4.1 标准库--正则表达式

# coding=utf-8

################
# re 正则表达式 #
################

import re

"""
正则表达式元字符
"""
s = r"abc"
print re.findall(s, "assffsdfdsfsfsd")

print re.findall(s, "abcfrefsafabcsfaabc")

# []，取其中的任何一个字符
str = "top tip tqp twp tep"
res = r"top"
print re.findall(res, str)

res = r"t[io]p"
str = "top tip tqp twp tep"
print re.findall(res, str)
# 取字符集之外的所有字符，注意，与单独使用^不同
res = r"t[^io]p"
str = "top tip tqp twp tep"
print re.findall(res, str)
# 去[io$]中的任意字符，注意，$在这代表的是普通字符，不是最后元字符
res = r"t[io$]p"
str = "top tip tqp twp tep"
print re.findall(res, str)
print "#"*20


# ^ 匹配字符串的开头
# 匹配开头是hello
res = r"^hello"
print re.findall(res, str)
# 行首没有hello，匹配为空
str = "word, hello boy"
print re.findall(res, str)
print "#"*20


# $ 匹配字符的结尾
res = r"boy"
str ="hello word,hello boy"
print re.findall(res, str)
res = r"boy$"
str ="hello word,hello boy"
print re.findall(res, str)
res = r"boy$"
str ="hello word,hello boys"
print re.findall(res, str)
print "#"*20


# 正则字符当正常字符使用，使用转义
res = "^abc"
str = "^abc ^abc ^abc"
print re.findall(res, str)
# 转义元字符
res = "\^abc"
str = "^abc ^abc ^abc"
print re.findall(res, str)

# 正则集合,数字
res = r'[0-9]'
str = "123456sre789sf0"
print re.findall(res, str)
res = r'[\d]'
str = "123456sre789sf0"
print re.findall(res, str)
# 取反
res = r'[\D]'
str = "123456sre789sf0"
print re.findall(res, str)

# 正则集合，字母、数字和_
res = r'[A-Za-z0-9_]'
str = "123456sre789_sf0AD@￥%………………%"
print re.findall(res, str)
res = r'[\w]'
str = "123456sre_789sf0AD@￥%………………%"
print re.findall(res, str)
# 取反
res = r'[\W]'
str = "123456sre7_89sf0AD@%%"
print re.findall(res, str)

# *(将*前面的字符重复0次或多次)
res = r"ab*"
str = "a b ab abc "
print re.findall(res, str)

# +（+前面的字符匹配1次或多次）
res = r"ab+"
str = "a b ab abc "
print re.findall(res, str)

# ? 可有可无，前面的字符重复0次或1次
res = r"^010-*\d{8}"
str = "010-12345678"
print re.findall(res, str)
res = r"^010-?\d{8}"
str = "010-12345678"
print re.findall(res, str)

# 贪婪模式,加载重复后面
res = r"ab+"
str = "abbbbbbbbbbb"
print re.findall(res, str)

# 非贪婪模式，取最小重复值
res = r"ab+?"
str = "abbbbbbbbbbb"
print re.findall(res, str)


# {}重复
res = r"^010-\d\d\d\d\d\d\d\d$"
str = "010-12345678"
print re.findall(res, str)
res = r"^010-\d{8}$"
str = "010-12345678"
print re.findall(res, str)

# {m,n}至少重复m次，最多重复n次
res = r"ab{2,6}"
str = "abbbbbbbbbbb"
print re.findall(res, str)
res = r"ab{15,19}"
str = "abbbbbbbbbbb"
print re.findall(res, str)

"""
正则表达式函数
"""
# 匹配电话号码
res = r"\d{3,4}-?\d{7,8}"
str ="010-12345678 01087654321 0531-33355566 0621123456"
print re.findall(res, str)

# compile 正则编译
res = r"\d{3,4}-?\d{7,8}"
p_tel = re.compile(res)
str ="010-12345678 01087654321 0531-33355566 0621-123456"
print p_tel.findall(str)

# match() 字符串中找正则对应的字符，匹配开头为正则的
# 如果能匹配，返回的不是字符串，group查看结果
# 如果没有匹配，返回None
res = "abc"
str = "abc bca"
x = re.match(res, str)
print x
print x.group()
res = "abc"
str = "babc bca"
y =  re.match(res, str)
print y
print "*"*30

# search() 查找字符串中匹配的正则，知道找到一个为止，而不是找到所有
res = "abc"
str = "bca abc"
print re.search(res, str)
res = "abc"
str = "abc bca abc"
z =  re.search(res, str)
print z
print z.group()

# finditer 返回迭代器
res = "abc"
str = "babc bca abc"
a = re.finditer(res, str)
print a

# sub 正则替换
res = "java"
str = "hello java.This java program?"
replaceStr = "python"
print re.sub(res, replaceStr, str)

# split 切割
ip = "192.168.1.1"
print ip.split(".")

res = r"[\+\-\*]"
str ="1+2-3*4"
print re.split(res, str)

"""
正则表达式修饰符--可选标志
"""
# re.I 正则不区分大小写
res = re.compile(r"abc", re.I)
str = "ABC ABC abc AbC"
print res.findall(str)

# re.S 是匹配包括换行在内的字符
res = r"baidu.com"
str = "www.baidu.com"
print re.findall(res, str)
res = r"baidu.com"
str = "www.baidu\ncom"
print re.findall(res, str)
res = r"baidu.com"
str = "www.baidu\ncom"
print re.findall(res, str, re.S)

# re.M 多行获取匹配
res = r"python"
str = """
    hello python
    python hello java
    hello c
    python hello perl
    """
print re.findall(res, str)
print re.findall(res, str, re.M)

# re.X 正则取消换行
res = r"""
    \d{3,4}
    -?
    \d{8}
    """
str = "010-12345678 051287654321"
print re.findall(res, str)
print re.findall(res, str, re.X)


"""
分组（|）
"""
res = r"\w{3}@(\.com|\.cn)"
print "*"*50