python识别提取楼宇地址

import re
import pandas as pd
import os
import glob
def building_discriminate(s):
    try:
        d = re.search("号(.*(座|大厦|栋|楼|中心|广场))", s)
        return re.sub('\d+楼','',d.group(1))\
            .replace('蔡屋围', '')\
            .replace('清水河', '')\
            .replace('笋岗', '')\
            .replace('一楼', '') \
            .replace('二楼', '') \
            .replace('三楼', '') \
            .replace('四楼', '') \
            .replace('五楼', '') \
            .replace('六楼', '') \
            .replace('七楼', '') \
            .replace('八楼', '') \
            .replace('九楼', '') \
            .replace('A栋', '') \
            .replace('B栋', '') \
            .replace('C栋', '') \
            .replace('D栋', '')\
            .replace('1栋','') \
            .replace('2栋','') \
            .replace('3栋','') \
            .replace('4栋','') \
            .replace('5栋','')\
            .replace('6栋','')\
            .replace('7栋','')\
            .replace('8栋','')\
            .replace('9栋','')\
            .replace('北楼','')\
            .replace('南楼','')\
            .replace('西楼','')\
            .replace('东楼','')\
            .replace('A座','')\
            .replace('B座','')\
            .replace('C座','')\
            .replace('D座','')\
            .replace('1号楼','')\
            .replace('2号楼','')\
            .replace('3号楼','')\
            .replace('4号楼','')\
            .replace('5号楼','')\
            .replace('6号楼','')\
            .replace('7号楼','')\
            .replace('8号楼','')\
            .replace('9号楼','')\
            .replace('10号楼','')
            
         
                            
                 
            
                            
            
    except:
        try:
            d = re.search("(侧|角|街道|路|社区)(.*(座|大厦|栋|楼|中心|广场)+([A-Z]座)?)", s)
            return re.sub('.*社区','',re.sub('\d+层','',re.sub('\d+楼', '', d.group(2)))) \
                .replace('蔡屋围', '') \
                .replace('清水河', '') \
                .replace('笋岗', '').replace('社区', '') \
                .replace('一楼', '') \
                .replace('二楼', '') \
                .replace('三楼', '') \
                .replace('四楼', '') \
                .replace('五楼', '') \
                .replace('六楼', '') \
                .replace('七楼', '') \
                .replace('八楼', '') \
                .replace('九楼', '')\
                .replace('A栋', '') \
                .replace('B栋', '') \
                .replace('C栋', '') \
                .replace('D栋', '') \
                .replace('1栋','') \
                .replace('2栋','') \
                .replace('3栋','') \
                .replace('4栋','') \
                .replace('5栋','') \
                .replace('6栋','')\
                .replace('7栋','')\
                .replace('8栋','')\
                .replace('9栋','')\
                .replace('北楼','')\
                .replace('南楼','')\
                .replace('西楼','')\
                .replace('东楼','')\
                .replace('A座','')\
                .replace('B座','')\
                .replace('C座','')\
                .replace('D座','')\
                .replace('1号楼','')\
                .replace('2号楼','')\
                .replace('3号楼','')\
                .replace('4号楼','')\
                .replace('5号楼','')\
                .replace('6号楼','')\
                .replace('7号楼','')\
                .replace('8号楼','')\
                .replace('9号楼','')\
                .replace('10号楼','')
                
                
                
        except:
            return 'NULL'

# 遍历指定目录下的所有 Excel 文件
for file_path in glob.glob('C:/Users/win10/Documents/*.xlsx'):
    # 读取 Excel 文件到 DataFrame
    df = pd.read_excel(file_path)
    # 在 DataFrame 中添加新列
    df['楼宇'] = df['企业地址'].map(building_discriminate, na_action='ignore')
    # 将 DataFrame 写入原始 Excel 文件
    df.to_excel(file_path, index=False)