zbparse/flask_app/货物标/货物标截取pdf.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

def clean_page_numbers(text):
    # 使用正则表达式删除页码
    # 假设页码在文本的最开始，紧跟着文字且无空格分隔
    cleaned_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
    # 删除结尾的页码
    cleaned_text = re.sub(r'\s+\d+\s*$', '', cleaned_text)
    # 删除形如 /129 的页码
    cleaned_text = re.sub(r'\s*\/\s*\d+\s*', '', cleaned_text)
    return cleaned_text
def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
    # 打开PDF文件
    pdf_document = PdfReader(pdf_path)
    start_page = None
    end_page = None
    # 遍历文档的每一页，查找开始和结束短语的位置
    for i in range(len(pdf_document.pages)):
        page = pdf_document.pages[i]
        text = page.extract_text()
        if text:
            cleaned_text = clean_page_numbers(text)
            if 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+1):
                end_page = i
                break
    # 确保找到了起始和结束页面
    if start_page is None or end_page is None:
        print(f"未找到起始或结束页在文件 {pdf_path} 中！")
        return None

    # 创建一个新的PDF文档保存截取的页面
    base_file_name = os.path.splitext(os.path.basename(pdf_path))[0]  # Get the base name without extension
    output_pdf_path = os.path.join(output_folder, f"{base_file_name}_{output_suffix}.pdf")
    output_doc = PdfWriter()

    # 添加需要的页面，从 start_page 开始，包括 end_page
    for page_num in range(start_page, end_page + 1):
        output_doc.add_page(pdf_document.pages[page_num])
    # 保存新的PDF文件
    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 process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
    # 确保输出文件夹存在
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)
    if os.path.isdir(input_path):
        generated_files = []
        # 遍历文件夹内的所有PDF文件
        for file in os.listdir(input_path):
            if file.endswith(".pdf"):
                pdf_path = os.path.join(input_path, file)
                output_pdf_path = extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix)
                if output_pdf_path and os.path.isfile(output_pdf_path):
                    generated_files.append(output_pdf_path)
        return generated_files
    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 and os.path.isfile(output_pdf_path):
            return [output_pdf_path]  # 以列表形式返回，以保持一致性
    else:
        print("提供的路径既不是文件夹也不是PDF文件。")
    return []


def truncate_pdf_main(input_path, output_folder, selection):
    if selection == 1:
        # Configure patterns and phrases for "投标人须知前附表"
        begin_pattern = re.compile(r'第[一二三四五六七八九十百千]+章.*?(?:服务|项目|商务).*?要求|第[一二三四五六七八九十百千]+章.*?采购.*')
        begin_page = 5
        end_pattern = re.compile(r'第[一二三四五六七八九十百千]+章\s*(资格审查|评标方法|评审办法|评定办法)')
        # 示例文本进行测试
        output_suffix = "tobidders_notice_table"

    else:
        print("无效的选择")
        return None

    # Process the selected input
    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\\WPSDrive\\292826853\\WPS云盘\\应用\\输出为PDF\\公安局音视频监控系统设备采购项目(定稿）_20240829133603.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)