正则表达式

 1 import re
 2 
 3 text = ‘Hi, I am Shirley Hilton. I am his wife.‘
 4 text2 = ‘site sea sue sweet see case sse ssee loses‘
 5 text3 = ‘312347829412231877187874328709‘
 6 text4 = ‘aj科 技eu_^%#@^(*&^^-=wio238 jdhfaD按数据库we97r389‘
 7 text5 = ‘(021)88776543 010-55667890 02584453362 0571 66345673 32473 23545346346547900‘
 8 
 9 print(re.findall(r"\bhi", text))   # \b是表示单词的开头或者结尾，空格、标点、换行都是单词的分隔。
10 print(re.findall("i.", text))      # .代表匹配任意一个字符
11 print(re.findall(".", text))
12 print(re.findall(r"\S", text))     # 不是空白符的任意一个字符
13 print(re.findall(r"i\S", text))
14 print(re.findall("I.*e", text))     # *代表前面前面的字符可以重复任意多次（包括0）仅代表数量
15 print(re.findall("I.*?e", text))    # ?懒惰匹配，与*不同，？匹配到最短的就停止
16 print(re.findall(r"\bs\S*?e\b", text2))    # 如果用 r"\bs.*?e\b"  会混进来一个带空格的两个单词，就不是要查询的一个单词了。
17 print(re.findall(r"\bs.*?e\b", text2))
18 print(re.findall("1[0-9]{10}", text3))
19 print(re.findall(r"\bc.*l", text2))
20 print(re.findall(r"\d+", text3))
21 print(re.findall("[0-9]*", text3))
22 print(re.findall("[0-9]+", text3))  # +与* 的区别就在于 +是会至少匹配1个， *可以是0
23 print(re.findall(r"\w", text4))   # 匹配字母、数字、下划线、汉字
24 print(re.findall(r"\s", text4))    # 匹配任意的空白符
25 print(re.findall(r"\(0\d{2,3}\)\d{7,8}|0\d{2,3}[ -]?\d{7,8}|\d+", text5))
26 #  首先看第一个|之前的 \(0\d{2,3}\)是匹配(021) \d{7,8}是后面的88776543
27 #  再看下一个0\d{2,3}[ -]?\d{7,8} 匹配0开头的0xx或者0xxx  然后后面紧跟着空格或者- 这两个符号可以匹配（可有可无？）然后再匹配剩下的后面的数字\d{7,8}
28 #  最后面的\d+ 就是一个收尾的，前面的匹配不成功的就在这里等着了， 根据管道符从左到右依次匹配，所以\d{7,8}放最后啦

[‘hi‘]
[‘i,‘, ‘ir‘, ‘il‘, ‘is‘, ‘if‘]
[‘H‘, ‘i‘, ‘,‘, ‘ ‘, ‘I‘, ‘ ‘, ‘a‘, ‘m‘, ‘ ‘, ‘S‘, ‘h‘, ‘i‘, ‘r‘, ‘l‘, ‘e‘, ‘y‘, ‘ ‘, ‘H‘, ‘i‘, ‘l‘, ‘t‘, ‘o‘, ‘n‘, ‘.‘, ‘ ‘, ‘I‘, ‘ ‘, ‘a‘, ‘m‘, ‘ ‘, ‘h‘, ‘i‘, ‘s‘, ‘ ‘, ‘w‘, ‘i‘, ‘f‘, ‘e‘, ‘.‘]
[‘H‘, ‘i‘, ‘,‘, ‘I‘, ‘a‘, ‘m‘, ‘S‘, ‘h‘, ‘i‘, ‘r‘, ‘l‘, ‘e‘, ‘y‘, ‘H‘, ‘i‘, ‘l‘, ‘t‘, ‘o‘, ‘n‘, ‘.‘, ‘I‘, ‘a‘, ‘m‘, ‘h‘, ‘i‘, ‘s‘, ‘w‘, ‘i‘, ‘f‘, ‘e‘, ‘.‘]
[‘i,‘, ‘ir‘, ‘il‘, ‘is‘, ‘if‘]
[‘I am Shirley Hilton. I am his wife‘]
[‘I am Shirle‘, ‘I am his wife‘]
[‘site‘, ‘sue‘, ‘see‘, ‘sse‘, ‘ssee‘]
[‘site‘, ‘sea sue‘, ‘sweet see‘, ‘sse‘, ‘ssee‘]
[‘12347829412‘, ‘18771878743‘]
[‘case sse ssee l‘]
[‘312347829412231877187874328709‘]
[‘312347829412231877187874328709‘, ‘‘]
[‘312347829412231877187874328709‘]
[‘a‘, ‘j‘, ‘科‘, ‘技‘, ‘e‘, ‘u‘, ‘_‘, ‘w‘, ‘i‘, ‘o‘, ‘2‘, ‘3‘, ‘8‘, ‘j‘, ‘d‘, ‘h‘, ‘f‘, ‘a‘, ‘D‘, ‘按‘, ‘数‘, ‘据‘, ‘库‘, ‘w‘, ‘e‘, ‘9‘, ‘7‘, ‘r‘, ‘3‘, ‘8‘, ‘9‘]
[‘ ‘, ‘ ‘]
[‘(021)88776543‘, ‘010-55667890‘, ‘02584453362‘, ‘0571 66345673‘, ‘32473‘, ‘23545346346547900‘]