python常用爬虫正则表达式

python常用爬虫正则表达式

>>> ma = re.match(r'[\w]{4,6}@(163|126).com','test@126.com')
#匹配@后面任意域## 名的邮件这种格式
>>> ma.group()#验证结果

>>> str1 = 'aafa 223,4343'#必须要这种格式逗号不然下面的匹配不出来
>>> info = re.findall(r'\d+',str1)
>>> info
['223', '4343']
sum([int(x) for x in range(1,4)])#直接输出计算结果1+2+3

>>> str1 = 'test = 1000 333,aaa=444'
>>> info = re.sub(r'\d+','111',str1)#替换所有的数字为111
>>> info
'test = 111 111,aaa=111'
>>> info = re.sub(r'\w+','111',str1)#替换所有的字符串为111
>>> info

>>> str1 = 'test:c b d,k'
>>> re.split(r'=|,| ',str1)#分割，指定以=号，逗号，空格分割，｜代表或
['test:c', 'b', 'd', 'k']
>>> 
-----------------------------------------------------------------
str1 = 'xafa'
.表示任意字符一个例：re.findall('x.',str1，re.S)
#re.Ss可以忽略要匹配字符串里面的换行符达到不影响匹配的效果
>>>xa  #可以多个点一个点就是一个暂位符
-----------------------------------------------------------------
str1 = 'xafa'
re.findall(r'x*',str1)
>>>['x',' ',' ',' ']#*对应的没有就输出空
-----------------------------------------------------
str1 = 'xafa'
re.findall(r'x？',str1)
>>>['x',' ',' ',' '] #？对应的没有就输出空
----------------------------------------------------
str1 = 'fafXX3XXafjdfXX4XX'
re.findall(r'xx.*xx'.str1)#.*大胖子
>>>['XX3XXafjdfXX4XX']
---------------------------------------------------
str1 = 'fafXX3XXafjdfXX4XX'
re.findall(r'xx.*?xx'.str1)#小吃多餐
>>>['XX3XX','XX4XX']
s = '12ffdfdd12'
re.sub('12(.*?)12','12ddd12',s)
>>>12dddd12
-------------------------------------------------------
str1 = 'fafXX3XXafjdfXX4XX'
re.findall(r'xx(.*?)xx',str1)#找出我们需要的内容时就是括起来
>>>['3','4']
-----------------------------------------------------------
s2 = 'asdfxxIxx2233xxlovexxdfd'
f2 = re.findall('xx(.*？)xx2233xx(.*?)xx',s2)
print f2[0][1]

-------------------爬虫正则表达式应用------------------
#!-*-coding:utf-8-*-
import re
import urllib2
result = urllib2.urlopen('http://www.test.com/course/list')
buff = result.read()
listurl = re.findall(r'http:.+\.jpg',buff)#匹配开头和结束

i = 0
for url in listurl:
    f = open(str(i)+'.jpg','w')
    req = urllib2.urlopen(url)
    buf = req.read()
    f.write(buf)
    i = i + 1