python 字符串(字符序列)和字节序列

>>> '你好'.encode("unicode_escape").decode()
'\\u4f60\\u597d'
>>>
>>> '\u4f60\u597d'
'你好'

>>> "你好".encode("utf-8")
b'\xe4\xbd\xa0\xe5\xa5\xbd'

>>> b
b'\xe4\xbd\xa0\xe5\xa5\xbd'
>>> b.decode("utf")
'你好'

# 安装chardet
pip install chardet

# 导入charet
>>> import chardet
>>> chardet.detect(b)

>>> b_2.decode("utf-8", errors='ignore')
'你好'

>>> b_2.decode("utf-8", errors='replace')
'你好��'

通过dir("")可以查看当前字符串的操作方法

>>> a = "a"
>>> id(a)
22951584
>>> a = a + "b"
>>> id(a)
60513280
>>> a
'ab'

a += "b"  就是 a = a + "b" 省略写法 

>>> a = "hello, world"
>>> a[1]
'e'

>>> a.find("e")
1
>>> a.find("!")
-1

# 找不到目标字符时, index会报错
>>> a.index("!")
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
ValueError: substring not found

>>> f = "2020-11-22-xxxxx"
>>> f.startswith("2020-11-22")
True
>>> f = "xxxxx.jpg"
>>> f.endswith("jpg")
True

a.replace("wer", "wor")

>>> a = "<<python>>, <<java>>, <<c++>>"
>>> a.split(",")
['<<python>>', ' <<java>>', ' <<c++>>']

>>> b
['<<python>>', ' <<java>>', ' <<c++>>']
>>> ",".join(b)
'<<python>>, <<java>>, <<c++>>'

>>> a
'          hello, world          '
>>> a.strip()
'hello, world'
>>>

# open函数打开一个文件, 没有文件会新建, 但是路劲不对会报错
# 指定文件名, 方法(读, 写, 追加), 编码格式
output = open("output.txt", "w", encoding="utf-8")
content = "hello, world"
# 正式写入文件
output.write(content)
# 关闭文件句柄
output.close()

input = open("output.txt", "r", encoding="utf-8")
# 获取文件中的内容
content = input.read()
print(content)

# 暂时理解为只能读取一遍
content_2 = input.read()
print(content_2)

output = open("output.txt", "a", encoding="utf-8")
content = "\nhello, world"
# 正式写入文件
output.write(content)
# 关闭文件句柄
output.close()

a = "ping"
b = "pong"

"play pingpong: {}, {}".format(a, b)

a = "ping"
b = "pong"

"play pingpong: {0}, {1}, {0}, {1}".format(a, b)

a = "ping"
b = "pong"

print("play pingpong: {a}, {b}, {a}, {b}".format(a='ping', b='pong'))

a = "ping"
b = "pong"

print(f"playing pingpong: {a}, {b}")

>>> "{:.2f}".format(3.14159)
'3.14'
>>>

>>> "playing %s %s" % ("ping", "pong")
'playing ping pong'