1. 定位符号

import re

print(re.findall(r'^Hello', 'Hello World'))   # ['Hello']  ^ 匹配开头
print(re.findall(r'World$', 'Hello World'))   # ['World']  $ 匹配结尾
print(re.findall(r'.', 'Hi'))                 # ['H','i']  . 匹配任意字符

---

2. 字符类

print(re.findall(r'[amk]', 'apple monkey kiwi'))  # ['a','m','k']  匹配 a 或 m 或 k
print(re.findall(r'[^abc]', 'abcxyz'))            # ['x','y','z']  匹配非 a/b/c

---

3. 数量限定符

print(re.findall(r'ab*', 'a ab abb abbb'))      # ['a','ab','abb','abbb']  * 0次或多次
print(re.findall(r'ab+', 'a ab abb abbb'))      # ['ab','abb','abbb']      + 1次或多次
print(re.findall(r'ab?', 'a ab abb abbb'))      # ['a','ab','ab','ab']     ? 0或1次
print(re.findall(r'o{2}', 'Bob food'))          # ['oo']                   精确2次
print(re.findall(r'o{2,}', 'foooood'))          # ['oooo']                 至少2次
print(re.findall(r'o{1,3}', 'foooood'))         # ['ooo']                  1到3次

---

4. 或者与分组

print(re.findall(r'cat|dog', 'I love cat and dog'))   # ['cat','dog']
m = re.match(r'(ab)+c', 'abababc')
print(m.group())  # 'abababc' 捕获分组

---

5. 标志位

print(re.findall(r'(?i)python', 'PYTHON python PyThOn'))
# ['PYTHON', 'python', 'PyThOn']  i=忽略大小写

---

6. 非捕获分组

print(re.findall(r'(?:ab)+', 'abababc'))   # ['ababab']  不保存分组内容

---

7. 注释

print(re.findall(r'foo(?# this is comment)bar', 'foobar'))  # ['foobar']

---

8. 前瞻与回溯

# 前向肯定 (?=re)
print(re.findall(r'foo(?=bar)', 'foobar foo123'))  # ['foo']  foo 后必须跟 bar

# 前向否定 (?!re)
print(re.findall(r'foo(?!bar)', 'foobar foo123 foo'))  # ['foo','foo']  foo 后不能跟 bar

# 回顾肯定 (?<=re)
print(re.findall(r'(?<=\$)\d+', 'Price is $100 and $20'))  # ['100','20']  前面要有 $

# 回顾否定 (?<!re)
print(re.findall(r'(?<!\$)\d+', 'Price is $100 and 200'))  # ['200'] 前面不能有 $

---

9. 单词边界

print(re.findall(r'er\b', 'never verb'))   # ['er']    单词边界
print(re.findall(r'er\B', 'never verb'))   # ['er']    非单词边界

---

10. 特殊字符类

print(re.findall(r'\w', 'Hi_123!'))    # ['H','i','_','1','2','3']  字母数字下划线
print(re.findall(r'\W', 'Hi_123!'))    # ['!']                       非字母数字下划线
print(re.findall(r'\s', 'a b\tc\n'))   # [' ','\t','\n']             空白符
print(re.findall(r'\S', 'a b'))        # ['a','b']                   非空白符
print(re.findall(r'\d', 'a1b2'))       # ['1','2']                   数字
print(re.findall(r'\D', 'a1b2'))       # ['a','b']                   非数字

---

11. 字符串边界

print(re.findall(r'\AHello', 'Hello World'))   # ['Hello']  只能匹配开头
print(re.findall(r'World\Z', 'Hello World'))   # ['World']  结尾（不含换行）

---

12. 分组引用

m = re.match(r'(\w+) \1', 'hello hello')
print(m.group())   # 'hello hello'   \1 表示第1个分组的内容

---