python入门学习笔记----爬虫之正则表达式

re.search()

import re
print(re.search(r'Fishc', 'I love Fishc.com!'))

<re.Match object; span=(7, 12), match='Fishc'>   # 第七到第十二

.find()

print('I love Fishc.com!'.find('Fishc'))

7

'.'可代表任何字符

import re
print(re.search(r'.', 'I love Fishc.com!'))     # 点表示任何字符，所以是第一个字符
print(re.search(r'Fish.', 'I love Fishc.com!'))

print(re.search(r'\.', 'I love Fishc.com!'))

<re.Match object; span=(0, 1), match='I'>
<re.Match object; span=(7, 12), match='Fishc'>
<re.Match object; span=(12, 13), match='.'>

\d匹配数字

import re
print(re.search(r'\d', 'I love 123Fishc.com!'))  # 匹配数字
print(re.search(r'\d\d\d', 'I love 123Fishc.com!'))

<re.Match object; span=(7, 8), match='1'>
<re.Match object; span=(7, 10), match='123'>

import re
print(re.search(r'\d\d\d\.\d\d\d\.\d\d\d\.\d\d\d', '192.168.111.123'))  # 匹配IP地址

<re.Match object; span=(0, 15), match='192.168.111.123'>

import re
print(re.search(r'\d\d\d\.\d\d\d\.\d\d\d\.\d\d\d', '192.168.1.1'))  # 匹配IP地址

None

中括号[]

import re
print(re.search(r'[aeiou]', 'I love Fishc.com!')) 

<re.Match object; span=(3, 4), match='o'>

import re
print(re.search(r'[aeiouAEIOU]', 'I love Fishc.com!'))  

<re.Match object; span=(0, 1), match='I'>

[a-z]

import re
print(re.search(r'[a-z]', 'I love Fishc.com!'))

<re.Match object; span=(2, 3), match='l'>

import re
print(re.search(r'[0-9]', 'I love 123Fishc.com!'))
print(re.search(r'[2-9]', 'I love 123Fishc.com!'))

<re.Match object; span=(7, 8), match='1'>
<re.Match object; span=(8, 9), match='2'>

{}表示次数

import re
print(re.search(r'ab{3}c', 'abbbc'))  # 大括号里面是重复的次数
print(re.search(r'ab{3}c', 'abbbbbc'))
print(re.search(r'ab{3,10}c', 'abbbbbc'))   # 3到10次

<re.Match object; span=(0, 5), match='abbbc'>
None
<re.Match object; span=(0, 7), match='abbbbbc'>

import re
print(re.search(r'[0-255]', '188'))      # 0到2，两个5
print(re.search(r'[0-2][0-5][0-5]', '188'))
print(re.search(r'[01]\d\d|2[0-4]\d|25[0-5]', '188'))  #01x or 24x or 25x

<re.Match object; span=(0, 1), match='1'>
None
<re.Match object; span=(0, 3), match='188'>

匹配IP地址

import re
print(re.search(r'(([01]{0,1}\d{0,1}\d|2[0-4]\d|25[0-5])\.){3}([01]{0,1}\d{0,1}\d|2[0-4]\d|25[0-5])', '192.168.1.1'))  

<re.Match object; span=(0, 11), match='192.168.1.1'>

print(re.search(r"Fish(C|D)", 'FishC'))
print(re.search(r"Fish(C|D)", 'FishD'))
print(re.search(r"Fish(C|D)", 'FishE'))

<re.Match object; span=(0, 5), match='FishC'>
<re.Match object; span=(0, 5), match='FishD'>
None

^ 脱字符 :匹配输入字符串的开始位置

import re
print(re.search(r"^FishC", 'I love FishC.com!'))
print(re.search(r"^FishC", 'FishC.com!'))

None
<re.Match object; span=(0, 5), match='FishC'>

$ :匹配输入字符串的结束位置

import re
print(re.search(r"FishC$", 'I love FishC.com!'))
print(re.search(r"FishC$", 'I love FishC'))

None
<re.Match object; span=(7, 12), match='FishC'>

\

1. 将一个普通字符变成特殊字符，例如\d表示匹配所有的十进制数字
2. 解除原字符的特殊功能，例如.表示匹配点号本身
3. 引用序号对应的子组所匹配的字符串

() 子组

import re
print(re.search(r"(FishC)\1", 'FishC.com!'))
print(re.search(r"(FishC)\1", 'FishCFishC!'))

None
<re.Match object; span=(0, 10), match='FishCFishC'>

import re
print(re.search(r"(FishC)\060", 'FishCFishC0'))

<re.Match object; span=(5, 11), match='FishC0'>

import re
print(re.search(r"(FishC)\141", 'FishCFishCa'))  # 三位数表示八进制

<re.Match object; span=(5, 11), match='FishCa'>

[…] 生成一个字符类

re.findall()

import re
print(re.search(r".", 'FishCFishCa'))
print(re.search(r"\.", 'FishCFishCa'))
print(re.search(r"[.]", 'FishC.com'))
print(re.findall(r"[a-z]", 'FishC.com'))

<re.Match object; span=(0, 1), match='F'>
None
<re.Match object; span=(5, 6), match='.'>
['i', 's', 'h', 'c', 'o', 'm']

import re
print(re.findall(r"[\n]", 'FishC.com\n'))
print(re.findall(r"[^a-z]", 'FishC.com\n'))  # 取反
print(re.findall(r"[a-z^]", 'FishC.com\n'))

['\n']
['F', 'C', '.', '\n']
['i', 's', 'h', 'c', 'o', 'm']

{M,N} 匹配M到N次

{M} 匹配M次

import re
print(re.search(r"FishC{3}", 'FishCCCCCC'))          # 匹配C三次
print(re.search(r"FishC{3,4}", 'FishCCCCCC'))        # 匹配C四次
print(re.search(r"(FishC){3}", 'FishCFishCFishC'))   # 匹配FishC三次
print(re.search(r"(FishC){1,4}", 'FishCFishCFishC')) # 匹配1到4次，这里只有三次

<re.Match object; span=(0, 7), match='FishCCC'>
<re.Match object; span=(0, 8), match='FishCCCC'>
<re.Match object; span=(0, 15), match='FishCFishCFishC'>
<re.Match object; span=(0, 15), match='FishCFishCFishC'>

*

表示匹配前面的子表达式零次或多次。等价于{0，}

+

表示匹配前面的子表达式一次或多次，等价于{1，}

？

表示匹配前面的子表达式一次或1次，等价于{0，1}

{M，N}？ 启用非贪婪模式，即只匹配M此

import re
print(re.search(r"(FishC){1,5}", 'FishCFishCFishC'))
s = ""
print(re.search(r"<.+>", s))  # 贪婪模式
print(re.search(r"<.+?>", s))

<re.Match object; span=(0, 15), match='FishCFishCFishC'>
<re.Match object; span=(0, 44), match=''>
<re.Match object; span=(0, 6), match=''>

注意

正则表达式里面不能随便加空格

python3正则表达式特殊符号及用法

字符	含义
.	表示匹配除了换行符外的任何字符。 注：通过设置re.DOTALL标志可以使.匹配任何字符（包括换行符）
|	A|B表示匹配正则表达式A或者B
^	1.（脱字符撇皮输入字符串的开始位置）；2.如果设置了re.MULTILINE标志，^也匹配换行符之后的位置
$	1.匹配输入字符串的结束位置；2.如果设置了re.MULTILINE标志 ，$也匹配换行符之前的位置