import re
import urllib
def getHtml(url):
page=urllib.urlopen(url)
html = page.read()
return html
def getImg(html):
reg = r'src="(.*?\.jpg)" pic' #正则表达式
imgre = re.compile(reg)
imglist = re.findall(imgre,html)
x = 0
for imgurl in imglist:
urllib.urlretrieve(imgurl,"%s.jpg" % x)
x+=1
return imglist
html = getHtml("http://tieba.baidu.com/p/2460150866")
print html
print getImg(html)
网易云课堂python里面的爬虫
最新推荐文章于 2024-08-28 10:44:00 发布