# import sys
# print sys.getdefaultencoding()
import urllib
import re

def  getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html
def getNewslist(html):
    reg = '<i class="icon-angle-right"></i>(.*)</a>'
    url = re.findall(reg,html) 

    return url

if __name__ == '__main__':
    cslgHighlightnews = 'http://news.cslg.cn/Index/newslist/id/161'
    html = getHtml(cslgHighlightnews)
    # print html
    newslist = getNewslist(html)
    for i in newslist:
        print i    

为何正则每次匹配的结果都不一样而且都是不完整的