zbparse/flask_app/main/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, chapter_pattern, begin_page, end_phrase_pattern, output_suffix):
    # 打开PDF文件
    pdf_document = PdfReader(pdf_path)
    start_page = None
    end_page = None

    qualification_pattern = re.compile(r'资格审查|资质条件|能力')
    # 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(chapter_pattern, cleaned_text) and i > begin_page:
                if output_suffix == "invalid" and start_page:           #仅当提取Invalid的时候，判断初始页码是第一个匹配到的页码，因为招标编号可能存在多个，后面的覆盖前面
                    continue
                if output_suffix == "qualification" and not re.search(qualification_pattern, cleaned_text):
                    # 如果是资格审查条件，但当前页不包含相关词汇，则不执行任何操作
                    pass
                else:
                    start_page = i
            if start_page is not None and re.search(end_phrase_pattern, cleaned_text) and i > (start_page+1):
                is_invalid_condition = output_suffix == "invalid" and i > 30
                if is_invalid_condition or output_suffix != "invalid":
                    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, chapter_pattern, begin_page, end_phrases, output_suffix,selection):
    # 确保输出文件夹存在
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)
    if(selection==3 or selection==4 or selection==5):
        end_phrase_pattern = re.compile('|'.join([phrase for phrase in end_phrases]), re.MULTILINE)
    else:
        end_phrase_pattern = re.compile('|'.join([re.escape(phrase) for phrase in end_phrases]))

    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, chapter_pattern, begin_page, end_phrase_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, chapter_pattern, begin_page, end_phrase_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"
        pattern = re.compile(r'第[一二三四五六七八九十]+章\s*投标人须知')
        begin_page = 3
        end_phrases = ["投标人须知正文"]
        output_suffix = "tobidders_notice_table"
    elif selection == 2:
        # Configure patterns and phrases for "评标办法"
        pattern = re.compile(r'第[一二三四五六七八九十]+章\s*评标办法')
        begin_page = 10
        end_phrases = ["评标办法正文", "评标办法"]
        output_suffix = "evaluation_method"
    elif selection == 3:
        # Configure patterns and phrases for "投标人须知正文"
        pattern = re.compile(r'投标人须知正文')
        begin_page = 5
        end_phrases = [
            r'^第[一二三四五六七八九十]+章\s*评标办法',r'^评标办法前附表',r'^附录：', r'^附录一：',r'^附件：', r'^附件一：',r'^附表：', r'^附表一：',r'^附录:', r'^附录一:',r'^附件:', r'^附件一:',r'^附表:', r'^附表一:',
        ]
        output_suffix = "tobidders_notice"
    elif selection==4:
        pattern = re.compile(r'第[一二三四五六七八九十]+章\s*招标公告|第一卷|招标编号:|招标编号：')
        begin_page = 0
        end_phrases = [
            r'第[一二三四五六七八九十]+章\s*合同',
            r'：清标报告',# 添加了新的匹配项
            r':清标报告'
        ]
        output_suffix="invalid"
    elif selection==5:
        appendix_pattern = r'^附录(?:一)?[：:]|^附件(?:一)?[：:]|^附表(?:一)?[：:]'
        pattern = re.compile(appendix_pattern)
        begin_page=5
        end_phrases = [r'评标办法正文', r'评标办法',appendix_pattern]
        output_suffix="qualification"
    else:
        print("无效的选择")
        return None

    # Process the selected input
    return process_input(input_path, output_folder, pattern, begin_page, end_phrases, output_suffix,selection)

def truncate_pdf_multiple(input_path, output_folder):
    truncate_files = []
    for selection in range(1, 6):
        files = truncate_pdf_main(input_path, output_folder, selection)
        truncate_files.extend(files)
    return truncate_files

if __name__ == "__main__":
    input_path = "C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest5.pdf"
    output_folder = "C:\\Users\\Administrator\\Desktop\\招标文件\\test"
    truncate_pdf_multiple(input_path,output_folder)
    # selection = 5  # 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)