testextraction.py 文件源码

def reg_date(url):
    url=url.strip("www.")
    print url
    ur="http://www.whois.com/whois/"+url
    r = requests.get(ur)
    data = r.content.decode("utf-8")

    #print data
    try :
        soup = BeautifulSoup(data)
        #<div class="whois_result" 
        for link in soup.find_all("div",{"class":"whois_result"}):
            site = link.get_text().lower()
            print site.decode("utf-8")
            print "\n date is \n"
            print re.findall("\d\d-[a-z][a-z][a-z]-\d\d\d\d",site.decode("utf-8"))[1]
            return re.findall("\d\d-[a-z][a-z][a-z]-\d\d\d\d",site.decode("utf-8"))[1]
    except:
        pass