python实用操作

将两个字段内容合并成一个字典

>>> a = ["id", "name", "score"]
>>> b = [[1, "name_1", "socre_1"],[2, "name_2", "socre_2"]]
>>> c = []
>>> for record in b:
    c.append(dict(zip(a, record)))
>>> c
[{'name': 'name_1', 'score': 'socre_1', 'id': 1}, 
{'name': 'name_2', 'score': 'socre_2', 'id': 2}]

对列表正序和倒序排序

>>> a = [4,5,3,7,2,9,8,1,0]
>>> a.sort()
>>> a
[0, 1, 2, 3, 4, 5, 7, 8, 9]
>>> a.sort(reverse=True)
>>> a
[9, 8, 7, 5, 4, 3, 2, 1, 0]

>>> b = [4,5,3,7,2,9,8,1,0]
>>> print(sorted(b))
[0, 1, 2, 3, 4, 5, 7, 8, 9]
>>> b
[4, 5, 3, 7, 2, 9, 8, 1, 0]
>>> print(sorted(b, reverse=True))
[9, 8, 7, 5, 4, 3, 2, 1, 0]
>>> b
[4, 5, 3, 7, 2, 9, 8, 1, 0]

lambda表达式对元素为字典的列表排序

>>> a = [{"name":"name_01", "age":12},{"name":"name_02", "age":10},{"name":"name_03", "age":15}]
>>> a.sort(key=lambda x:x["age"])
>>> a
[{'name': 'name_02', 'age': 10}, {'name': 'name_01', 'age': 12}, {'name': 'name_03', 'age': 15}]

字典与与json字符串转换

>>> d = {"a":1, "b":2, "c":3}
>>> import json
>>> json_str = json.dumps(d)  # dict-》json
>>> print(json_str, type(json_str))
{"b": 2, "a": 1, "c": 3} <class 'str'>
>>> a = json.loads(json_str)
>>> print(a, type(a))
{'b': 2, 'a': 1, 'c': 3} <class 'dict'>

正则表达式

match用于匹配，search用于搜索

>>> re.match("hello", "ahello") #匹配不到
>>> re.match(".*hello", "ahello") #可以匹配到
<_sre.SRE_Match object; span=(0, 6), match='ahello'>
>>> re.search("hello", "ahello") #可以搜索到
<_sre.SRE_Match object; span=(1, 6), match='hello'>

用正则表达式查找字符串中所有email，所有email域名是.com或.net,不区分大小写

>>> ls = "邮箱是123@163.com,还是xyz@122.com,或者是abc@qq.com"
>>> prefix = "[0-9a-zA-Z]+@[0-9a-zA-Z]+\."
>>> lt = re.findall(prefix+"com|"+prefix+"net", ls, re.I) #re.I为不区分大小写
>>> lt
['123@163.com', 'xyz@122.com', 'abc@qq.com']

提取url

>>> ls = "<a href='https://www.baidu.com'>a1</a> <a href='https://www.google.com'>a2</a>"
>>> lt = re.findall(r"[a-z]+\:\/\/[a-z]+\.[a-z]+\.[a-z]+", ls, re.I)
>>> for url in lt:
    print(url)
https://www.baidu.com
https://www.google.com

copy和deepcopy
copy：只复制深层对象的引用
deepcopy：复制深层对象本身

>>> import copy
>>> a = [1,2,3,4,['a','b']]
>>> c = copy.copy(a) # 浅拷贝
>>> d = copy.deepcopy(a) # 深拷贝
>>> a.append(5)
>>> c
[1, 2, 3, 4, ['a', 'b']]
>>> d
[1, 2, 3, 4, ['a', 'b']]
>>> a
[1, 2, 3, 4, ['a', 'b'], 5]

>>> a[4].append('c')
>>> a
[1, 2, 3, 4, ['a', 'b', 'c'], 5]
>>> c
[1, 2, 3, 4, ['a', 'b', 'c']]
>>> d
[1, 2, 3, 4, ['a', 'b']]

soup获取所有指定标签的内容

from bs4 import BeautifulSoup
import requests

r = requests.get("http://www.baidu.com")
r.encoding = r.apparent_encoding
soup = BeautifulSoup(r.text, "html.parser")
print(soup.prettify())

lt = []
for a in soup.find_all('a'):
    lt.append(a)

print(lt)

datetime计算日期

>>> import datetime
>>> a = datetime.date(1990, 1, 3)
>>> delta = datetime.timedelta(30)
>>> b = a + delta
>>> b
datetime.date(1990, 2, 2)