</h1>
<div class="clear"></div>
<div class="postBody">
一、正则表达式
1.使用正则表达式的动机
1. 文本处理已经成为计算机常见工作之一
2. 对文本内容的搜索，定位，提取是逻辑比较复杂的工作
import re
s = "Levi:1994,Sunny:1993"
pattern = r"(\w+):(\d+)"
# re模块调用
# l = re.findall(pattern, s)
# print(l)
# compile对象调用
regex = re.compile(pattern, flags=0)
l = regex.findall(s, 0, 55 )
print(l)
[('Levi', '1994'), ('Sunny', '1993')]
import re
s = “hello world how are you”
# pattern = r"[^\w]+"
pattern = r"\W+"
l = re.split(pattern, s)
print(l)
import re
s = “时间:2019/10/12”
ns = re.sub(r’/’, ‘-’, s)
print(ns)
时间:2019-10-12
import re
s = “时间:2019/10/12”
ns = re.subn(r’/’, ‘-’, s, 4)
print(ns)
(‘时间:2019-10-12’, 2)
import re
s = ‘2019年，建国70周年’
pattern = r"\d+"
ite = re.finditer(pattern, s)
# 方法1
print(“ite类型”, type(ite))
print(ite.next().group())
print(ite.next().group())
# 方法2
print("=========")
for i in ite:
print(i.group())
ite类型 <class ‘callable_iterator’>
2019
70
import re
m = re.fullmatch(r’\w+’,“hello1973”)
print(m.group())
import re
#验证密码是否符合规范---只含字母和数字 m = re.fullmatch(r'[0-9A-Za-z]+', "hello1973")
print(m.group())
hello1973
import re
m = re.match(r’[A-Z]\w*’,“Hello1973”)
print(m.group())
Hello1973
import re
m = re.search(r’\S+’, “好\n嗨 哟”)
print(m.group())
好
import re
pattern = r"(ab)cd(?P<pig>ef)"
regex = re.compile(pattern)
# 生成match对象
obj = regex.search(“abcdefghi”, pos=0, endpos=7)
# 演示match对象属性变量
print(obj.pos)
print(obj.endpos)
print(obj.re)
print(obj.string)
print(obj.lastgroup)
print(obj.lastindex)
0
7
re.compile(’(ab)cd(?P<pig>ef)’)
abcdefghi
pig
2
import re
pattern = r"(ab)cd(?P<pig>ef)"
regex = re.compile(pattern)
# 生成match对象
obj = regex.search(“abcdefghi”, pos=0, endpos=7)
# 演示match对象方法
print(obj.start())
print(obj.end())
print(obj.span())
print(obj.groupdict())
print(obj.groups())
print(obj.group())#获取整个match对象内容
print(obj.group(1))#获取第一子组内容
print(obj.group(‘pig’))#获取组名为pig的子组内容
0
6
(0, 6)
{‘pig’: ‘ef’}
(‘ab’, ‘ef’)
abcdef
ab
ef
import re
s = “”“hello world
你好，北京
“””
# 只能匹配ASCII码字符
regex = re.compile(r’\w+’, flags=re.A)
l = regex.findall(s)
print(l)
[‘Hello’, ‘world’]
import re
s = “”“Hello world
你好，北京
“””
# 匹配时忽略字母大小写
regex = re.compile(r’[A-Z]+’, flags=re.I)
l = regex.findall(s)
print(l)
[‘Hello’, ‘world’]
import re
s = “”“Hello world
你好，北京
“””
# 匹配时不可以匹配换行
regex = re.compile(r’.+’)
l = regex.findall(s)
print(l)
[‘Hello world’, ‘你好，北京’]
import re
s = “”“Hello world
你好，北京
“””
# 匹配时可以匹配换行
regex = re.compile(r’.+’,flags=re.S)
l = regex.findall(s)
print(l)
[‘Hello world\n你好，北京\n’]
import re
s = “”“Hello world
你好，北京
“””
# 匹配每一行的开头或者结尾
regex = re.compile(r’world$’,flags=re.M)
l = regex.findall(s)
print(l)
[‘world’]
import re
s = “”“Hello world
你好，北京
“””
# 匹配每一行的开头或者结尾
pattern = r"""\w+ # 第一部分
\s+ # 第二部分
\w+ # 第三部分
“”"
regex = re.compile(pattern,flags=re.X)
l = regex.findall(s)
print(l)
[‘Hello world’]
""" 匹配每段ＩＰ地址，要求： 根据输入的每段首单词，获取ＩＰ地址 """
import re
import sys
port = sys.argv[1]
f = open(‘1.txt’)
# 找到ｐｏｒｔ段落
while True:
data = ‘’
for line in f:
if line != ‘\n’: # 不是空行
data += line
else:
break
if not data: # 文件结尾
print(“Not Found the %s”%port)
break
<span style="color: #008000;">#</span><span style="color: #008000;"> 匹配字符串首个单词</span>
key_word = re.match(r<span style="color: #800000;">'</span><span style="color: #800000;">\S+</span><span style="color: #800000;">'</span><span style="color: #000000;">,data).group()
</span><span style="color: #0000ff;">if</span> port ==<span style="color: #000000;"> key_word:
</span><span style="color: #008000;">#</span><span style="color: #008000;"> 匹配目标内容</span>
<span style="color: #008000;">#</span><span style="color: #008000;"> pattern = r"[0-9a-f]{4}\.[0-9a-f]{4}\.[0-9a-f]{4}"</span>
pattern=r<span style="color: #800000;">"</span><span style="color: #800000;">(\d{1,3}\.){3}\d{1,3}/\d+|Unknow</span><span style="color: #800000;">"</span>
<span style="color: #0000ff;">try</span><span style="color: #000000;">:
address </span>=<span style="color: #000000;"> re.search(pattern,data).group()
</span><span style="color: #0000ff;">print</span><span style="color: #000000;">(address)
</span><span style="color: #0000ff;">except</span><span style="color: #000000;">:
</span><span style="color: #0000ff;">print</span>(<span style="color: #800000;">"</span><span style="color: #800000;">No address</span><span style="color: #800000;">"</span><span style="color: #000000;">)
</span><span style="color: #0000ff;">break</span></pre>
<div class="clear"></div>
<div id="post_next_prev">
<a href="https://www.cnblogs.com/yuxiangyang/p/10864161.html" class="p_n_p_prefix">« </a> 上一篇： <a href="https://www.cnblogs.com/yuxiangyang/p/10864161.html" title="发布于 2019-05-14 19:42">python IO网络编程</a>
<br>
<a href="https://www.cnblogs.com/yuxiangyang/p/10885385.html" class="p_n_p_prefix">» </a> 下一篇： <a href="https://www.cnblogs.com/yuxiangyang/p/10885385.html" title="发布于 2019-05-18 12:46">python并发编程基础</a>
