python基础高级用法

1.ChainMap

• 当我们有2个字段o1和o2 你想将它们从合并后进行查找操作(比如先从o1找，如果o1找不到，再去o2找)，如下：

from collections import ChainMap

o1 = {"a": 1, "c": 10}
o2 = {"b": 5, "c": 4}
o3 = ChainMap(o1, o2)
print(o3) # ChainMap({'a': 1, 'c': 10}, {'b': 5, 'c': 4})

print(o3["a"])
print(o3["b"])
print(o3["c"])
# 如果查寻一个不存在的key通过[]会报错，我们可以通过get方式更缓和一点
print(o3.get("d")) # None

• 当然o3也具备字典的特性，我们通过删除，更新，添加操作总是优先影响第一个字典

# 更新
o3["c"] = 100
print(o3)# ChainMap({'a': 1, 'c': 100}, {'b': 5, 'c': 4})
print(o1) # {'a': 1, 'c': 100}
# 删除
del o3["c"]
print(o3)# ChainMap({'a': 1}, {'b': 5, 'c': 4})
# 新增
o3["d"] = 20
print(o3)# ChainMap({'a': 1, 'd': 20}, {'b': 5, 'c': 4})

• 作为范围变量用法

values = ChainMap()
values["x"] = 1
# 新建一个空的映射对象
values = values.new_child()
values["x"] = 2
values = values.new_child()
values["x"] = 3

print(values) # ChainMap({'x': 3}, {'x': 2}, {'x': 1})
print(values["x"]) # 3

# 类似列表中取 [1:]切片
values = values.parents
print(values)# ChainMap({'x': 2}, {'x': 1})
print(values["x"])# 2
values = values.parents
print(values["x"]) # 1

2.字符串开口结尾匹配

• 一般我们匹配字符串以开头或结尾用的方法是:startswith,endswith.
• 匹配是否存在

lst = ["hello.py", "world.py", "think.py"]
lst2 = ["jsp.jar", "hello.vue", "foo.c"]
print(any(name.endswith(".py") for name in lst2)) # False
print(any(name.endswith(".py") for name in lst2)) # True

• 匹配多个字符串开头

from urllib.request import urlopen
def read_data(name):
    if name.startswith(("http", "https", "tcp")):
        return urlopen(name).read()
    else:
        with open(name) as f:
            return f.read()

• 示例2

filename_list = ["a.png", "b.mp4", "c.txt", "d.pdf"]
if any(name.endswith(("png","jpg","jpeg")) for name in filename_list):
    print("存在图片")

3.通配符匹配字符串

• fnmatch 模块提供了两个函数—— fnmatch() 和 fnmatchcase() ，可以用来实现这样的匹配

from fnmatch import fnmatch, fnmatchcase

print(fnmatch("1.txt", "*.txt"))# True
print(fnmatch("Day23.csv", "Day[0-9]*"))# True
print(fnmatch("hello.txt", "??llo.txt"))# True

file = ["Day21.txt","Day22.Txt", "uwsgi.ini"]
print([name for name in file if fnmatch(name,"Day*.txt")])# ['Day21.txt', 'Day22.txt']

# 完全匹配，对大小写也进行验证
print(fnmatchcase("tell.txt","*.TxT"))# False

4.字符串的替换

• findall找到所有符合要求数据

text = 'UPPER PYTHON, lower python, Mixed Python'
result = re.findall("python", text, flags=re.IGNORECASE)
print(result)# ['PYTHON', 'python', 'Python']

• sub替换字符串

result2 = re.sub('python', 'snake', text, flags=re.IGNORECASE)
print(result2)# UPPER snake, lower snake, Mixed snake

• 替换字符串并不会自动跟被匹配字符串大小写保持一致，为了大小写保持一致可以通过辅助函数修复。

def matchcase(word):
    def replace(m):
        text = m.group()
        if text.isupper():
            return word.upper()
        elif text.islower():
            return word.lower()
        elif text[0].isupper():
            return word.capitalize()
        else:
            return word
    return replace
result3 = re.sub("python", matchcase("snake"), text, flags=re.IGNORECASE)
print(result3)# UPPER SNAKE, lower snake, Mixed Snake

5.多行字符串匹配

text1 = '''/* this is a
good man */
'''
comment = re.compile(r'/\*((?:.|\n)*?)\*/')
print(comment.findall(text1))# [' this is a\ngood man ']

6.扁平数据结构转树形接口

lst = [
    {"id": 1, "name": "dep1", "pid": 0},
    {"id": 2, "name": "dep2", "pid": 1},
    {"id": 3, "name": "dep3", "pid": 1},
    {"id": 4, "name": "dep4", "pid": 2},
    {"id": 5, "name": "dep5", "pid": 4},
]

def list_to_tree(lst):
    result = list()
    mapper = {}
    for item in lst:
        id = item["id"]
        pid = item["pid"]
        name = item["name"]
        if not mapper.get("id"):
            mapper[id] = {
                "children": []
            }
        mapper[id] = {
            "id": id,
            "pid": pid,
            "name": name,
            "children": mapper[id]["children"]
        }
        tree_item = mapper[id]
        if (pid == 0):
            result.append(tree_item)
        else:
            if not mapper.get(pid):
                mapper[pid] = {
                    "children": []
                }
            mapper[pid]["children"].append(tree_item)

    return result

res = list_to_tree(lst)
print(res)

7.字符串对

• 字符串对齐,除了使用 ljust() , rjust() 和 center() 方法外，还可以使用>, <, ^进行填充。

>>> format(text, '>20')
'         Hello World'
>>> format(text, '<20')
'Hello World         '
>>> format(text, '^20')
'    Hello World     '
# 如果使用非空格填充可以使用
>>> format(text, '=>20s')
'=========Hello World'
>>> format(text, '*^20s')
'****Hello World*****'