python 有关网站ip，whois信息，是否自定义404,headers

判断网站是http://1.1.1.1还是http://www.xx.com,利用tld模块

获取网站ip方法一

import ipgetter
import requests


IP = ipgetter.myip()
url = 'http://freegeoip.net/json/'+IP
r = requests.get(url)
js = r.json()
print 'IP Adress: '         +   js['ip']
print 'Country Code: '      +   js['country_code']
print 'Country Name: '      +   js['country_name']
print 'Region Code: '       +   js['region_code']
print 'Region Name: '       +   js['region_name']
print 'City Name: '         +   js['city']
print 'Zip code: '          +   js['zip_code']
print 'Time Zone: '         +   js['time_zone']
print 'Latitude: '          +   str(js['latitude'])
print 'Longitude: '         +   str(js['longitude'])

获取网站ip方法二

import socket
import tld
print tld.get_tld(url)
from Config import FileConfig
from url_list import get_url_list

def get_ip(domain):
    import socket
    ip_url = socket.getaddrinfo(domain,'http')[0][4][0]
    return ip_url

for i in get_url_list(FileConfig.URLFILE):
    tt = 'www.' + tld.get_tld(i)
    print tt
    print get_ip(tt)
    

匹配网站地址为ip地址

import tld
a = [] 
import re


g = open('url.txt','w+')
#----------------------------------------------------------------------
def ceshi_url(url_file):
    """"""
    with open(url_file) as w:
        urls = w.readlines()
        for i in urls:
            i = i.strip('\n').strip('\r')
            reip = re.compile(r"(?

#coding:utf-8
import requests
import re
import pymongo

connection=pymongo.MongoClient('127.0.0.1',27017) 
db=connection.wangzuxian
collection=db.page_404

########################################################################
class page_404(object):
    """"""
    #----------------------------------------------------------------------
    def __init__(self, url):
        """Constructor"""
        super(page_404, self).__init__()
        self.url = url
        self.page_waf_name = ["非法","防火墙","安全狗","SafeDog","管理员","云防御","365","创宇盾"]
        self.test_path1 = '/nikendingbuzhidaowoyaoganma.html'
        self.test_path2 = '/nikendingbuzhidaowoyaoganma.asp'
        #self.keyWord_list = []
   
    #----------------------------------------------------------------------
    def page_content(self):
        """"""
        r1 = requests.get(self.url + self.test_path1)
        r2 = requests.get(self.url + self.test_path2)
        #print r1.content
        #print 'r1'
        #print r2.content
        return r1.content,r2.content

    #----------------------------------------------------------------------
    def keyWord_page(self):
        """"""
        keyWord_list = []
        r1 ,r2 = self.page_content()
        #print r1
        #print type(self.page_waf_name)
        for i in self.page_waf_name:
            #print i
            m = re.findall(str(i),str(r1))
            if len(m) != 0:
                for i in m:
                    print i
                    collection.update({"URL":self.url},
                                              {"$set": {'WAF' + i : i }},
                                                 upsert = True)                     
                    #keyWord_list.append(i)
                    #print keyWord_list
                    
            #return keyWord_list
         
              
   
    #----------------------------------------------------------------------
    def cmp_page(self):
        """"""
        r1,r2 = self.page_content()
        try:
            if cmp(r1,r2) == 0:
                print '自定义404'
                collection.update({"URL":self.url},
                                                  {"$set": {'404_page':'True'}},
                                                          upsert = True)                 
                
            
        except Exception,e:
            print str(e)  

headers

---

import requests

resp = requests.get('http://www.4399.com')
k_list = []
v_list = []
for k in resp.headers.keys():
    print k + '----' + resp.headers[k]