import re
print(re.findall('alex','hahahah alex is alex is dsb'))
alex
print(re.findall('\w','Aah123 +-_')) 匹配字母数字下划线
\w
print(re.findall('\w\w','Aah123 +-_'))
\w\w
['Aa','h1','23',]
print(re.findall('\w9\w','Aa9h123 aaa9c+-_'))
\w9\w
['a9h','a9c']
print(re.findall('\W','Aah123 +-_')) 匹配非字母数字下划线
print(re.findall('\s','Aah\t12\n3 +-_')) 匹配任意空白字符
print(re.findall('\S','Aah\t12\n3 +-_')) 匹配任意非空字符
print(re.findall('\d','Aah\t12\n3 +-_')) 匹配任意数字
print(re.findall('\D','Aah\t12\n3 +-_')) 匹配任意非数字
print(re.findall('\w\w\d\d','asfdasdfegon001adfadfegon002asdfxx01 yy02'))
print(re.findall('\s','Aah\t12\n3 +-_')) 只匹配＼ｓ
print(re.findall('\t','Aah\t12\n3 +-_')) 只匹配＼ｔ
print(re.findall('\n','Aah\t12\n3 +-_')) 只匹配＼ｎ
^: 仅从头开始匹配
print(re.findall('^alex',' alex is alex is alex'))
^alex
$: 仅从尾部开始匹配
print(re.findall('alex$',' alex is alex is alex1'))
alex$
.: 代表匹配一个字符,该字符可以是除换行符之外任意字符
print(re.findall('a.c','a a1c aaac a c asfdsaf a\nc',re.DOTALL))
a.c
['a1c','aac','a c','a\nc']
[]:代表匹配一个字符,这一个字符是来自于我们自定义的范围
print(re.findall('a[0-9]c','a,c a a1c a9c aaac a c asfdsaf a\nc',re.DOTALL))
print(re.findall('a[a-zA-Z]c','a,c aAc a1c a9c aaac a c asfdsaf a\nc',re.DOTALL))
print(re.findall('a[a-zA-Z]c','a,c aAc a1c a9c aaac a c asfdsaf a\nc',re.DOTALL))
print(re.findall('a[+*/-]c','a,c a+c a-c a*c a/c aAc a1c a9c aaac a c asfdsaf a\nc',re.DOTALL))
print(re.findall('a[+*\-/]c','a,c a+c a-c a*c a/c aAc a1c a9c aaac a c asfdsaf a\nc',re.DOTALL))
print(re.findall('a[^0-9]c','a,c a a1c a9c aaac a c asfdsaf a\nc',re.DOTALL))
重复匹配
?:代表左边那一个字符出现0次到1次
print(re.findall('ab?','a ab abb abbbb a123b a123bbbb'))
ab?
['a','ab','ab','ab','a','a']
*: 代表左边那一个字符出现0次到无穷次
print(re.findall('ab*','a ab abb abbbb a123b a123bbbb'))
ab*
['a','ab','abb','abbbb','a','a']
+: 代表左边那一个字符出现1次到无穷次
print(re.findall('ab+','a ab abb abbbb a123b a123bbbb'))
ab+
['ab','abb','abbbb']
{n,m}:代表左边那一个字符出现n次到m次
print(re.findall('ab{1,3}','a ab abb abbbb a123b a123bbbb'))
['ab', 'abb', 'abbb']
print(re.findall('ab{1,}','a ab abb abbbb a123b a123bbbb'))
print(re.findall('ab+','a ab abb abbbb a123b a123bbbb'))
print(re.findall('ab{0,}','a ab abb abbbb a123b a123bbbb'))
print(re.findall('ab*','a ab abb abbbb a123b a123bbbb'))
print(re.findall('ab{3}','a ab abb abbbb a123b a123bbbb'))
.*: 匹配任意0个到无穷个字符,贪婪匹配
print(re.findall('a.*c','a123213123asdfasdfc123123123123+-0)((c123123'))
a.*c
.*?:匹配任意0个到无穷个字符,非贪婪匹配
print(re.findall('a.*?c','a123213123asdfasdfc123123123123+-0)((c123123'))
|:或者
print(re.findall('companies|company','Too many companies have gone bankrupt,c and the next one is my company'))
companies|company
():分组 默认只取组内内容
print(re.findall('compan(?:ies|y)','Too many companies have gone bankrupt,c and the next one is my company'))
compan(ies|y)
print(re.findall('href="(.*?)"','<p>动感视频</p><a href="https://www.douniwan.com/1.mp4">逗你玩呢</a><a href="https://www.xxx.com/2.mp4">葫芦娃</a>'))
href=".*?"
？：取消组内
'a\\c'
print(re.findall('a\\\\c','a\c aac'))
print(re.findall(r'a\\c','a\c aac'))
print(re.findall('alex','my name is alex Alex is dsb aLex ALeX',re.I))
忽略大小写 ｒｅ．Ｉ
print(re.findall('alex','my name is alex Alex is dsb aLex ALeX',re.I))
msg="""
my name is egon
asdfsadfadfsadf egon
123123123123123egon
"""
ｒｅ．Ｍ ：以＼ｎ为分隔符 为一行内容
print(re.findall('egon$',msg,re.M)) #my name is egon\nasdfsadfadfsadf egon\n123123123123123egon'
re模块其他方法
res=re.findall('(href)="(.*?)"','<p>动感视频</p><a href="https://www.douniwan.com/1.mp4">逗你玩呢</a><a href="https://www.xxx.com/2.mp4">葫芦娃</a>')
print(res)
ｒｅ．ｓｅａｒｃｈ：只匹配成功的一次，没有则返回Ｎｏｎｅ，匹配第一个内容，以及内容的索引位置
res=re.search('(href)="(.*?)"','<p>动感视频</p><a href="https://www.douniwan.com/1.mp4">逗你玩呢</a><a href="https://www.xxx.com/2.mp4">葫芦娃</a>')
print(res)
print(res.group(0)) 默认只取第一个分组
print(res.group(1)) 只取第一个分组
print(res.group(2)) 只取第二个分组
res=re.match('abc','123abc') ## res=re.search('^abc','123abc') 默认从头开始找，找到就结束．
print(res)
print(re.findall('alex','alex is alex is alex'))
print(re.search('alex','alex is alex is alex'))
print(re.match('alex','alex is alex is alex'))
pattern=re.compile('alex') ｃｏｍｉｌｅ：公用表达式
print(pattern.findall('alex is alex is alex'))
print(pattern.search('alex is alex is alex'))
print(pattern.match('alex is alex is alex'))
['1', '2', '60', '-40.35', '5', '-4', '3']
msg="1-2*(60+(-40.35/5)-(-40*3))"
print(re.findall('\D?(-?\d+\.?\d*)',msg))
msg="1-2*(60+(-40.35/5)-(-40*3))"
\D?-?\d+\.?\d*
hashlib模块
'''
1. 什么是hash
hash是一种算法,该算法接受一系列的数据,经过运算会得到一个hash值,
hash值具备三大特性:
1. 只要传入的内容一样,那么得到的hash值一定是一样
2. 只要采用hash算法固定,无论传入的内容多大,hash值的长度是固定
3. hash值不可逆,即不能通过hash值逆推出内容
2. 为何要用hash
特性1+2=>文件完整性校验
特性3==>加密
'''
特性１：
import hashlib
m=hashlib.md5()
m.update('你好'.encode('utf-8'))
m.update('hello'.encode('utf-8'))
print(m.hexdigest()) #65c83c71cb3b2e2882f99358430679c3
特性２：
m1=hashlib.md5()
m1.update('你好hello'.encode('utf-8'))
print(m1.hexdigest()) #65c83c71cb3b2e2882f99358430679c3
print(len(m1.hexdigest())) #32
特性３：
m2=hashlib.sha512()
m2.update(b'asdfassssssssssssssssssssssssssss')
print(m2.hexdigest())
print(len(m2.hexdigest()))
with open(r'D:\脱产5期内容\day17\今日内容',mode='rb') as f:
m=hashlib.md5()
for line in f:
m.update(line)
print(m.hexdigest())
pwd=input('password>>> ').strip()
m=hashlib.md5()
m.update('天王盖地虎'.encode('utf-8'))
m.update(pwd.encode('utf-8'))
m.update('一行白鹭上青天'.encode('utf-8'))
print(m.hexdigest())