# 提取大小寫字母混合的單詞
import re
a = 'Excel 12345Word23456PPT12Lr'
r = re.findall('[a-zA-Z]{3,5}',a)
# 提取字母的數(shù)量3個(gè)到5個(gè)
print(r)
# ['Excel', 'Word', 'PPT']
# 貪婪 與 非貪婪  【Python默認(rèn)使用貪婪模式】
# 貪婪：'[a-zA-Z]{3,5}'
# 非貪婪：'[a-zA-Z]{3,5}?' 或 '[a-zA-Z]{3}'
# 建議使用后者，不要使用?號(hào)，否則你會(huì)與下面的?號(hào)混淆
# 匹配0次或無(wú)限多次 *號(hào)，*號(hào)前面的字符出現(xiàn)0次或無(wú)限次
import re
a = 'exce0excell3excel3'
r = re.findall('excel*',a)
r = re.findall('excel.*',a) # ['excell3excel3']
# excel 沒(méi)有l(wèi) 有很多l(xiāng)都可以匹配出來(lái)
print(r)
# ['exce', 'excell', 'excel']
# 匹配1次或者無(wú)限多次 +號(hào)，+號(hào)前面的字符至少出現(xiàn)1次
import re
a = 'exce0excell3excel3'
r = re.findall('excel+',a)
print(r)
# ['excell', 'excel']
# 匹配0次或1次  ?號(hào)，?號(hào)經(jīng)常用來(lái)去重復(fù)
import re
a = 'exce0excell3excel3'
r = re.findall('excel?',a)
print(r)
# ['exce', 'excel', 'excel']

line = 'xyz,xcz.xfc.xdz,xaz,xez,xec'
r = re.findall('x[de]z', line)
# pattern 是x開始，z結(jié)束，含d或e
print(r)
# ['xdz', 'xez']
r = re.findall('x[^de]z', line)
# pattern 是x開始，z結(jié)束，不是含d或e
print(r)
# ['xyz', 'xcz', 'xaz']

# \w 可以提取中文，英文，數(shù)字和下劃線，不能提取特殊字符
import re
a = 'Excel 12345Word\n23456_PPT12lr'
r = re.findall('\w',a)
print(r)
# ['E', 'x', 'c', 'e', 'l', '1', '2', '3', '4', '5', 'W', 'o', 'r', 'd', '2', '3', '4', '5', '6', '_', 'P', 'P', 'T', '1', '2', 'l', 'r']
# \W 提取特殊字符，空格 \n \t
import re
a = 'Excel 12345Word\n23456_PPT12lr'
r = re.findall('\W',a)
print(r)
# [' ', '\n']

# 限制電話號(hào)碼的位置必需是8-11位才能提取
import re
tel = '13811115888'
r = re.findall('^\d{8,11}$',tel)
print(r)
# ['13811115888']

# 將abc打成一個(gè)組，{2}指的是重復(fù)幾次，匹配abcabc
import re
a = 'abcabcabcxyzabcabcxyzabc'
r = re.findall('(abc){2}',a)  # 與
# ['abc', 'abc']
print(r)
r = re.findall('(abc){3}',a)
# ['abc']

# findall第三參數(shù) re.I忽略大小寫
import re
a = 'abcFBIabcCIAabc'
r = re.findall('fbi',a,re.I)
print(r)
# ['FBI']
# 多個(gè)模式之間用 | 連接在一起
import re
a = 'abcFBI\nabcCIAabc'
r = re.findall('fbi.{1}',a,re.I | re.S)
# 匹配fbi然后匹配任意一個(gè)字符包括\n
print(r)
# ['FBI\n']

import re
re.findall(pattern, string, flags=0)
pattern.findall(string[ , pos[ , endpos]])

import re
line = "111aaabbb222小呼嚕奧利奧"
r = re.findall('[0-9]',line)
print(r)
# ['1', '1', '1', '2', '2', '2']

re.match(pattern, string, flags=0)
# (標(biāo)準(zhǔn)，要匹配的，標(biāo)志位)

print(re.match('www','www.xxxx.com'))
print(re.match('www','www.xxxx.com').span())
print(re.match('com','www.xxxx.com'))

<re.Match object; span=(0, 3), match='www'>
(0, 3)
None

import re
a = 'life is short,i use python,i love python'
r = re.search('life(.*)python(.*)python',a)
print(r.group(0)) # 完整正則匹配 ，life is short,i use python,i love python
print(r.group(1)) # 第1個(gè)分組之間的取值 is short,i use 
print(r.group(2)) # 第2個(gè)分組之間的取值 ,i love 
print(r.group(0,1,2)) # 以元組形式返回3個(gè)結(jié)果取值 ('life is short,i use python,i love python', ' is short,i use ', ',i love ')
print(r.groups()) # 返回就是group(1)和group(2) (' is short,i use ', ',i love ')

import re
# .*  表示任意匹配除換行符（\n、\r）之外的任何單個(gè)或多個(gè)字符
# (.*?)  表示"非貪婪"模式，只保存第一個(gè)匹配到的子串
# re.M多行匹配，影響 ^ 和 $
# re.I使匹配對(duì)大小寫不敏感
line = "Cats are smarter than dogs"
matchObj1 = re.match(r'(.*) are (.*?) .*', line,  re.M|re.I)
matchObj2 = re.match(r'(.*) smarter (.*?) .*', line,  re.M|re.I)
matchObj3 = re.match(r'(.*) than (.*)', line,  re.M|re.I)
print(matchObj1)
print(matchObj2)
print(matchObj3)
# <re.Match object; span=(0, 26), match='Cats are smarter than dogs'>
# <re.Match object; span=(0, 26), match='Cats are smarter than dogs'>
# None
if matchObj1:
print ("matchObj1.group() : ", matchObj1.group())
print ("matchObj1.group(1) : ", matchObj1.group(1))
print ("matchObj1.group(2) : ", matchObj1.group(2))
else:
print ("No match!!")
if matchObj2:
print ("matchObj2.group() : ", matchObj2.group())
print ("matchObj2.group(1) : ", matchObj2.group(1))
print ("matchObj2.group(2) : ", matchObj2.group(2))
else:
print ("No match!!")
if matchObj3:
print ("matchObj3.group() : ", matchObj3.group())
print ("matchObj3.group(1) : ", matchObj3.group(1))
print ("matchObj3.group(2) : ", matchObj3.group(2))
else:
print ("No match!!")
# matchObj1.group() :  Cats are smarter than dogs
# matchObj1.group(1) :  Cats
# matchObj1.group(2) :  smarter
# matchObj2.group() :  Cats are smarter than dogs
# matchObj2.group(1) :  Cats are
# matchObj2.group(2) :  than
# matchObj3.group() :  Cats are smarter than dogs
# matchObj3.group(1) :  Cats are smarter
# matchObj3.group(2) :  dogs

import re
# 點(diǎn) 是匹配單個(gè)字符
# 星是前面的東西出現(xiàn)0次或無(wú)數(shù)次
# 點(diǎn)星就是任意字符出現(xiàn)0次或無(wú)數(shù)次
str = "a b a b"
matchObj1 = re.match(r'a(.*)b', str,  re.M|re.I)
matchObj2 = re.match(r'a(.*?)b', str,  re.M|re.I)
print("matchObj1.group() : ", matchObj1.group())
print("matchObj2.group() : ", matchObj2.group())
# matchObj1.group() :  a b a b
# matchObj2.group() :  a b

re.search(pattern, string, flags=0)

import  re
line = "cats are smarter than dogs"
matchObj = re.match(r'dogs',line,re.M|re.I)
matchObj1= re.search(r'dogs',line,re.M|re.I)
matchObj2= re.match(r'(.*) dogs',line,re.M|re.I)
if matchObj:
print ("match --> matchObj.group() : ", matchObj.group())
else:
print ("No match!!")
if matchObj1:
print ("match --> matchObj1.group() : ", matchObj1.group())
else:
print ("No match!!")
if matchObj2:
print ("match --> matchObj2.group() : ", matchObj2.group())
else:
print ("No match!!")
# No match!!
# match --> matchObj1.group() :  dogs
# match --> matchObj2.group() :  cats are smarter than dogs

re.sub('被替換的','替換成的',a)

# 把FBI替換成BBQ
import re
a = 'abcFBIabcCIAabc'
r = re.sub('FBI','BBQ',a)
print(r)
# 把FBI替換成BBQ，第4參數(shù)寫1，證明只替換第一次，默認(rèn)是0（無(wú)限替換）
import re
a = 'abcFBIabcFBIaFBICIAabc'
r = re.sub('FBI','BBQ',a,1)
print(r)
# abcBBQabcCIAabc
# abcBBQabcFBIaFBICIAabc

# 把函數(shù)當(dāng)參數(shù)傳到sub的列表里，實(shí)現(xiàn)把業(yè)務(wù)交給函數(shù)去處理，例如將FBI替換成$FBI$
import re
a = 'abcFBIabcFBIaFBICIAabc'
def 函數(shù)名(形參):
 分段獲取 = 形參.group()  # group（）在正則表達(dá)式中用于獲取分段截獲的字符串，獲取到FBI
 return '$' + 分段獲取 + '$'
r = re.sub('FBI',函數(shù)名,a)
print(r)