给大家提供了便利,帮助到大家的记得点个赞~ 直接上代码:
import os labels = [] aaa = [] #用来存每个数据重复出现的次数 new_list = [] test_txt= open('C:/Users/GJF/Desktop/111.txt') #需要处理的数据 for line in test_txt: #循环读文件中的每一行进行处理 # print(type(line)) code = line.split(',') #以逗号分隔 label = code[1] #要第二个逗号的内容 # print(label) labels.append(label) #将提取出来处理的内容放到列表里面 # print(labels) # print(labels) mylist = set(labels ) #myset是另外一个列表,里面的内容是mylist里面的无重复项 print(mylist) mylist = list(mylist) ##set提取出来的无重复项会显示不是list,这里转化成list方便后面处理 # print(mylist) for item in mylist: # print(item) aaa.append(labels.count(item)) #统计数量 print(aaa) #筛选部分,将aaa中总数大于2的提取,写入新txt: num = -1 for i in aaa: num = num+1 if i > 2: print(i) with open('C:/Users/GJF/Desktop/111.txt','r') as r: lines=r.readlines() print(lines) with open('C:/Users/GJF/Desktop/1111.txt','a') as w: for l in lines: print(l) code_l = l.split(',') #code 以,分隔 bbb = code_l[1] print(bbb) # print(code[1]) # print(mylist[i-1]) if code_l[1] == mylist[num]: w.write(l)