读取PDF文件，并写入excel表

import re

from openpyxl import Workbook

pdf_name = 'D:/beifangzhongzhi/zhongye/百保科技/疾病/疾病.pdf'
import PyPDF2


def get_text(pdf_name):
    with open(pdf_name, 'rb') as file:
        reader = PyPDF2.PdfReader(file)
        num_pages = len(reader.pages)
        text_str = ''
        for i in range(num_pages):
            page = reader.pages[i]
            # 处理每一页的内容
            text = page.extract_text()
            text_str += text
        return text_str
# 创建一个新的工作簿
wb = Workbook()
# 选择默认的工作表
ws = wb.active
# 获取pdf文字内容
text = get_text(pdf_name)
# 获取重大疾病定义内容
zhongdajibing_old = \
    ''.join(text.split('第五十六条  重大疾病定义')[1]).split('第五十七条  中症疾病定义 ')[0]
'''通过数字加小数点分段，再根据第一个空格切割疾病名称和症状'''
zhongdajibing = zhongdajibing_old.replace('\n', '')
num_list = re.findall('\d+\. \d+', zhongdajibing_old)
for num in num_list:
    zhongdajibing = zhongdajibing.replace(num, '###')
zhongdajibing_list = zhongdajibing.split('###')
print('zhongdajibing_list:',len(zhongdajibing_list),zhongdajibing_list)
num=2
for zhongdajibing_new in zhongdajibing_list:
    if zhongdajibing_new == '  ':
        pass
    else:
        # 删除瑞华新瑞保终身重大疾病保险（ 2.0版）
        zhongdajibing_new = re.sub('\d+  瑞华新瑞保终身重大疾病保险（ 2.0版） ', '', zhongdajibing_new)
        zhongdajibing = zhongdajibing_new.split('  ')
        # 删除空格和开头数字
        zhongdajibing_z = [z for z in zhongdajibing if z != '' and z.isdigit() == False]
        zhongdajibing_z = ''.join(zhongdajibing_z).split(' ')
        zhongdajibing_y = [y.strip() for y in zhongdajibing if y != '' and y.isdigit() == False]
        name_old = zhongdajibing_y[0]
        name_old = re.sub('\d+', '', name_old)
        print(f'zhongdajibing_y:{len(zhongdajibing_y),zhongdajibing_y}')
        print(f'name_old:{name_old}')
        name = name_old.strip().split(' ')[0]
        if len(zhongdajibing_y)==1:
            zhengzhuang = ''.join(name_old.strip().split(' ')[1:])
        else:
            zhengzhuang = ''.join(name_old.strip().split(' ')[1:] + zhongdajibing_y[1:])
        print(name)
        print(zhengzhuang)
        # 数据可以直接分配到单元格中
        ws['A1'] = "疾病名字"
        ws['B1'] = "疾病描述"
        ws[f'A{num}'] = name
        ws[f'B{num}'] = zhengzhuang
        # 保存工作簿到文件
        wb.save("重大疾病定义.xlsx")
        print('\n')
        num+=1