域名匹配

import requests
import time
import xlrd
import xlwt
import threading
import threadpool
import socket
import os

def debug():
import inspect
caller_name = inspect.stack()[1][3]
print ("[DEBUG]: enter {}()".format(caller_name) )

class pipei:

    def __init__(self,xls):
            self.dict1={}
            self.domains=[]
            self.xls=xls
    
    def url_pipe(self):
            #data=xlrd.open_workbook('C:\\Users\\ThinkPad\\Desktop\kl\\URL_IP.xlsx')
            data=xlrd.open_workbook(self.xls)
            table=data.sheets()[0]
            for row_index in range(table.nrows):
                    value = table.cell(rowx=row_index,colx=0).value
                    self.domains.append(value)
            for domain in self.domains:
                        self.dict1[domain]=0
                        
            
            for root, dirs, files in os.walk('C:\\Users\\ThinkPad\\Desktop\\kl\\URL\\url'):
                List1=files
                print(List1) #当前路径下所有非目录子文件  

            for file in files:
                i=0
                data=xlrd.open_workbook('C:\\Users\\ThinkPad\\Desktop\kl\\URL\\url\\%s' %file,ragged_rows = True)
                #data=xlrd.open_workbook('C:\\Users\\ThinkPad\\Desktop\kl\\URL\\5月22日志\\URL分类过滤日志列表 (1).xls')
                table=data.sheets()[0]
                print('----------------------------------------')
                for row_index in range(table.nrows):
                    value = table.cell(rowx=row_index,colx=4).value
                    for domain in self.domains:

                        if domain == value:
                            #print(value)
                            self.dict1['%s'%value]=self.dict1['%s'%value]+1
             
                        else:
                            continue

  
       
            for key,value in self.dict1.items():
                    if value >0:
                        print( key+':',value)

class yuming:

    def __init__(self,path):
            self.dict1={}
            self.path=path
    
    def yuming_pipe(self):
        #debug()
        
            for root, dirs, files in os.walk(self.path):
                List1=files
                print(List1) #当前路径下所有非目录子文件  

            for file in files:
                data=xlrd.open_workbook('C:\\Users\\ThinkPad\\Desktop\kl\\URL\\url\\%s' %file,ragged_rows = True)
            
                table=data.sheets()[0]
                print('----------------------------------------')
                for row_index in range(table.nrows):
                    domain = table.cell(rowx=row_index,colx=4).value
                    if domain not in self.dict1:
                            self.dict1[domain]=1
                    else:
                            self.dict1[domain]=self.dict1[domain]+1

            for key,value in self.dict1.items():
                     print( key+'::',value)                 

if name == ‘main’:
# pipei1=pipei(‘C:\Users\ThinkPad\Desktop\kl\URL_IP.xlsx’)

   # pipei1.url_pipe()

    yuming1=yuming('C:\\Users\\ThinkPad\\Desktop\\kl\\URL\\url')
    yuming1.yuming_pipe()