PythonStudy——re 模块

# 将目标字符串中的所以数字找出
data = ‘123abc呵呵‘

res = re.findall(r‘\d‘, data)  # \d就代表数字
print(res)  # [‘1‘, ‘2‘, ‘3‘]

# re.I不区分大小写的匹配
print(re.findall(r‘a‘, ‘abc123嘿嘿abcABC‘, flags=re.I))  # [‘a‘, ‘a‘, ‘A‘]

# a|b a或b单个字符
print(re.findall(r‘a|b‘, ‘abc123嘿嘿abcABC‘, flags=re.I))  # [‘a‘, ‘b‘, ‘a‘, ‘b‘, ‘A‘, ‘B‘]

# [a,b] a或,或b单个字符
print(re.findall(r‘[a,b]‘, ‘abc,123嘿嘿abcABC‘, flags=re.I))  # [‘a‘, ‘b‘, ‘,‘, ‘a‘, ‘b‘, ‘A‘, ‘B‘]

# [^ab]非a及非b的所有单个字符
print(re.findall(r‘[^ab]‘, ‘abc,123嘿嘿abcABC‘))  # [‘c‘, ‘,‘, ‘1‘, ‘2‘, ‘3‘, ‘嘿‘, ‘嘿‘, ‘c‘, ‘A‘, ‘B‘, ‘C‘]

# [a-z]所有单个小写字母   [A-Z]所有单个大写字母   [0-9]所有单个数字
print(re.findall(r‘[a-z]‘, ‘abc,123嘿嘿abcABC‘))  # [‘a‘, ‘b‘, ‘c‘, ‘a‘, ‘b‘, ‘c‘]
print(re.findall(r‘[0-9]‘, ‘abc,123嘿嘿abcABC‘))  # [‘1‘, ‘2‘, ‘3‘]

# 所有小写大写数字单个字符
print(re.findall(r‘[a-z]|[A-Z]|[0-9]‘, ‘abc,123嘿嘿abcABC‘))  # [‘a‘, ‘b‘, ‘c‘, ‘1‘, ‘2‘, ‘3‘, ‘a‘, ‘b‘, ‘c‘, ‘A‘, ‘B‘, ‘C‘]

print(re.findall(r‘[A-Za-z0-9]‘, ‘abc,123嘿嘿[abcABC‘))  # [‘a‘, ‘b‘, ‘c‘, ‘1‘, ‘2‘, ‘3‘, ‘a‘, ‘b‘, ‘c‘, ‘A‘, ‘B‘, ‘C‘]

# .会匹配除\n以为的所有单个字符
print(re.findall(r‘.‘, ‘*\_+=\n \r\t‘))  # [‘*‘, ‘\\‘, ‘_‘, ‘+‘, ‘=‘, ‘ ‘, ‘\r‘, ‘\t‘]

# re.S会让.能匹配所有单个字符
print(re.findall(r‘.‘, ‘*\_+=\n \r\t‘, flags=re.S))  # [‘*‘, ‘\\‘, ‘_‘, ‘+‘, ‘=‘, ‘\n‘, ‘ ‘, ‘\r‘, ‘\t‘]

# \d单个数字 == [0-9]
print(re.findall(r‘\d‘, ‘abc,123嘿嘿[abcABC‘))  # [‘1‘, ‘2‘, ‘3‘]
# \w == [A-Za-z0-9_]  将常见的汉字就理解为单个字母

print(re.findall(r‘\w‘, ‘abc,123嘿[_‘))  # [‘a‘, ‘b‘, ‘c‘, ‘1‘, ‘2‘, ‘3‘, ‘嘿‘, ‘_‘]
# \s == [\f\n\r\t\v ] 单个空：空格、制表符、换页符等

print(re.findall(r‘\s‘, ‘\f\n\r\t\v ‘))  # [‘\x0c‘, ‘\n‘, ‘\r‘, ‘\t‘, ‘\x0b‘, ‘ ‘]

# \D就是\d的对立面：非数字的所有单个字符  \W就是\w的对立面  \S就是\s的对立面
print(re.findall(r‘\D‘, ‘abc,123嘿[_‘))  # [‘a‘, ‘b‘, ‘c‘, ‘,‘, ‘嘿‘, ‘[‘, ‘_‘]


# 单个汉字 [\u4e00-\u9fa5]
print(re.findall(r‘[\u4e00-\u9fa5]‘, ‘abc,123嘿[_‘))  # [‘嘿‘]

# 建议使用  [0-9]  [A-Za-z0-9_]  [\f\n\r\t\v ]  [^0-9]  [\u4e00-\u9fa5]
# 不建议使用 \d  \w   \s  \D   \w

import re
# 1.将r‘\\‘的正则语法字符串转换成 正则对象 ‘\‘, 用来匹配 ‘\‘ 字符的
# 2.拿着转换后的正则对象，来匹配目标字符串
print(re.findall(r‘\\‘, r‘a\d\p\\‘))  # [‘\\‘, ‘\\‘, ‘\\‘, ‘\\‘]


re_obj = re.compile(r‘\n‘)  # 转换成匹配 换行符 的正则对象
res = re_obj.findall(‘\n‘)
print(res)  # [‘\n‘]

re_obj = re.compile(r‘\\d‘)  # 转换成匹配 \d 的正则对象
res = re_obj.findall(‘\d‘)
print(res)  # [‘\\d‘]

re_obj = re.compile(r‘\d‘)  # 转换成匹配 数字 的正则对象
res = re_obj.findall(‘\d‘)  # \d不是数字
print(res)  # []

re_obj = re.compile(r‘\\n‘)  # 转换成匹配 \n 的正则对象
res = re_obj.findall(‘\n‘)  # 代表换行，不能被匹配
print(res)  # []
res = re_obj.findall(r‘\n‘)  # 就代表\n，能被匹配
print(res)  # [‘\\n‘]

# 明确个数的重复
# {n}
print(re.findall(r‘a‘, ‘aaabbb‘))  # [‘a‘, ‘a‘, ‘a‘]
print(re.findall(r‘a{2}‘, ‘aaabbb‘))  # [‘aa‘]
print(re.findall(r‘ab‘, ‘aabbababab‘))  # [‘ab‘, ‘ab‘, ‘ab‘, ‘ab‘]
print(re.findall(r‘a{2}b{2}‘, ‘aabbababab‘))  # [‘aabb‘]
print(re.findall(r‘ab{2}‘, ‘aabbababab‘))  # [‘abb‘]

# {n,}  匹配n到无数个，题中最少匹配abb, 贪婪匹配 abbb 能被匹配为 abb 和 abbb，优先匹配多的
print(re.findall(r‘ab{2,}‘, ‘ababbabbbabbbb‘))  # [‘abb‘, ‘abbb‘, ‘abbbb‘]

# {,n} 匹配0到n个，ab{,2} 优先匹配abb，没有ab也行，如果还没有a也将就
print(re.findall(r‘ab{,2}‘, ‘aababbabbbabbbb‘))  # [‘a‘, ‘ab‘, ‘abb‘, ‘abb‘, ‘abb‘]

# {n,m} 匹配n到m个，ab{1,3} 优先匹配 abbb，再考虑abb, ab
print(re.findall(r‘ab{1,3}‘, ‘aababbabbbabbbb‘))  # [‘ab‘, ‘abb‘, ‘abbb‘, ‘abbb‘]

# 特殊符号的重复
# *: 匹配0到无数个
print(re.findall(r‘ab*‘, ‘aababbabbbabbbb‘))  # [‘a‘, ‘ab‘, ‘abb‘, ‘abbb‘, ‘abbbb‘]
# +: 匹配1到无数个
print(re.findall(r‘ab+‘, ‘aababbabbbabbbb‘))  # [‘ab‘, ‘abb‘, ‘abbb‘, ‘abbbb‘]
# ?: 匹配0到1个
print(re.findall(r‘ab?‘, ‘aababbabbbabbbb‘))  # [‘a‘, ‘ab‘, ‘ab‘, ‘ab‘, ‘ab‘]


# 需求：匹配所以单词
print(re.findall(r‘[a-z]+‘, ‘abc def hello print‘))  # [‘abc‘, ‘def‘, ‘hello‘, ‘print‘]
print(re.findall(r‘[a-z]+\b‘, ‘abc def hello print‘))  # [‘abc‘, ‘def‘, ‘hello‘, ‘print‘]

# \b代表单词边界，用空格(字符串的结尾也包括)作为匹配规则
print(re.findall(r‘[a-z]*c‘, ‘abc def hello print acb zc‘))  # [‘abc‘, ‘ac‘, ‘zc‘]
print(re.findall(r‘[a-z]*c\b‘, ‘abc def hello print acb zc‘))  # [‘abc‘, ‘zc‘]

import re
s = """http://www.baidu.com
https://sina.com.cn
https://youku.com
haam
abchttp://www.oldboy.com
"""
# ^代表以什么开头，$代表以什么结尾，必须结合flags=re.M来完成多行匹配
print(re.findall(r‘^http.+com$‘, s, re.M))  # [‘http://www.baidu.com‘, ‘https://youku.com‘]

import re

url = ‘https://www.baidu.com, http://www.youku.com‘
# 需求：拿到url的域名的  baidu , youku
print(re.findall(r‘www.([a-z]+).com‘, url))  # [‘baidu‘, ‘youku‘]

# ()代表分组
# findall匹配，如果匹配规则用有分组语法，只存放分组结果
print(re.findall(r‘(www).([a-z]+).com‘, url))  # [(‘www‘, ‘baidu‘), (‘www‘, ‘youku‘)]

# 分组的编号：分组的顺序编号按照左括号的前后顺序
print(re.findall(r‘(((w)ww).([a-z]+).com)‘, url))  # [(‘www.baidu.com‘, ‘www‘, ‘w‘, ‘baidu‘), (‘www.youku.com‘, ‘www‘, ‘w‘, ‘youku‘)]


# findall是全文匹配，可以从任意位置开始，匹配多次
# match非全文匹配，必须从头开始匹配，只能匹配一次

# 专门处理分组的方法：分组，分组编号，有名分组，取消分组
# 取消分组: 必须写()，但是()为分组语法，我们只是想通过()将一些数据作为整体，所以()必须，再取消分组即可
# (?:) 取消分组只是作为整体   (?P<名字>) 有名分组
url = ‘www.baidu.com,www.youku.com‘
res = re.match(r‘((?:www).(?P<name>[a-z]+).com)‘, url)
# print(res)  # <_sre.SRE_Match object; span=(0, 13), match=‘www.baidu.com‘>
print(res.group(1))  # www.baidu.com
print(res.group(2))  # baidu
print(res.group(‘name‘))  # baidu

import re

s = ‘a b ac def‘
print(s.split(‘ ‘))  # [‘a‘, ‘b‘, ‘ac‘, ‘def‘]

# 正则拆分
s = ‘a b,ac@def‘
print(re.split(r‘[ ,@]‘, s))  # [‘a‘, ‘b‘, ‘ac‘, ‘def‘]


s = ‘python abc python‘
print(re.sub(‘python‘, ‘Python‘, s))  # Python abc Python
print(re.sub(‘python‘, ‘Python‘, s, count=1))  # Python abc python


# 结合分组可以完成信息的重组与替换
s = ‘day a good!!!‘  # ‘a good good day‘
print(re.sub(‘(day) (a) (good)‘, r‘today is \2 \3 \3 \1‘, s))