python7

import re #导入正则

string = “taoyunjiaoyu”
pat = “yun”
result = re.search(pat,string)
print(result)
‘’’
<re.Match object; span=(3, 6), match=‘yun’>
match 就是正则提取的结果
‘’’

‘’’
1.普通字符作为原子
2.通用字符作为原子
3.原子表
4.非打印字符作为原子
‘’’

#非打印字符作为原子

\n 换行符 \t 制表符

string = ‘’‘taoyunjiaoyu
baidu
‘’’
pat = “\n”
result1 = re.search(pat,string)
print(result1)
‘’’
<re.Match object; span=(12, 13), match=’\n’>
match 就是正则提取的结果
‘’’

#通用字符作为原子
‘’’
\w 字母、数字、下划线 的任意字符
\W 除 字母、数字、下划线 以外的任意字符
\d 十进制数字
\D 除 十进制数字 以外的任意字符
\s 空白字符
\S 除 空白字符 以外的任意字符
‘’’
string = “dscsaxa123xsacx”
pat = “\d\d”
result2 = re.search(pat,string)
print(result2)
‘’’
<re.Match object; span=(7, 9), match=‘12’>
‘’’

string = “dscsaxa123xsacx”
pat = “\d\d\d”
result3 = re.search(pat,string)
print(result3)
‘’’
<re.Match object; span=(7, 10), match=‘123’>
‘’’

string = “dscsaxa123xsacx”
pat = “\d\d\d\w”
result4 = re.search(pat,string)
print(result4)
‘’’
<re.Match object; span=(7, 11), match=‘123x’>
‘’’

string = “dscsaxa123xsacx”
pat = “\d\d\d\d\d\w”
result5 = re.search(pat,string)
print(result5)
‘’’
没有这种格式的，就是None
None
‘’’

#原子表 从这个表任意提取 一个 原子出来
string = “taoyunjiaoyu”
pat = “tao[xyz]un”
result6 = re.search(pat,string)
print(result6)
‘’’
<re.Match object; span=(0, 6), match=‘taoyun’>
‘’’

string = “taoyunjiaoyu”
pat = “tao[^xyz]un” # [^xyz] 除了xyz以外任何字符 ^在原子表里 : 非的意思
result6 = re.search(pat,string)
print(result6)