def search(self, queryStr):
   queryStr = urllib2.quote(queryStr)
   url = 'https://www.google.com.hk/search"htmlcode">

user_agents = ['Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20130406 Firefox/23.0',      'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:18.0) Gecko/20100101 Firefox/18.0',      'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533+      (KHTML, like Gecko) Element Browser 5.0',      'IBM WebExplorer /v0.94', 'Galaxy/1.0 [en] (Mac OS X 10.5.6; U; en)',      'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)',      'Opera/9.80 (Windows NT 6.0) Presto/2.12.388 Version/12.14',      'Mozilla/5.0 (iPad; CPU OS 6_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko)      Version/6.0 Mobile/10A5355d Safari/8536.25',      'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko)      Chrome/28.0.1468.0 Safari/537.36',      'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.0; Trident/5.0; TheWorld)']
 def search(self, queryStr):
   queryStr = urllib2.quote(queryStr)
   url = 'https://www.google.com.hk/search?hl=en&q=%s' % queryStr
   request = urllib2.Request(url)
   index = random.randint(0, 9)
   user_agent = user_agents[index]
   request.add_header('User-agent', user_agent)
   response = urllib2.urlopen(request)
   html = response.read()
   results = self.extractSearchResults(html)





　　不要被user_agents那个list吓到，那其实就是10个user agent 字符串，这么做是让我们伪装的更好一些，如果你需要更多的user agent 请看这里 UserAgentString。
17-19行表示随机选择一个user agent 字符串，然后用request 的add_header方法伪装一个user agent。
　　通过伪装user agent能够让我们持续抓取搜索引擎结果，如果这样还不行，那我建议在每两次查询间随机休眠一段时间，这样会影响抓取速度，但是能够让你更持续的抓取结果，如果你有多个IP，那抓取的速度也就上来了。
　　github上有本文所有源代码，需要的同学可从下面的网址下载:
https://github.com/meibenjin/GoogleSearchCrawler