2020-工作代码

导出银行字典静综

import pandas as pd 
import numpy  as np
import os 
import re


text_list=[]
words=''
for root, dirs, files in os.walk('F:\\案件数据\\警综\\raw'):
            for name in files:
                if name[-5:]=='s.txt':
                    text_list.append(os.path.join(root, name))
for i in text_list:
#     print(i)
    try:
        with open(i,encoding='gbk') as f:
            text_word=f.read()
            words=words+text_word
    except:
        with open(i,encoding='utf8') as f:
            text_word=f.read()
            words=words+text_word
# words_list=re.findall('<.*c=(.*d=.*)" p',words) 
# for i in words_list:
#     words_clean=re.findall('\d+',i)[0]+'-'+re.findall('d="(.*)',i)[0]
    
list_data=[]
for i in words_list:
    words_clean=re.findall('\d+',i)[0]+'-'+re.findall('d="(.*)',i)[0]
    list_data.append(words_clean)
data={'银行名称':list_data}
DF=pd.DataFrame(data)
DF.to_excel("警综字典.xlsx",index=False)