Python 爬虫笔记（三）

#用正则表达式爬取图片#! /usr/bin/env python#coding=utf-8import urllib2importrefrombs4 importBeautifulSouphtml=urllib2.urlopen("http://www.pythonscraping.com/pages/page3.html")bsObj=BeautifulSoup(ht

张章章Sam

558人浏览 · 2016-09-27 12:12:02

张章章Sam · 2016-09-27 12:12:02 发布

#用正则表达式爬取图片
#! /usr/bin/env python
#coding=utf-8

import urllib2
import  re 
from    bs4 import  BeautifulSoup

html=urllib2.urlopen("http://www.pythonscraping.com/pages/page3.html")
bsObj=BeautifulSoup(html)
images=bsObj.findAll("img", {"src":re.compile("\.\.\/img\/gifts/img.*\.jpg")})
for image in images:
            print(image["src"])