Python爬虫之正则表达式基本用法实例分析

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

import re
p = re.compile('abcd')
print(type(p))
#<class '_sre.SRE_Pattern'>
print(dir(p))
#['__class__', '__copy__', '__deepcopy__', '__delattr__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__gt__', '__hash__', '__init__', '__le__', '__lt__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__sizeof__', '__str__', '__subclasshook__', 'findall', 'finditer', 'flags', 'fullmatch', 'groupindex', 'groups', 'match', 'pattern', 'scanner', 'search', 'split', 'sub', 'subn']
m = p.match('abcdef')
print(type(m))
#<class '_sre.SRE_Match'>
print(dir(m))
#['__class__', '__copy__', '__deepcopy__', '__delattr__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__gt__', '__hash__', '__init__', '__le__', '__lt__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__sizeof__', '__str__', '__subclasshook__', 'end', 'endpos', 'expand', 'group', 'groupdict', 'groups', 'lastgroup', 'lastindex', 'pos', 're', 'regs', 'span', 'start', 'string']
print(m.group())
#abcd
print(m.group(0))
#abcd

import re
p = re.compile('abcd')
m = p.match('abdcef')
print(m.group())
#AttributeError: 'NoneType' object has no attribute 'group'

import re
p = re.compile('.')
m = p.match('abdcef')
print(m.group())
#a

import re
p = re.compile('\.')
#匹配符号点（注意这里可前面加上了转义符\，就不是匹配任意字符了）
m = p.findall('abc.def.')
print(type(m))
#<class 'list'>
print(m)
#['.', '.']
#可以得出，返回的是一个list，全局查找，不想match方法只匹配字符串开头

import re
p = re.compile('[abc]+')
m = p.findall('abcdef')
print(m)
#*
 #['abc', '', '', '', '']
#+
 #['abc']

import re
p = re.compile('[abc]{3}')
m = p.findall('abcdabcd')
print(m)
#{1}
 #['a', 'b', 'c', 'a', 'b', 'c']
#{2}
 #['ab', 'ab']
#{3}
 #['abc', 'abc']

import re
p = re.compile('abcd')
m = p.search('abcdabcd')
print(m.group())

re.sub(pattern, repl, string, count=0, flags=0)

import re
phone = "2004-959-559 # 这是一个国外电话号码"
num = re.sub('#.*','',phone)
print(num)

import re
phone = "2004-959-559 # 这是一个国外电话号码"
num = re.sub('\D','',phone)
print(num)