Skip to content

Latest commit

 

History

History
97 lines (82 loc) · 2.36 KB

python-rexp.rst

File metadata and controls

97 lines (82 loc) · 2.36 KB

Python Regular Expression cheatsheet

Compare HTML tags

tag type format example
all tag <[^>]+> <br />, <a>
open tag <[^/>][^>]*> <a>, <table>
close tag </[^>]+> </p>, </a>
self close <[^/>]+/> <br /> 
# open tag
>>> re.search('<[^/>][^>]*>', '<table>') != None
True
>>> re.search('<[^/>][^>]*>', '<a href="#label">') != None
True
>>> re.search('<[^/>][^>]*>', '<img src="/https/github.com/img">') != None
True
>>> re.search('<[^/>][^>]*>', '</table>') != None
False

# close tag
>>> re.search('</[^>]+>', '</table>') != None
True

# self close
>>> re.search('<[^/>]+/>', '<br />') != None
True

re.findall() match string

# split all string
>>> re.findall('[\w]+', source)
['Hello', 'World', 'Ker', 'HAHA']

# parsing python.org website
>>> import urllib
>>> import re
>>> s = urllib.urlopen('https://www.python.org')
>>> html = s.read()
>>> s.close()
>>> print "open tags"
open tags
>>> re.findall('<[^/>][^>]*>', html)[0:2]
['<!doctype html>', '<!--[if lt IE 7]>']
>>> print "close tags"
close tags
>>> re.findall('</[^>]+>', html)[0:2]
['</script>', '</title>']
>>> print "self-closing tags"

Group Comparison

# (...) group a regular expression
>>> m = re.search(r'(\d{4})-(\d{2})-(\d{2})', '2016-01-01')
>>> m
<_sre.SRE_Match object; span=(0, 10), match='2016-01-01'>
>>> m.groups()
('2016', '01', '01')
>>> m.group()
'2016-01-01'
>>> m.group(1)
'2016'
>>> m.group(2)
'01'
>>> m.group(3)
'01'

# Nesting groups
>>> m = re.search(r'(((\d{4})-\d{2})-\d{2})', '2016-01-01')
>>> m.groups()
('2016-01-01', '2016-01', '2016')
>>> m.group()
'2016-01-01'
>>> m.group(1)
'2016-01-01'
>>> m.group(2)
'2016-01'
>>> m.group(3)
'2016'