python基础_集合、文件操作

集合

集合是一个无序的且数据不会重复。有去重、关系测试的作用

list = ["11","22","33","44","55"]
list = set(list)
print(list,type(list))
结果为：
{‘33‘, ‘11‘, ‘22‘, ‘55‘, ‘44‘} <class ‘set‘>

关系测试list1 = set(["11","22","33","44","55"])
list2 = set(["55","66","77","88","99"])
list3 = set(["11","22"])
#list = set(list)
print(list1,type(list))
#交集
print(list1.intersection(list2))
#并集
print(list1.union(list2))
#差集
print(list1.difference(list2))#list1 有，list2没有
#子集
print(list1.issubset(list2))# False
print(list3.issubset((list1))) #True

print(list1.isdisjoint(list2))#没有交集

#反相差集
print(list1.symmetric_difference(list2))#把不是交集部分取出
结果为：
{‘55‘, ‘44‘, ‘11‘, ‘22‘, ‘33‘} <class ‘type‘>
{‘55‘}
{‘11‘, ‘22‘, ‘66‘, ‘44‘, ‘33‘, ‘88‘, ‘77‘, ‘99‘, ‘55‘}
{‘44‘, ‘11‘, ‘22‘, ‘33‘}
False
True
{‘11‘, ‘66‘, ‘22‘, ‘33‘, ‘88‘, ‘77‘, ‘99‘, ‘44‘}

文件操作

f = open("test","r",encoding= "utf-8")
data = f.read()
data2 = f.read()
print(data)
print("-----data2-----%s"%data)

读r

f = open("test","w",encoding= "utf-8")
f.write("北京")
f.write("天安门")

写w

f1 = open("test","a",encoding="utf-8")#追加，只能写
f1.write("lalala")

追加a

f = open ("test","r",encoding="utf-8")
print(f.readline())
print(f.readline())
print(f.readline())#按行读

或
f = open ("test","r",encoding="utf-8")
for i in range(5):
    print(f.readline())#按行读

按行读readline

f = open ("test","r",encoding="utf-8")
print(f.readlines())#每行为一个元素，打印出整个列表
结果：
[‘第一句话北京天安门lalala\n‘, ‘第二句呼啦啦哗啦啦\n‘, ‘第三句规定不到佛‘]

f = open ("test","r",encoding="utf-8")
for i in f.readlines():#打印出每一行的元素，就是打印整个文件
    print(i)

readlines

f = open ("test","r",encoding="utf-8")
for i in f:#一行行的读，读完并释放内存，高效
    print(i)

f = open ("test","r",encoding="utf-8")
for index,line in enumerate(f.readlines()):#将文件转换成列表
    if index == 1:
        print("跳过")
    else:
        print(line)

循环读取

f = open ("test","r",encoding="utf-8")
print(f.readline(),"读到第一行")
print(f.read())#从第二行读取
f.seek(0) #光标移回第一行，可重新开始读
print(f.read())

seek，tell按字符结束

其他方法
encoding
f = open ("test","r",encoding="utf-8")
print(f.encoding)#打印文件的编码

fileno
f = open ("test","r",encoding="utf-8")
print(f.fileno())#文件句柄在操作系统的编号

f = open ("test","r",encoding="utf-8")
print(f.isatty())#判断是不是终端设备

f = open("test","r+",encoding="utf-8")#读和追加模式
print(f.readline())
f.write("\n******")
print(f.readline())

r+

f = open("test","w+",encoding="utf-8")#写读，先创建文件
f.write("******\n")
f.write("******\n")
f.write("******\n")
f.write("******\n")
print(f.readline())
print(f.tell())
f.write("1******")
print(f.readline())

w+

f = open("test","rb")#以二进制去读，不要添加,encoding="utf-8"
print(f.readline())

rb

f = open("test","wb")#以二进制去读，不要添加,encoding="utf-8"
f.write("噜啦噜啦啦欧拉".encode())

wb

文件替换

#with
with open("test","r",encoding="utf-8") as f:
    print(f.readline())
    for line in f:
        print(line.strip())

with

#打开多个文件with open("test","r",encoding="utf-8") as f,\    open("test","r",encoding="utf-8"):