Python3中的re模块

re是python3中的一个内置模块，用于处理python的正则表达式相关的内容。

Python3代码例子

import re 

text = "sdfreer  [e-mail]  rerersdfer 3435343434"

result = re.findall(r"\w+@\w+\.\w+", text, re.ASCII)
print(result)

# findall() 是固定的文本
result1 = re.findall(r"\d{10}", text)  # 里面的数字10得根据
print(result1)

结果如下：

['[e-mail]']
['3435343434']

---

通过一个例子来做正则表达式

import re 

email = input("邮箱: ")

isValid = re.match(r"^\w+@\w+\.\w+$", email)
if isValid:
    print("格式合法")
else:
    print("格式错误")

---

正则表达式里的相关库

# 固定文本

import re 

text = "aaa aaab  aaaaac"

dataLst = re.findall(r"aaaa", text)

print(dataLst)

# 结果
['aaaa']

# 含特定字符

import re 

text = "aaa aaab  aaaaac"

dataLst = re.findall(r"aa[ab]", text)

print(dataLst)

# 结果
['aaa', 'aaa', 'aaa']

import re 

text = "aaa aaab  aaaaac"

dataLst = re.findall(r"aa[a-z]", text)

print(dataLst)

# 输出
['aaa', 'aaa', 'aaa', 'aac']

import re 

text = "aaa1 aaab2  aaa4c"

dataLst = re.findall(r"aa[0-9]", text)

print(dataLst)

# 输出
['aa1', 'aa4']

import re 

text = "aaa55651 aaab23434  aaa434343ererec"

dataLst = re.findall(r"a\d{3}", text)

print(dataLst)

# 输出
['a556', 'a434']

# 动态的提取

import re 

text = "aaa55651 aaab23434  aaa434343ererec"

dataLst = re.findall(r"a\d{3,}", text)

print(dataLst)

# 输出
['a55651', 'a434343']

import re 

text = "aaa55651 aaab23434  aaa434343ererec"

dataLst = re.findall(r"a\d{3,5}", text)

print(dataLst)

# 输出
['a55651', 'a43434']

import re 

text = "a55651 ab23434  a434343ererec"

# ？代表 0个或1个
dataLst = re.findall(r"a\d?", text)

print(dataLst)

# 输出
['a5', 'a', 'a4']

import re 

text = "a55651 ab23434  a434343ererec"

# + 代表 1个或n个
dataLst = re.findall(r"a\d+", text)

print(dataLst)

# 输出
['a55651', 'a434343']

import re 

text = "a55651 ab23434  a434343ererec"

# * 代表 0个或n个
dataLst = re.findall(r"a\d*", text)

print(dataLst)

# 输出
['a55651', 'a', 'a434343']

import re 

text = "a55651 ab23434  a434343ererec中"

# \w  代表 字母，数字，下划线
dataLst = re.findall(r"a\w*", text)

print(dataLst)

# 输出
['a55651', 'ab23434', 'a434343ererec中']

import re 

text = "a55651 ab23434  a43ererec中"

# .  代表除换行以外任意字符
dataLst = re.findall(r".{2}", text)

print(dataLst)

# 提取字符串中的数字

import re 

text = "身份证号222333199911009988, 其他人身份证号22255519991100998X"

res1 = re.findall('(\d{6}(\d{4})\d{7}[\dX])', text)
print(res1)

res2 = re.findall('\d{6}(\d{4})\d{7}[\dX]', text)
print(res2)

# 输出结果
[('222333199911009988', '1999'), ('22255519991100998X', '1999')]
['1999', '1999']

---

给个赞呗~