学习python就一直想做爬虫的东西,还要继续学
理论上的东西一要加强
#!/usr/bin/python #coding=utf-8 import urllib import re def getHtml(url): page = urllib.urlopen(url) html = page.read() return html def getImg(html): reg = r\'src=\"(.+?\\.jpg)\" pic_ext\' imgre = re.compile(reg) imglist = re.findall(imgre,html) x = 0 for imgurl in imglist: urllib.urlretrieve(imgurl,\'%s.jpg\' % x) x+=1 html = getHtml(\"http://tieba.baidu.com/p/3102805968\") print getImg(html)
爬到的图片