一文介绍Python中的正则表达式用法

import re
pattern = r"abc"  # 匹配字符串 "abc"
string = "xyz abc def"
result = re.findall(pattern, string)
print(result)  # Output: ['abc']

import re
pattern = r"[0-9]"  # 匹配任意数字字符
string = "abc 123 def"
result = re.findall(pattern, string)
print(result)  # Output: ['1', '2', '3']

import re
pattern = r"a+"  # 匹配一个或多个连续的字符 "a"
string = "aaaabbb"
result = re.findall(pattern, string)
print(result)  # Output: ['aaaa']

import re
pattern = r"\bhello\b"  # 匹配整个单词 "hello"
string = "hello world"
result = re.findall(pattern, string)
print(result)  # Output: ['hello']

import re

import re
pattern = r"hello"
string = "hello world"
result = re.match(pattern, string)
if result:
    print("Match found!")
else:
    print("No match")

import re
pattern = r"world"
string = "hello world"
result = re.search(pattern, string)
if result:
    print("Match found!")
else:
    print("No match")

import re
pattern = r"\d+"
string = "I have 10 apples and 20 oranges."
result = re.findall(pattern, string)
print(result)  # Output: ['10', '20']

import re
pattern = r"apple"
string = "I have an apple."
result = re.sub(pattern, "banana", string)
print(result)  # Output: "I have an banana."

import re
pattern = r"(\d+)-(\d+)-(\d+)"  # 匹配日期格式 "YYYY-MM-DD"
string = "Today is 2023-06-28."
result = re.search(pattern, string)
if result:
    year = result.group(1)
    month = result.group(2)
    day = result.group(3)
    print(f"Year: {year}, Month: {month}, Day: {day}")
else:
    print("No match")

import re
pattern = r"a+?"
string = "aaaaa"
result = re.findall(pattern, string)
print(result)  # Output: ['a', 'a', 'a', 'a', 'a']

import re
pattern = r"(?<=@)\w+"  # 匹配邮箱地址中的用户名
string = "john@example.com"
result = re.findall(pattern, string)
print(result)  # Output: ['example']

import re
pattern = r"(\w+)\s+\1"  # 匹配重复的单词
string = "hello hello world world"
result = re.findall(pattern, string)
print(result)  # Output: ['hello', 'world']

import re
pattern = r"\d+(?= dollars)"  # 匹配 "dollars" 前面的数字
string = "I have 100 dollars."
result = re.findall(pattern, string)
print(result)  # Output: ['100']

import re
pattern = r"^\w+@\w+\.\w+$"  # 匹配邮箱地址
email = "test@example.com"
result = re.match(pattern, email)
if result:
    print("Valid email address")
else:
    print("Invalid email address")

import re
pattern = r"http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+"
text = "Visit my website at https://example.com. You can also check out https://example.org."
result = re.findall(pattern, text)
print(result)  # Output: ['https://example.com', 'https://example.org']

import re
pattern = r"<([^>]+)>"  # 匹配HTML标签
html = "<h1>Hello</h1><p>World</p>"
result = re.findall(pattern, html)
print(result)  # Output: ['h1', '/h1', 'p', '/p']

import re
sensitive_words = ["bad", "evil", "dangerous"]
text = "This is a bad example."
for word in sensitive_words:
    pattern = fr"\b{re.escape(word)}\b"  # 匹配敏感词并确保单词边界
    text = re.sub(pattern, "***", text)
print(text)  # Output: "This is a *** example."