
            if start_page is None:
                print(f"{output_suffix}: 未找到起始页，提取失败！ 文件: {pdf_path}")
                return ""

        if start_page is None:
            print(f"未找到起始页，提取失败！ 文件: {pdf_path}")
            return ""

        if end_page is None:
            end_page = len(pdf_document.pages) - 1
            print(f"{output_suffix}: 未找到结束页，默认截取到文件末尾。 文件: {pdf_path}")

        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 process_files(file_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
    """
    处理单个文件：转换为PDF（如果需要）并提取页面。
    """
    # pdf_path = convert_to_pdf(file_path)
    pdf_path=file_path
    return extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix) or ""


def process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
    """
    处理输入路径，可以是文件或目录。
    """
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)
    generated_files = []

    if os.path.isdir(input_path):
        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_files(file_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix)
                generated_files.append(result)
    elif os.path.isfile(input_path) and is_pdf_or_doc(input_path):
        result = process_files(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix)
        generated_files.append(result)
    else:
        print("提供的路径既不是文件夹也不是PDF/Word文件。")

    return [f for f in generated_files if f]  # 过滤空字符串


def truncate_pdf_main(input_path, output_folder, selection):
    """
    主函数，根据选择截取PDF内容。
    """
    try:
        if selection == 1:  # 投标文件格式
            begin_page = 10
            begin_pattern = re.compile(
                r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:响应|投标).*?格式.*',
                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
            )
            local_output_suffix = "format"
        else:
            print("无效的选择:请选择1")
            return []

        # 调用相应的处理函数
        return process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, local_output_suffix)
    except Exception as e:
        print(f"Error in truncate_pdf_main: {e}")
        return []


if __name__ == "__main__":
    # 定义输入和输出路径
    input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\包头市公安支队机动车查验监管系统招标文201907.pdf"
    output_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\新建文件夹"
    selection = 1  # 1 - 投标文件格式
    # 执行截取
    generated_files = truncate_pdf_main(input_path, output_folder, selection)
    print("生成的文件:", generated_files)