Public feed
#722538
headers = urllib.urlencode({'Host':'www.google.com'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.7) Gecko/20070914 Firefox/2.0.0.7','Accept text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5','Accept-Language':'en-us,en;q=0.5','Accept-Encoding':'gzip,deflate','Accept-Charset':'ISO-8859-1,utf-8;q=0.7,*;q=0.7','Keep-Alive':'300','Connection':'keep-alive','Referer':'http://www.google.com/webhp?hl=en&tab=iw','Cookie':'PREF=ID=2d354a310d3935a7:TM=1191215097:LM=1191215097:S=4oANUmhSP2QveVoJ' #i don't know how python will handle a cookie})class googleSearchPage: def __init__(self, query, languageCode="en", get="http://www.google.com/search?%s"): self.params = urllib.urlencode({"hl":languageCode,"q":query,"btnG":"Google Search"}) self.URL = get % self.params self.page = urllib2.urlopen(self.URL, headers) print self.page.read() #this line is for testing!! def getResults(self, resultRegexString = '<div class=g><!--m-->.+?</div>'): resultRegex = re.compile(resultRegexString) #self.results = [googleResult(result) for result in re.compile(resultRegex).findall(self.page.read())] self.results = [result for result in re.compile(resultRegex).findall(self.page.read())] return len(self.results)gsp = googleSearchPage("internet")gsp.getResults()print gsp.results