무회blog

python: 정규식 예제,test 본문

Python

python: 정규식 예제,test

최무회 2021. 3. 15. 00:48
import re
import pandas as pd 
import os, time 
from html2text import html2text
from datetime import date

from selenium.webdriver.common.service import _HAS_NATIVE_DEVNULL

today = date.today()
today = str(today)

# str = "I am 12 years old , but he is 5 월 years old."
# # p = re.compile(r'\d+')
# p = re.compile(r'원|세')
# ss = p.findall(str)
# print(len(ss))


# print(today)
# #  경로 체크 하기 

patt = 'D:\Src\python\spyder\writeFile\휘경동_parse_2021-03-15.txt'

p = re.compile(r'월세|평|층|구|동')
tts = ""
yuezu = []
pingfang = []
diyu = []
with open(patt,'r',encoding='utf-8') as file:
    for line in file.readlines():
        rs = p.findall(line)
        if(len(rs)> 0 ):
            if(rs[0] == '월세'):                
                if(len(line)<15):
                    yuezu.append(line)
        if(len(rs)> 0 ):
            if(rs[0] == '평'):                
                if(len(line)<15):
                    pingfang.append(line)        
        if(len(rs)> 0 ):
            if(rs[0] == '구' or rs[0] =='동'):                
                if(len(line)<10):
                    diyu.append(line)
                    
dics = {'yuezu': yuezu, 'pingfang':pingfang, 'diyu':diyu}
filename = 'D:\Src\python\spyder\writeFile\휘경동_parse_2021-03-15.xlsx'
df = pd.DataFrame(dics).to_excel(filename)
print(df)

# print('len(yuezu): ' ,len(yuezu))
# print('len(pingfang): ' ,len(pingfang))
# print('len(diyu): ' ,len(diyu))
# print(pingfang)

휘경동_parse_2021-03-15.txt
0.01MB

Comments