20个Python 正则表达式应用与技巧

import re

text = "The quick brown fox jumps over the lazy dog"

# 使用 re 模块查找匹配项
matches = re.findall(r'\b\w{3}\b', text)

print(matches)  # 输出匹配的单词列表

text = "Contact us at: [email protected], [email protected]"

# 使用分组提取邮件地址
emails = re.findall(r'([a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,})', text)

print(emails)  # 输出提取的邮件地址列表

text = "There are 123 apples and 456 oranges"

# 使用 re.sub() 函数替换文本中的数字为 "X"
new_text = re.sub(r'\d+', 'X', text)

print(new_text)  # 输出替换后的文本

pattern = re.compile(r'\bpython\b', re.IGNORECASE)

text = "Python is a popular programming language"

# 使用编译后的正则表达式进行匹配
match = pattern.search(text)

if match:
    print("Found")
else:
    print("Not found")

text = "The code is 1234 and the password is abcd_123"

# 使用预定义字符类匹配数字和字母密码
codes = re.findall(r'\b\w+\b', text)

print(codes)  # 输出匹配的代码和密码列表

text = "The Python programming language is widely used for data analysis"

# 使用量词匹配至少包含两个字母的单词
words = re.findall(r'\b\w{2,}\b', text)

print(words)  # 输出匹配的单词列表

text = "Python is a great language for both beginners and experts"

# 使用锚点匹配以 Python 开头的句子
sentence = re.findall(r'^Python.*', text)

print(sentence)  # 输出匹配的句子

text = "Python is a powerful programming language"

# 使用贪婪匹配查找 "p" 到 "g" 之间的内容
greedy_match = re.findall(r'p.*g', text)

# 使用非贪婪匹配查找 "p" 到 "g" 之间的内容
non_greedy_match = re.findall(r'p.*?g', text)

print("贪婪匹配:", greedy_match)  # 输出贪婪匹配结果
print("非贪婪匹配:", non_greedy_match)  # 输出非贪婪匹配结果

text = "apple apple orange orange"

# 使用后向引用匹配重复的单词
duplicates = re.findall(r'(\b\w+\b) \1', text)

print("重复的单词:", duplicates)  # 输出匹配到的重复单词列表

text = """Python is a popular programming language.
It is used for web development, data analysis, and more.
Python has a simple syntax and is easy to learn."""

# 使用多行匹配模式匹配以大写字母开头的句子
sentences = re.findall(r'^[A-Z].*$', text, re.MULTILINE)

print("以大写字母开头的句子:", sentences)  # 输出匹配到的句子列表

text = "John has 5 apples, Mary has 3 oranges"

# 使用命名分组提取人名和水果数量
matches = re.findall(r'(?P<name>\w+) has (?P<quantity>\d+) \w+', text)

for match in matches:
    print("Name:", match['name'], "- Quantity:", match['quantity'])

text = "apple banana orange grape"

# 使用预搜索断言匹配出包含 "apple" 之后的所有水果
result = re.findall(r'(?<=apple\s)(\w+)', text)

print("包含 'apple' 之后的水果:", result)  # 输出匹配到的水果列表

text = "Python is a powerful programming language"

# 使用肯定预搜索断言匹配包含 "is" 的单词
positive_result = re.findall(r'\b\w+(?= is\b)', text)

# 使用否定预搜索断言匹配不包含 "is" 的单词
negative_result = re.findall(r'\b\w+(?! is\b)', text)

print("肯定预搜索断言:", positive_result)  # 输出匹配到的单词列表
print("否定预搜索断言:", negative_result)  # 输出匹配到的单词列表

text = "Python is a powerful programming language"

# 使用 re.finditer() 函数匹配所有单词
matches_iter = re.finditer(r'\b\w+\b', text)

for match in matches_iter:
    print(match.group())  # 输出匹配到的单词

text = "apple,banana,orange,grape"

# 使用 re.split() 函数根据逗号拆分字符串
fruits = re.split(r',', text)

print("拆分后的水果列表:", fruits)  # 输出拆分后的水果列表

def double(match):
    return str(int(match.group(0)) * 2)

text = "The numbers are 1, 2, 3, and 4"

# 使用替换函数参数将所有数字乘以2
new_text = re.sub(r'\d+', double, text)

print("替换后的文本:", new_text)  # 输出替换后的文本

pattern = re.compile(r'\d{4}-\d{2}-\d{2}')

date1 = "2022-01-15"
date2 = "15-01-2022"

# 使用 re.fullmatch() 函数检查日期格式
match1 = pattern.fullmatch(date1)
match2 = pattern.fullmatch(date2)

if match1:
    print("日期格式正确")
else:
    print("日期格式错误")

if match2:
    print("日期格式正确")
else:
    print("日期格式错误")

pattern = re.compile(r'python', re.IGNORECASE)

text = "Python is a powerful programming language"

# 使用不区分大小写匹配模式查找 "Python"
match = pattern.search(text)

if match:
    print("Found")
else:
    print("Not found")

pattern = re.compile(r'\b\w{3}\b', re.DEBUG)

text = "The quick brown fox jumps over the lazy dog"

# 输出编译后的正则表达式调试信息
pattern.findall(text)