1 import re
2
3 """
4 re.compile(regex)
5     编译一个正则表达式模式，返回一个模式对象
6 """
7 regex = r'[a-z]'
8 pattern = re.compile(regex)

 1 import re
 2
 3 """
 4 re.findall(pattern, str)
 5     返回所有满足匹配条件的结果，并放到列表中
 6 """
 7 regex = r'[a-zA-Z]+'
 8 s = 'Hello Python'
 9 pattern = re.compile(regex)
10
11 lst = re.findall(pattern, s)
12 print(lst)    # ['Hello', 'Python']

 1 import re
 2
 3 """
 4 re.finditer(pattern, str)
 5     返回迭代器
 6     迭代器中每一个元素需要调用group()，得到结果
 7 """
 8 regex = r'[a-zA-Z]+'
 9 s = 'Hello Python'
10 pattern = re.compile(regex)
11
12 iterator = re.finditer(pattern, s)
13
14 print(iterator)    # <callable_iterator object at 0x000001FDB3F29BE0>
15
16 for i in iterator:
17     print(i.group())

 1 import re
 2
 3 """
 4 re.search(pattern, str)
 5     返回满足匹配条件的第一个结果对象
 6 """
 7 regex = r'[a-zA-Z]+'
 8 s = 'Hello Python'
 9 pattern = re.compile(regex)
10
11 obj = re.search(pattern, s)
12
13 if obj:
14     print(obj.group())

 1 import re
 2
 3 """
 4 flags
 5     re.I    忽略大小写
 6     re.M    多行模式，改变^和$的行为
 7     re.S    .可以匹配任意字符，包括换行符
 8 """
 9 regex = r'<dd>.*?title="(?P<title>.*?)".*?</dd>'
10 s = '<dd><a href="#" title="Python中的正则">...</a></dd>'
11 pattern = re.compile(regex, re.S)
12
13 iterator = re.finditer(pattern, s)
14
15 for i in iterator:
16     print(i.group('title'))

 1 import re
 2
 3 """
 4 取消分组
 5     (?:)
 6 或匹配
 7     long|short
 8 """
 9 regex = r'www.(?:page|hopen).com'
10 s = 'www.hopen.com'
11 pattern = re.compile(regex)
12
13 iterator = re.finditer(pattern, s)
14
15 for i in iterator:
16     print(i.group())

 1 import re
 2
 3
 4 def get_data(regex, s):
 5     pattern = re.compile(regex)
 6     obj = re.search(pattern, s)
 7     if obj:
 8         return obj.group()
 9
10
11 # 贪婪匹配
12 regex_greedy = r'<.*>'
13 # 惰性匹配
14 regex_lazy = r'<.*?>'
15 content = '<a href="#">...</a>'
16
17 ret_1 = get_data(regex_greedy, content)
18 ret_2 = get_data(regex_lazy, content)
19 print(ret_1)    # <a href="">...</a>
20 print(ret_2)    # <a href="">