【第五篇】Python数据类型--str&bytes

 1 #!/usr/bin/env python3
 2 # -*-coding:utf-8-*-
 3 
 4 """
 5 @author:fyh
 6 @time:2019/5/31
 7 """
 8 
 9 str1 = "hello python"
10 
11 for c in str1:
12     print(c, end='\t')
13     
14 # 运行结果：h    e    l    l    o         p    y    t    h    o    n

 1 #!/usr/bin/env python3
 2 # -*-coding:utf-8-*-
 3 
 4 """
 5 @author:fyh
 6 @time:2019/5/31
 7 """
 8 
 9 # 1   * 重复输出字符串
10 print('hello' * 2)
11 
12 # 2 [] ,[:] 通过索引获取字符串中字符
13 print('helloworld'[2:])
14 
15 # 3 in  成员运算符 - 如果字符串中包含给定的字符返回 True
16 print('el' in 'hello')
17 
18 # 4 %   格式字符串
19 print('alex is a good teacher')
20 print('%s is a good teacher' % 'alex')
21 
22 # 5 +   字符串拼接
23 a = '123'
24 b = 'abc'
25 c = '789'
26 d1 = a + b + c
27 print(d1)  # +效率低,该用join
28 
29 # join效率高
30 d2 = ''.join([a, b, c])
31 print(d2)

 1 #!/usr/bin/env python3
 2 # -*-coding:utf-8-*-
 3 
 4 """
 5 @author:fyh
 6 @time:2019/5/31
 7 """
 8 
 9 name = "hello world"
10 # 小写字母变为大写
11 print(name.upper())    # HELLO WORLD
12 print(name)            # hello world
13 
14 # 把大写字母变小写
15 name2 = "HELLO WORLD"
16 print(name2.lower())    # hello world
17 print(name2)            # HELLO WORLD
18 
19 # 判断是否以。。。开头
20 name3 = "hello"
21 print(name3.startswith("he"))   # True
22 # 检查字符串是否以。。结尾
23 print(name3.endswith("lo"))     # True
24 
25 # replace   替换
26 name4 = "python"
27 print(name4.replace('th', 'aa'))    # pyaaon
28 
29 # 去除空格
30 name5 = "  bbcc  "
31 print(name5.strip())    # bbcc
32 
33 # 分割
34 str1 = "aa|bb|cc|dd"
35 print(str1.split('|'))  # ['aa', 'bb', 'cc', 'dd']
36 
37 # 查找  返回开始的索引值
38 str2 = "we are family"
39 print(str2.find("are"))     # 3
40 
41 # join  拼接
42 lst1 = ['aa', 'bb', 'cc', 'dd']
43 print("-".join(lst1))       # aa-bb-cc-dd

 1 #!/usr/bin/env python3
 2 # -*-coding:utf-8-*-
 3 
 4 """
 5 @author:fyh
 6 @time:2019/5/31
 7 """
 8 
 9 str1 = "hello world"
10 
11 
12 print(str1[1:6])
13 # 结果是ello
14 
15 print(str1[1:6:2])
16 # 结果是el
17 
18 print(str1[2:])
19 # 结果是llo world
20 # 保留start_index，但省略end_index，这样会从起始索引开始，切到最后一个元素为止
21 
22 print(str1[:5])
23 # 结果是hello
24 # 省略start_index，保留end_index，这样会从第一个元素开始，切到end_index - 1的元素为止
25 
26 print(str1[-1:-6:-1])
27 # 结果是dlrow
28 
29 print(str1[1:6:-1])
30 # 结果为空
31 # 切片时,一定要保证start_index到end_index的方向与步长step的方向同向，否则会切出空的序列

 1 tpl = "i am %s" % "alex"
 2   
 3 tpl = "i am %s age %d" % ("alex", 18)
 4   
 5 tpl = "i am %(name)s age %(age)d" % {"name": "alex", "age": 18}
 6   
 7 tpl = "percent %.2f" % 99.97623
 8   
 9 tpl = "i am %(pp).2f" % {"pp": 123.425556, }
10   
11 tpl = "i am %.2f %%" % 123.425556

 1 tpl = "i am {}, age {}, {}".format("seven", 18, 'alex')
 2    
 3 tpl = "i am {}, age {}, {}".format(*["seven", 18, 'alex'])
 4    
 5 tpl = "i am {0}, age {1}, really {0}".format("seven", 18)
 6    
 7 tpl = "i am {0}, age {1}, really {0}".format(*["seven", 18])
 8    
 9 tpl = "i am {name}, age {age}, really {name}".format(name="seven", age=18)
10    
11 tpl = "i am {name}, age {age}, really {name}".format(**{"name": "seven", "age": 18})
12    
13 tpl = "i am {0[0]}, age {0[1]}, really {0[2]}".format([1, 2, 3], [11, 22, 33])
14    
15 tpl = "i am {:s}, age {:d}, money {:f}".format("seven", 18, 88888.1)
16    
17 tpl = "i am {:s}, age {:d}".format(*["seven", 18])
18    
19 tpl = "i am {name:s}, age {age:d}".format(name="seven", age=18)
20    
21 tpl = "i am {name:s}, age {age:d}".format(**{"name": "seven", "age": 18})
22   
23 tpl = "numbers: {:b},{:o},{:d},{:x},{:X}, {:%}".format(15, 15, 15, 15, 15, 15.87623, 2)
24   
25 tpl = "numbers: {:b},{:o},{:d},{:x},{:X}, {:%}".format(15, 15, 15, 15, 15, 15.87623, 2)
26   
27 tpl = "numbers: {0:b},{0:o},{0:d},{0:x},{0:X}, {0:%}".format(15)
28   
29 tpl = "numbers: {num:b},{num:o},{num:d},{num:x},{num:X}, {num:%}".format(num=15)

>>> s = "中文"
>>> s
'中文'
>>> type(s)
<class 'str'>
>>> b = bytes(s, encoding='utf-8')
>>> b
b'\xe4\xb8\xad\xe6\x96\x87'
>>> type(b)
<class 'bytes'>

 1 #!/usr/bin/env python3
 2 # -*-coding:utf-8-*-
 3 
 4 """
 5 @author:fyh
 6 @time:2019/5/31
 7 """
 8 # gbk编码的bytes
 9 b = bytes('中国', encoding='gbk')
10 print(b)        # b'\xd6\xd0\xb9\xfa'
11 print(type(b))  # <class 'bytes'>
12 
13 str1 = str(b)
14 print(str1)     # b'\xd6\xd0\xb9\xfa'
15 print(type(str1))   # <class 'str'>
16 
17 # 指定编码格式
18 str2 = str(b, encoding='gbk')
19 print(str2)     # 中国
20 print(type(str2))   # <class 'str'>
21 
22 # 再把字符串str2转换为utf8编码格式的bytes类型:
23 b2 = bytes(str2, encoding='utf8')
24 print(b2)       # b'\xe4\xb8\xad\xe5\x9b\xbd'
25 print(type(b2))     # <class 'bytes'>

 1 #!/usr/bin/env python3
 2 # -*-coding:utf-8-*-
 3 
 4 """
 5 @author:fyh
 6 @time:2019/5/31
 7 """
 8 
 9 """
10 其中decode()与encode()方法可以接受参数， 其声明分别为:
11     bytes.decode(encoding="utf-8", errors="strict")
12     str.encode(encoding="utf-8", errors="strict")
13 
14         其中 encoding是指在解码/编码(动词)过程中使用的字符编码(名词)
15         
16         errors是指错误的处理方案,errrors参数默认值是strict(严格的)意味着如果编解码出错将会抛出UnicodeError
17 
18         如果想忽略编解码错误 可以将errors设置为ignore
19 """
20 
21 
22 # 编码 encode
23 str1 = "中国"
24  
25 str1_utf8 = str1.encode(encoding='utf8')
26 print(str1_utf8)        # b'\xe4\xb8\xad\xe5\x9b\xbd'
27 print(type(str1_utf8))  # <class 'bytes'>
28 
29 str1_gbk = str1.encode(encoding="gbk")
30 print(str1_gbk)         # b'\xd6\xd0\xb9\xfa'
31 print(type(str1_gbk))   # <class 'bytes'>
32  
33 
34 # 解码 decode
35 str2 = str1_utf8.decode(encoding="utf8")
36 print(str2)     # 中国
37 print(type(str2))   # <class 'str'>
38 
39 str3 = str1_gbk.decode(encoding="gbk")
40 print(str3)         # 中国
41 print(type(str3))   # <class 'str'>