- #win python 2.7.x
- import re,sys,urllib,codecs
- xh = urllib.urlopen("http://www.baidu.com/s?q1=123&rn=100").read().decode('utf-8')
- rc = re.compile(r'<td class=f><h3 class="t"><a.*?>(?P<first>.*?)</h3>',re.I)
- match = rc.finditer(xh)
- rcr = re.compile(r'<[^>]+>',re.I)
- f = codecs.open("xiaohei.txt", "w", "utf-8")
- for i in rc.finditer(xh):
- ss = i.group(0)
- s1 = rcr.sub('',ss)
- print (s1)
- f.write(s1)
- f.close()
- #该片段来自于http://www.codesnippet.cn/detail/130620133988.html
来源: http://www.codesnippet.cn/detail/130620133988.html