python网站搭建（Python快速实现一个域名）

域名和ip地址信息是非常基础的情报信息，目前网上有很多网站都提供了域名信息的查询、IP地址及归属地的查询。本文通过Python Flask实现域名及IP情报信息的聚合网站。因为域名和IP地址信息会有变化，为了减少接口压力，做了本地数据库的存储，新鲜度保存一周，每次查询先从本地数据库获取信息，如果本地库信息有并且没有超过一个星期就从本地库取，没有就从其他网站获取，并更新到本地库。一、获取域名WHOIS信息网上提供域名WHOIS信息查询的网站有很多，这里以http://whois.chinafu.com 为例实现WHOIS信息的查询和解析。12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758import requestsfrom bs4 import BeautifulSoupheaders = { 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'}def getwhoisinfobychinafu(domain): ret_result = {} result=getWhoisInfoFromDB(domain) if len(result)==0: whois_service_url = 'http://whois.chinafu.com/whois.php' post_data={"domain":domain} try: post_result=requests.post(whois_service_url,post_data) if post_result.status_code == 200: ret_str = post_result.content.decode('utf-8') soup = BeautifulSoup(ret_str, 'lxml') items_tr =soup.find(name='table',attrs={'class':'listtable'}).find_all(name='tr') for item_tr in items_tr: td_item=item_tr.find(name='td') if 'colspan' in td_item.attrs: key_name='详情' key_value=td_item.find(name='div',id='tab1').text else: key_name=item_tr.find(name='th').text key_value=item_tr.find(name='td').text ret_result[key_name]=key_value addchinafuWhoisInfo2DB(ret_result) except Exception as r: print('未知错误 %s' % (r)) #ret_result = json.dumps(ret_result, ensure_ascii=False) else: ret_result=result[0] return ret_resultdef getWhoisInfoFromDB(domainname): whoisInfos=db.session.execute('select * from whoisinfo where domain_name="%s" and updated_time > DATE_SUB(CURDATE(), INTERVAL 1 WEEK)' % domainname).fetchall() whoisInfo_dics=[] for whoisInfo in whoisInfos: chinafuwhoisinfo_dic=chinafuwhoisinfo2dic(whoisInfo) whoisInfo_dics.append(chinafuwhoisinfo_dic) return whoisInfo_dicsdef addchinafuWhoisInfo2DB(chinafuWhoisInfo_dic): chinafuWhois=WhoisInfo() chinafuWhois.domain_name=chinafuWhoisInfo_dic.get('域名DomainName') chinafuWhois.domain_status=chinafuWhoisInfo_dic.get('域名状态Domain Status','') chinafuWhois.registrar=chinafuWhoisInfo_dic.get('注册商Sponsoring Registrar','') chinafuWhois.name_server=chinafuWhoisInfo_dic.get('DNS 服务器Name Server','') chinafuWhois.registrar_creation_date=chinafuWhoisInfo_dic.get('注册日期Registration Date','') chinafuWhois.registrar_updated_date = chinafuWhoisInfo_dic.get('更新日期Update Date', '') chinafuWhois.registrar_expiry_date = chinafuWhoisInfo_dic.get('到期日期Expiration Date', '') chinafuWhois.detail=chinafuWhoisInfo_dic.get('详情', '')[0:10000] chinafuWhois.source = '中国福网' db.session.execute('delete from whoisinfo where domain_name="%s" and source="%s"' % (chinafuWhoisInfo_dic.get('域名DomainName'), chinafuWhois.source)) db.session.add(chinafuWhois) db.session.commit()这里为了减少直接从其他网站获取WHOIS信息的压力，做了本地数据库的存储，每次先从本地数据库取WHOIS的信息，如果本地库信息有并且没有超过一个星期就从本地库取，没有就从其他网站获取，并更新到本地库。这里getWhoisInfoFromDB实现了取新鲜度为1周的数据，addchinafuWhoisInfo2DB实现将获取的信息保存到本地数据库。二、根据域名解析出IP根据域名解析出IP代码：12345678def getIPbyDomain(domain): addr='' try: myaddr = socket.getaddrinfo(domain, 'http') addr=myaddr[0][4][0] except Exception as e: print(e) return addr三、获取IP信息获取IP信息的API接口也有很多，有淘宝的 https://ip.taobao.com/outGetIpInfo 、IPINFO http://ipinfo.io/、IPAPI http://ip-api.com/ 以及GeoLite2离线库等。从淘宝IP获取IP信息12345678910111213141516171819202122def getipinfobytaobao(ip): taobaoIp_url = 'https://ip.taobao.com/outGetIpInfo' post_data={"ip":ip,"accessKey":"alibaba-inc"} ret_ipinfo= {} try: return_data=requests.post(taobaoIp_url,post_data) #其中返回数据中code的值的含义为，0：成功，1：服务器异常，2：请求参数异常，3：服务器繁忙，4：个人qps超出 return_json=json.loads(return_data.text) if return_json['code']==0: ret_ipinfo['ip']=return_json['data']['ip'] ret_ipinfo['country']=return_json['data']['country'] ret_ipinfo['region']=return_json['data']['region'] ret_ipinfo['org']='' ret_ipinfo['city'] = return_json['data']['city'] ret_ipinfo['isp']=return_json['data']['isp'] ret_ipinfo['loc'] = '' ret_ipinfo['timezone'] = '' ret_ipinfo['source']='淘宝IP' addIPInfo2DB(ret_ipinfo) except Exception as e: print('未知错误 %s' % (e)) return ret_ipinfo从ipinfo.io获取IP信息123456789101112def getipinfobyipinfo(ip): api_url='http://ipinfo.io/'+ip ipinfo = {} try: req_return = requests.get(api_url) if req_return.status_code == 200: ipinfo = json.loads(req_return.text) ipinfo['source']='ipinfo.io' addIPInfo2DB(ipinfo) except Exception as e: print('未知错误 %s' % (e)) return ipinfo从ip-api.com获取IP信息1234567891011121314def getipinfobyipapi(ip): api_url='http://ip-api.com/json/'+ip ipinfo={} try: req_return=requests.get(api_url) if req_return.status_code==200: ipinfo=json.loads(req_return.text) ipinfo['ip'] = ip ipinfo['source'] = 'ip-api.com' ipinfo['loc'] = str(ipinfo['lat'])+','+str(ipinfo['lon']) addIPInfo2DB(ipinfo) except Exception as e: print('未知错误 %s' % (e)) return ipinfo从GeoLite离线库获取IP信息如何获取GeoLite离线库及如何读取，详见：http://xiejava.ishareread.com/posts/2c5697c0/123456789101112131415def getipinfobygeoip2(ip): ipinfo={} dbdir=Config.geoLiteDBdir with geoip2.database.Reader(dbdir) as reader: response = reader.city(ip) ipinfo['ip'] =ip ipinfo['country'] = response.country.names['zh-CN'] ipinfo['region'] ='' ipinfo['city']=response.city.name ipinfo['org'] ='' ipinfo['loc'] = str(response.location.latitude)+','+str(response.location.longitude) ipinfo['timezone'] = response.location.time_zone ipinfo['source'] = 'GeoIP' addIPInfo2DB(ipinfo) return ipinfo四、搭建一个FLASK Web应用来查询聚合的域名、IP情报信息1、FLASK Web应用的工程组织2、配置数据及读取配置数据1）配置数据配置数据分别放在.env及.flaskenv中，其中.env放的是工程中用到的数据库链接等比较私密的配置信息。.flaskenv放的是Flask运行环境的信息.env的配置信息参考如下：123456DEV_DATABASE_URI = 'mysql+pymysql://dbuser:[email protected]:3306/infocol_db_dev?charset=utf8'TEST_DATABASE_URI = 'mysql+pymysql://dbuser:[email protected]:3306/infocol_db_test?charset=utf8'PROD_DATABASE_URI = 'mysql+pymysql://dbuser:[email protected]:3306/infocol_db?charset=utf8'SQLALCHEMY_TRACK_MODIFICATIONS = TrueSECRET_KEY=your secret key.falskenv配置信息参考如下：1FLASK_ENV=development2）实现读取配置数据通过config.py实现配置数据的读取及管理12345678910111213141516171819202122232425262728293031323334353637import osfrom dotenv import load_dotenvbasedir=os.path.abspath(os.path.dirname(__file__))flaskenv_path=os.path.join(basedir,'.flaskenv')env_path=os.path.join(basedir,'.env')if os.path.exists(flaskenv_path): load_dotenv(flaskenv_path)if os.path.exists(env_path): load_dotenv(env_path)class Config: geoLiteDBdir=os.path.join(basedir,'GeoLite2\GeoLite2-City.mmdb') flaskenv = os.getenv('FLASK_ENV','development') SECRET_KEY=os.getenv('SECRET_KEY','123!@#') SQLALCHEMY_TRACK_MODIFICATIONS=os.getenv('SQLALCHEMY_TRACK_MODIFICATIONS') SQLALCHEMY_DATABASE_URI = os.getenv('DEV_DATABASE_URI') @staticmethod def init_app(app): passclass DevelopmentConfig(Config): DEBUG=True SQLALCHEMY_DATABASE_URI = os.getenv('DEV_DATABASE_URI')class TestingConfig(Config): TESTING=True SQLALCHEMY_DATABASE_URI = os.getenv('TEST_DATABASE_URI')class ProductionConfig(Config): SQLALCHEMY_DATABASE_URI = os.getenv('PROD_DATABASE_URI')config={ 'development':DevelopmentConfig, 'testing':TestingConfig, 'production':ProductionConfig, 'default':DevelopmentConfig}3、界面及路由界面很简单就一个域名/IP的输入框，输入域名或IP后去查询相应的域名信息或IP信息显示到界面上。界面用jinjia2的模板index.html代码如下：123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293{% extends "bootstrap/base.html" %}{% block title %}InfoCol{% endblock %}{% block head %} {{ super() }} <style></style>{% endblock %}{% block body %} {% block navbar %} <div class="navbar navbar-inverse" role="navigation"> <div class="container"> <div class="navbar-header"> <button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-collapse"> <span class="sr-only">Toggle navigation</span> <span class="icon-bar"></span> <span class="icon-bar"></span> <span class="icon-bar"></span> </button> <a class="navbar-brand" href="/">InfoCol</a> </div> <div class="navbar-collapse collapse"> <ul class="nav navbar-nav"> <li><a href="/">Home</a></li> </ul> </div> </div> </div> {% endblock %} {% block content %} <div class="container"> <div class="page-header " > <form method="post" class="center-block"> <div class="center-block" style="text-align:center"> {{ form.hidden_tag() }} {{ form.name.label }}{{ form.name() }} {{ form.submit() }} </div> </form> </div> <div> {% if whois_info %} <table class="table table-bordered"> <tr><th colspan="2">{{ name }}的Whois信息</th></tr> {% for item in whois_info %} {% if item!='详情' %} <tr><td style="width: 20%">{{ item }}</td><td style="width: 80%">{{ whois_info[item] }}</td></tr> {% else %} <tr> <td style="width: 20%"> <a role="button" data-toggle="collapse" href="#collapseExample" aria-expanded="false" aria-controls="collapseExample"> {{ item }} </a> </td> <td style="width: 80%"> <div class="collapse" id="collapseExample"> <div class="well"> {{ whois_info[item] }} </div> </div> </td> </tr> {% endif %} {% endfor %} </table> {% endif %} {% if ipinfos|length>0 %} <table class="table table-bordered"> <tr><th>IP</th><th>国家/地区</th><th>省份</th><th>城市</th><th>机构</th><th>ISP</th><th>经纬度</th><th>来源</th></tr> {% for ipinfo in ipinfos %} <tr> <td>{{ ipinfo['ip'] }}</td> <td>{{ ipinfo['country'] }}</td> <td>{{ ipinfo['region'] }}</td> <td>{{ ipinfo['city'] }}</td> <td>{{ ipinfo['org'] }}</td> <td>{{ ipinfo['isp'] }}</td> <td>{{ ipinfo['loc'] }}</td> <td> {% if ipinfo['source']=='ipinfo.io' %} <a href="http://ipinfo.io/{{ ipinfo['ip'] }}" target="_blank">{{ ipinfo['source'] }}</a> {% elif ipinfo['source']=='ip-api.com'%} <a href="http://ip-api.com/json/{{ ipinfo['ip'] }}" target="_blank">{{ ipinfo['source'] }}</a> {% else %} {{ ipinfo['source'] }} {% endif %} </td> </tr> {% endfor %} </table> {% endif %} </div> </div> {% endblock %}{% endblock %}路由配置处理中实现了获取表单中的信息，并判断是域名还是IP如果是域名者获取whois信息，并根据域名获取IP信息。如果输入的是IP则获取IP信息，并反馈到页面上。1234567891011121314151617@index_bp.route('/',methods=['GET','POST'])def index(): name = '' ipinfos = [] whois_info = '' form = InputForm() if form.validate_on_submit(): name = form.name.data if checkip(name): ipinfos = getipinfo(name) else: whois_info = getwhoisinfo(name) whois_ip = getIPbyDomain(name) if checkip(whois_ip): ipinfos = getipinfo(whois_ip) form.name.data = '' return render_template('index.html',form=form, name=name, ipinfos=ipinfos, whois_info=whois_info)4、最终实现效果至此通过Python快速实现了一个简单的域名、IP信息聚合网站全部源代码：https://github.com/xiejava1018/infocollect演示地址：http://test.ishareread.com/原文链接： https://xiejava.gitee.io/posts/fa820ec9/