feature_extraction.py 文件源码

def location(url):
    fdata={'Accept':'*/*',
    'Accept-Encoding':'gzip, deflate',
    'Accept-Language':'en-US,en;q=0.8',
    'Connection':'keep-alive',
    'Content-Length':'29',
    'Content-type':'application/x-www-form-urlencoded',
    'Cookie':'PHPSESSID=hisbu0rrh09nssn99vckkqr740; __utma=103585558.1324897437.1443987736.1443987736.1443987736.1; __utmb=103585558.2.10.1443987736; __utmc=103585558; __utmz=103585558.1443987736.1.1.utmcsr=google|utmccn=(organic)|utmcmd=organic|utmctr=(not%20provided)',
    'Host':'get-site-ip.com',
    'Origin':'http://get-site-ip.com',
    'Referer':'http://get-site-ip.com/',
    'User-Agent':'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36'}
    response=requests.post('http://get-site-ip.com/_pages/_moduler/ajaxSkrivUtIpPaNamn.php',data={'dnsNakeLookUp_In':url})
    #print response.content
    soup=BeautifulSoup(response.content,"lxml")
    #print "Location : "
    for i in soup.find_all("div", { "class" :"response"}):
    #   print i.get_text()
    #   print i.get_text().split('-')[2].replace(' ','')
        return i.get_text().split('-')[2].replace(' ','')

#Finds number of special characters