Python正则表达式之re.match()精准匹配字符串开头详解

import re

result = re.match(r'pattern', 'target_string', flags)

import re

text = "123abc"
match_obj = re.match(r'\d+', text)

if match_obj:
    print("✅ 匹配成功:", match_obj.group())  # 输出: 123
else:
    print("❌ 匹配失败")

import re

text = "abc123def"
match_obj = re.match(r'\d+', text)  # 尝试从开头匹配数字

if match_obj:
    print("✅ 匹配成功:", match_obj.group())
else:
    print("❌ 匹配失败")  # 输出此句！

import re

text = "Hello 456 World"

# match() —— 必须从开头匹配
print("🔹 match():", re.match(r'\d+', text))  # None

# search() —— 可在任意位置匹配
print("🔸 search():", re.search(r'\d+', text))  # <re.Match object; span=(6, 9), match='456'>

import re

def is_valid_mobile(text):
    pattern = r'^1[3-9]\d{9}$'
    return bool(re.match(pattern, text))

# 测试用例
test_numbers = [
    "13812345678",   # ✅ 有效
    "15098765432",   # ✅ 有效
    "12345678901",   # ❌ 无效（不是合法号段）
    "013812345678"   # ❌ 无效（以0开头）
]

for num in test_numbers:
    status = "✅ 有效" if is_valid_mobile(num) else "❌ 无效"
    print(f"{num} → {status}")

import re

log_line = "[2024-04-05 14:32:10] User login successful"

# 匹配时间戳部分
timestamp_pattern = r'^\[\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}\]'

match_result = re.match(timestamp_pattern, log_line)

if match_result:
    print("📅 时间戳匹配成功:", match_result.group())
else:
    print("⚠️ 未找到时间戳格式")

import re

def check_email_domain(email):
    pattern = r'^[^@]+@example\.com$'
    return bool(re.match(pattern, email))

# 测试
emails = [
    "user@example.com",      # ✅
    "admin@other.com",       # ❌
    "test@EXAMPLE.COM",      # ❌（大小写不匹配）
    "a@b@c.com"              # ❌（非法格式）
]

for e in emails:
    status = "✅ 允许" if check_email_domain(e) else "❌ 拒绝"
    print(f"{e} → {status}")

match_result = re.match(r'^[^@]+@example\.com$', email, re.IGNORECASE)

import re

email = "john.doe@example.org"

pattern = r'^([a-zA-Z][a-zA-Z0-9._]*)@([a-zA-Z0-9.-]+\.[a-zA-Z]{2,})$'

match_obj = re.match(pattern, email)

if match_obj:
    username = match_obj.group(1)
    domain = match_obj.group(2)
    print(f"👤 用户名: {username}")
    print(f"🌐 域名: {domain}")
    print(f"📍 起始位置: {match_obj.start()}, 结束位置: {match_obj.end()}")

import re

text = "2024-04-05 15:20:30"

pattern = r'^(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2}) (?P<hour>\d{2}):(?P<minute>\d{2}):(?P<second>\d{2})$'

match_obj = re.match(pattern, text)

if match_obj:
    print(f"📅 年份: {match_obj.group('year')}")
    print(f"📆 月份: {match_obj.group('month')}")
    print(f"📅 日期: {match_obj.group('day')}")
    print(f"⏰ 时间: {match_obj.group('hour')}:{match_obj.group('minute')}:{match_obj.group('second')}")

import re

text = "123abc"

# 错误写法：没有 ^，实际相当于 search
result = re.match(r'\d+', text)  # 会成功？不！还是成功！因为 123 在开头！

# 但如果字符串是 "abc123"，就失败了
text2 = "abc123"
result2 = re.match(r'\d+', text2)  # ❌ 失败！因为不是从头开始

import re

# 错误做法（危险！）
re.match(r'\d+', '123')  # ✅ 正确

# 危险写法（潜在问题）
re.match('\\d+', '123')  # ⚠️ 可能出错，特别是在嵌套字符串中

import re

text = "Hello 世界! 123 @#$%"

# 能匹配什么？
pattern = r'^[A-Za-z]+\s+[^\w]*\d+\s*[@#$%]+$'

match_obj = re.match(pattern, text)

print("🎉 匹配结果:", match_obj.group() if match_obj else "无匹配")