zbparse/flask_app/general/读取文件/按页读取pdf.py

import PyPDF2
import re  # 导入正则表达式库

from PyPDF2 import PdfReader


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
    text = re.sub(r'\s*[—-]\s*\d+\s*[—-]\s*', '', text)  # 删除形如 '—2—' 或 '-2-' 的页码
    return text
def extract_common_header(pdf_path):
    from PyPDF2 import PdfReader

    pdf_document = PdfReader(pdf_path)
    headers = []
    total_pages = len(pdf_document.pages)

    # 确定要读取的页数和起始页
    if total_pages == 2:
        pages_to_read = 2
        start_page = 0
    else:
        pages_to_read = 3
        middle_page = total_pages // 2
        start_page = max(0, middle_page - 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(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，按顺序保留
    common_headers = []
    for lines in zip(*headers):
        # 提取第一行的词汇顺序
        first_words = lines[0].split()
        # 筛选所有页面都包含的词汇，保持顺序
        common_line = [word for word in first_words if all(word in line.split() for line in lines[1:])]
        if common_line:
            common_headers.append(' '.join(common_line))

    return '\n'.join(common_headers)


def extract_text_by_page(file_path):
    common_header = extract_common_header(file_path)
    result = ""
    with open(file_path, 'rb') as file:
        reader = PyPDF2.PdfReader(file)
        num_pages = len(reader.pages)
        # print(f"Total pages: {num_pages}")
        for page_num in range(num_pages):
            page = reader.pages[page_num]
            text = page.extract_text()
            if text:
                print("-------------------")
                cleaned_text = clean_page_content(text,common_header)
                print(cleaned_text)
                result += cleaned_text
                # print(f"Page {page_num + 1} Content:\n{cleaned_text}")
            else:
                print(f"Page {page_num + 1} is empty or text could not be extracted.")
        return result

# import fitz  # PyMuPDF
# import re
#
#
# def clean_page_content(text, common_header):
#     if common_header:
#         for header_line in common_header.split('\n'):
#             if header_line.strip():
#                 text = re.sub(r'^' + re.escape(header_line.strip()) + r'\n?', '', text, count=1)
#
#     text = re.sub(r'^\s*\d+\s*(?=\D)', '', text)
#     text = re.sub(r'\s+\d+\s*$', '', text)
#     text = re.sub(r'\s*\/\s*\d+\s*', '', text)
#
#     return text
#
#
# def extract_common_header(pdf_path):
#     doc = fitz.open(pdf_path)
#     headers = []
#     total_pages = len(doc)
#
#     if total_pages == 2:
#         pages_to_read = 2
#         start_page = 0
#     else:
#         pages_to_read = 3
#         middle_page = total_pages // 2
#         start_page = max(0, middle_page - 1)
#
#     for i in range(start_page, min(start_page + pages_to_read, total_pages)):
#         page = doc[i]
#         text = page.get_text()
#         if text:
#             first_lines = text.strip().split('\n')[:3]
#             headers.append(first_lines)
#
#     doc.close()
#
#     if len(headers) < 2:
#         return ""
#
#     common_headers = []
#     for lines in zip(*headers):
#         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 extract_text_by_page(file_path):
#     common_header = extract_common_header(file_path)
#     result = ""
#     doc = fitz.open(file_path)
#     num_pages = len(doc)
#
#     for page_num in range(num_pages):
#         page = doc[page_num]
#         text = page.get_text()
#         if text:
#             cleaned_text = clean_page_content(text, common_header)
#             print(cleaned_text)
#             result += cleaned_text
#         else:
#             print(f"Page {page_num + 1} is empty or text could not be extracted.")
#
#     doc.close()
#     return result


if __name__ == '__main__':
    file_path = "C:\\Users\\Administrator\\Desktop\\new招标文件\\招标文件\\HBDL-2024-0181-001-招标文件.pdf"
    # file_path = 'C:\\Users\\Administrator\\Desktop\\货物标\\output4\\2-招标文件（2020年广水市中小学教师办公电脑系统及多媒体“班班通”设备采购安装项目）_tobidders_notice_part2.pdf'
    # file_path = 'C:\\Users\\Administrator\\Desktop\\货物标\\output4\\磋商文件_tobidders_notice_part2.pdf'
    # file_path = 'C:\\Users\\Administrator\\Desktop\\货物标\\截取test\\交警支队机动车查验监管系统项目采购_tobidders_notice_part1.pdf'
    # file_path = "C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest8.pdf"
    # file_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\45f650ce-e519-457b-9ad6-5840e2ede539\\ztbfile_procurement.pdf"
    # ress = extract_common_header(file_path)
    # print(ress)
    res=extract_text_by_page(file_path)
    # print(res)磋商文件_tobidders_notice_part2.pdf