Python数据分析中正则表达式匹配字符串与常用函数示例详解

re.match(参数1,参数2)

import re

messaga = '张三、李四、王五、赵六、张三'
result = re.match('张三', messaga)
print(result)

result1 = re.match('李四', messaga)
print(result1)

re.search(参数1，参数2)

messaga1 = '张三、李四、王五、赵六、王五'
result2 = re.search('王五', messaga1)
print(result2)

re.findall(参数1,参数2)

import re

messaga1 = '张三、李四、王五、赵六、王五'
result3 = re.findall('王五', messaga1)
print(result3)

运行结果：
['王五','王五']

import re

message = 'Pythonnnnncc93,c87,Javac63,C++88'
result_1 = re.search('[cn]', message)  # 只返回第一个匹配成功的信息
result_2 = re.findall('[0-9]', message)
result_3 = re.findall('[cn]*[0-9]', message)
print(result_1)
print(result_2)
print(result_3)

import re

message1 = 'da2a7ddbre77yifed777t3fefd777b'
result = re.findall('[a-z]*[0-9][a-z]', message1)
print(result)

import re

text = "Hello, World! 123 @#$"
clean = re.sub(r"\W", " ", text)  # \W = 非单词字符
print(clean)  # "Hello  World  123   "

text = "<div>Hello</div><div>World</div>"

# 贪婪：匹配整个字符串
print(re.search(r"<div>.*</div>", text).group())
# 输出：<div>Hello</div><div>World</div>

# 非贪婪：只匹配第一个标签
print(re.search(r"<div>.*?</div>", text).group())
# 输出：<div>Hello</div>

re.findall(r"jpg|png|gif", "image1.jpg, image2.png, icon.gif")
# 输出：['jpg', 'png', 'gif']

date_str = "2025-04-05"
match = re.search(r"(\d{4})-(\d{2})-(\d{2})", date_str)
print(match.groups())      # ('2025', '04', '05')
print(match.group(1))      # '2025'（年）

import re

text = "Call me at 138****5678"
cleaned = re.sub(r"\d{3}\*\*\*\d{4}", "[PHONE_HIDDEN]", text)
print(cleaned)  # Call me at [PHONE_HIDDEN]

import re

text = "John Doe"
swapped = re.sub(r"(\w+) (\w+)", r"\2, \1", text)
print(swapped)  # Doe, John

phone_pattern = re.compile(r"1[3-9]\d{9}")

# 后续可直接调用
if phone_pattern.search(text1):
    ...
if phone_pattern.findall(text2):
    ...

import re

log_info = "用户ID:10086,订单号:ORD20260122001,支付金额:99.9元;用户ID:10087,订单号:ORD20260122002,支付金额:199.5元;用户ID:10088,订单号:ORD20260122003,支付金额:0.88元"

pattern1 = re.compile(':(\d+),')
print(pattern1.findall(log_info))

pattern2 = re.compile('ORD\d+')  # 贪婪模式
print(pattern2.findall(log_info))

pattern3 = re.compile('ORD2026012200\d+?')  # 非贪婪模式
print(pattern3.findall(log_info))

pattern4 = re.compile(':(\d+.\d+)元')
print(pattern4.findall(log_info))