Python抓取百度查询结果,python抓取查询结果,#win python


#win python 2.7.ximport re,sys,urllib,codecsxh = 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://byrx.net

评论关闭