【自然语言处理】NLP入门（八）：1、正则表达式与Python中的实现（8）：正则表达式元字符：.、[]、^、$、*、+、?、{m,n}

/^1[34578][0-9]$/

import re
s = 'hi, i am a student. my name is Hilton.'

# 匹配所有的i
print(re.findall(r'i', s))  # ['i', 'i', 'i', 'i']

# 匹配除换行符以外的任意字符
print(re.findall(r'.', s))  # ['h', 'i', ',', 'i', ' ', 'a', 'm', ' ', 'a', ' ', 's', 't', 'u', 'd', 'e', 'n', 't', '.', 'm', 'y', ' ', 'n', 'a', 'm', 'e', ' ', 'i', 's', ' ', 'H', 'i', 'l', 't', 'o', 'n', '.']

# 匹配i后面跟除换行符以外的任意字符的形式
print(re.findall(r'i.', s))  # ['i,', 'i ', 'is', 'il']

# 匹配i后面跟不是空白符的任意字符的形式
print(re.findall(r'i\S', s))  # ['i,', 'is', 'il']

import re
s = 'map mit mee mwt meqwt'

# 匹配'me'
print(re.findall(r'me', s))  # ['me', 'me']

# 匹配m后面跟i或者w再跟t形式
print(re.findall(r'm[iw]t', s))  # ['mit', 'mwt']

# 元字符“.”放在[]内，不起作用
print(re.findall(r'm[.]', s))  # []


s = '0x12x3x567x8xy'
print(re.findall(r'x[0123456789]x', s))  # ['x3x', 'x8x']
print(re.findall(r'x[0-9]x', s))  # ['x3x', 'x8x']
print(re.findall(r'x[^3]x', s))  # ['x8x']

import re
s = 'hello hello world hello Mary hello John'
print(re.findall(r'hello', s))  # ['hello', 'hello', 'hello', 'hello']
print(re.findall(r'^hello', s))  # ['hello']

import re
s = 'hello hello world hello Mary hello John'
print(re.findall(r'hello$', s))  # []
s = 'hello hello world hello Mary hello'
print(re.findall(r'hello$', s))  # ['hello']
s = 'map mit mee mwt meqmtm$'
print(re.findall(r'm[aiw]$', s))  # []
print(re.findall(r'm[aiwt$]', s))  # ['ma', 'mi', 'mw', 'mt', 'm$']
print(re.findall(r'm[aiwt$]$', s))  # ['m$']

import re
s = '0x12x3x567x8xy'

# 使用字符集匹配数字
print(re.findall(r'[0-9]', s))  
# ['0', '1', '2', '3', '5', '6', '7', '8']

# 使用\d匹配数字
print(re.findall(r'\d', s))  
# ['0', '1', '2', '3', '5', '6', '7', '8']

# 匹配字母“x”或数字
print(re.findall(r'[x\d]', s))  
# ['0', 'x', '1', '2', 'x', '3', 'x', '5', '6', '7', 'x', '8', 'x']

import re
s = 'a ab abbbbb abbbbbxa'
print(re.findall(r'ab*', s))  
# ['a', 'ab', 'abbbbb', 'abbbbb', 'a']

import re
s = 'a ab abbbbb abbbbbxa'
print(re.findall(r'ab+', s))  
# ['ab', 'abbbbb', 'abbbbb']

import re
s='a ab abbbb abbbbbxa'
re.findall(r'ab+',s) #最大模式、贪心模式
# ['ab', 'abbbb', 'abbbbb']
re.findall(r'ab+?',s) #最小模式、非贪心模式
# ['ab', 'ab', 'ab']

import re
s = '021-33507yyx,021-33507865,010-12345678,021-123456789'
print(re.findall(r'021-\d{8}', s))  
# ['021-33507865', '021-12345678']
print(re.findall(r'\b021-\d{8}\b', s))  
# ['021-33507865']

import re
import random
import string

def generate_random_string(length):
    characters = string.ascii_letters + string.digits + "_.#%"
    return ''.join(random.choice(characters) for _ in range(length))

random_strings = [generate_random_string(random.randint(1, 25)) for _ in range(10)]
print("随机生成的字符串列表：", random_strings)

filtered_strings = [s for s in random_strings if re.match(r"^[a-zA-Z][a-zA-Z0-9_.]{4,19}$", s)]
print("符合条件的字符串列表：", filtered_strings)