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
from flask_app.main.format_change import docx2pdf


def clean_page_content(text, common_header):
    # 首先删除抬头公共部分
    if common_header:  # 确保有公共抬头才进行替换
        for header_line in common_header.split('\n'):
            if header_line.strip():  # 只处理非空行
                # 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 eg:89/129   这个代码分三步走可以把89/129完全删除
    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
    text = re.sub(r'\s+\d+\s*$', '', text)  # 删除结尾的页码
    text = re.sub(r'\s*\/\s*\d+\s*', '', text)  # 删除形如 /129 的页码

    return text
def extract_common_header(pdf_path):
    pdf_document = PdfReader(pdf_path)
    headers = []
    total_pages = len(pdf_document.pages)
    middle_page = total_pages // 2  # 计算中间页

    # 确保中间页前后各一页（共3页），如果不足3页，则尽可能取足
    start_page = max(0, middle_page - 1)
    num_pages_to_read = 3

    for i in range(start_page, min(start_page + num_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(first_lines)

    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
    common_headers = []
    for lines in zip(*headers):
        # 在每一行中寻找公共单词
        common_line = set(lines[0].split()).intersection(*[set(line.split()) for line in lines[1:]])
        if common_line:
            common_headers.append(' '.join(common_line))

    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):
    # 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_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)
    generated_files = []
    if os.path.isdir(input_path):
        # 遍历文件夹内的所有PDF文件
        for file in os.listdir(input_path):
            file_path = os.path.join(input_path, file)
            if is_pdf_or_doc(file):
                pdf_path = convert_to_pdf(file_path)
                output_pdf_path = extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern,
                                                output_suffix)
                if output_pdf_path:
                    generated_files.append(output_pdf_path)
    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:
            generated_files.append(output_pdf_path)
    else:
        print("提供的路径既不是文件夹也不是PDF文件。")
    return generated_files

def extract_pages_twice(pdf_path, output_folder, output_suffix,common_header):
    pdf_document = PdfReader(pdf_path)
    begin_page=5
    start_page = None
    end_page = None
    # 定义用于检测是否包含"文件的构成"的正则表达式
    exclusion_pattern = re.compile(r'文件的构成|文件的组成')
    if output_suffix == "procurement":
        begin_pattern = re.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',
            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
        )
        for i in range(len(pdf_document.pages)):
            page = pdf_document.pages[i]
            text = page.extract_text() or ""
            cleaned_text = clean_page_content(text,common_header)
            if re.search(begin_pattern, cleaned_text) and i > begin_page and not re.search(exclusion_pattern, cleaned_text):
                start_page = i
            if start_page is not None and re.search(end_pattern, cleaned_text) and i > start_page:
                end_page = i
                break
        if start_page is None or end_page is None:
            print(f"twice: 未找到起始或结束页在文件 {pdf_path} 中！")
            return ""
        else:
            return save_extracted_pages(pdf_document,start_page, end_page, pdf_path,output_folder, output_suffix)


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)
        start_page = None
        end_page = None
        for i in range(len(pdf_document.pages)):
            page = pdf_document.pages[i]
            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) and i > begin_page:
                start_page = i
            if start_page is not None and re.search(end_pattern, cleaned_text) and i > start_page:
                end_page = i
                break
        if start_page is None or end_page is None:
            if output_suffix == "procurement":
                return extract_pages_twice(pdf_path, output_folder, output_suffix,common_header)
            else:
                print(f"未找到起始或结束页在文件 {pdf_path} 中！")
                return None

        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 None

def save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix):
    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")
    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"已截取并保存页面从 {start_page} 到 {end_page} 为 {output_pdf_path}")
    return output_pdf_path


def truncate_pdf_main(input_path, output_folder, selection):
    if selection == 1:
        # 更新的正则表达式以匹配"第x章"和"第x部分"，考虑到可能的空格和其他文字
        begin_pattern = re.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.*',
            # r'^[一二三四五六七八九十百千]+、\s*采购清单',
        )
        begin_page = 5
        end_pattern = re.compile(
            r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+'
        )
        output_suffix = "procurement"

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

    # 调用相应的处理函数
    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\\Desktop\\货物标\\zbfiles\\招标文件(107国道).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)