'''
Search: regex101 online regular matching
https://regex101.com/
'''
'''
Number: \d
non-numeric: \D
Empty string: \s
Non-empty string: \S
accsii code: \w
Non-accsii code: \W
All characters: *
A single arbitrary character: .
0 or one: ?
Occurs mn times: {m,n}
one or more: +
what to start with: ^
what ends with: $
or: | ---> abc|bcd
The matched regular is named as the name variable: {?P<name>regular}
'''
'''
matches '<h1>xxx</h1>'
'''
# re.compile('<(?P<tagname>\w*)>.*</(?P=tagname)>')
# re.match('<h1>xxx</h1>')
#a = timeit.timeit(setup='''import re ; reg = re.compile('<(?P<tagname>\w*)>.*</(?P=tagname)>')''',stmt='''reg.match('<h1>xxx</h1>')''',number=1000000)
#b = timeit.timeit(setup='''import re''',stmt='''re.match('<(?P<tagname>\w*)>.*</(?P=tagname)>','<h1>xxx</h1>')''',number=1000000)
# print(a)
# print(b)
# 0.895464103505607
# 2.401233610585925
# Write the regular expression object first, and then the matching efficiency is high
'''
In: https://regex101.com/ enter:
<(?P<tagname>\w*)>.*</(?P=tagname)>
<(?P<tagname>\w*)>(.*)</(?P=tagname)>
<(?P<tagname>\w*)>.*</(?P=tagname)>
<h1>xxx</h1>
What result do you want, add parentheses
grouping with parentheses
(<(?P<tagname>\w*)>(.*)</(?P=tagname)>) # There are three groups
'''
#First declare a regular object and match it through the regular object, which is efficient
s = str("aa<h1>xxx</h1> 到的 的 <html>xxx</html>")
# reg = re.compile(r"(<(?P<tagname>\w*)>(.*)</(?P=tagname)>)") #Add an r to solve the escape problem
reg = re.compile(r"(<(?P<tagname>\w+)>(.*)</(?P=tagname)>)") #Add an r to solve the escape problem
a=reg.match(s) # match at the beginning, no return
print(a) # None
b=reg.search(s).groups() # match from the beginning, then the second, return a result
g=reg.search(s).group("tagname") # match from the beginning, then the second, return a result
# group()[1]
print(b) #('<h1>xxx</h1>', 'h1', 'xxx')
print(g) #h1
# reg.split()
t = reg.findall(s)
print(t) #[('<h1>xxx</h1>', 'h1', 'xxx'), ('<html>xxx</html>', 'html', 'xxx')]
# reg.groups() # match search 的
# Real-time debugging and modification using https://regex101.com/
x = '1one2two3three4four'
reg1 = re.compile("\d")
c = reg1.findall(x) # find regex -- match all
d = reg1.split(x) # Regular is the separator
print(c) # ['1', '2', '3', '4']
print(d) # ['', 'one', 'two', 'three', 'four']