domain_search.py

# coding=utf8
import subprocess
import itertools
import psycopg2

dc = "a,ai,an,ang,ao,ba,bai,ban,bang,bao,bei,ben,beng,bi,bian,biao,bie,bin,bing,bo,bu,ca,cai,can,cang,cao,ce,cei,cen,ceng,cha,chai,chan,chang,chao,che,chen,cheng,chi,chong,chou,chu,chua,chuai,chuan,chuang,chui,chun,chuo,ci,cong,cou,cu,cuan,cui,cun,cuo,da,dai,dan,dang,dao,de,dei,den,deng,di,dia,dian,diao,die,din,ding,diu,dong,dou,du,duan,dui,dun,duo,e,ei,en,eng,er,fa,fan,fang,fei,fen,feng,fiao,fo,fou,fu,ga,gai,gan,gang,gao,ge,gei,gen,geng,gong,gou,gu,gua,guai,guan,guang,gui,gun,guo,ha,hai,han,hang,hao,he,hei,hen,heng,hm,hng,hong,hou,hu,hua,huai,huan,huang,hui,hun,huo,ji,jia,jian,jiang,jiao,jie,jin,jing,jiong,jiu,ju,juan,jue,jun,ka,kai,kan,kang,kao,ke,kei,ken,keng,kong,kou,ku,kua,kuai,kuan,kuang,kui,kun,kuo,la,lai,lan,lang,lao,le,lei,leng,li,lia,lian,liang,liao,lie,lin,ling,liu,lo,long,lou,lu,luan,lun,luo,ma,mai,man,mang,mao,me,mei,men,meng,mi,mian,miao,mie,min,ming,miu,mo,mou,mu,n,na,nai,nan,nang,nao,ne,nei,nen,neng,ng,ni,nia,nian,niang,niao,nie,nin,ning,niu,nong,nou,nu,nuan,nun,nuo,o,ou,pa,pai,pan,pang,pao,pei,pen,peng,pi,pian,piao,pie,pin,ping,po,pou,pu,qi,qia,qian,qiang,qiao,qie,qin,qing,qiong,qiu,qu,quan,que,qun,ran,rang,rao,re,ren,reng,ri,rong,rou,ru,rua,ruan,rui,run,ruo,sa,sai,san,sang,sao,se,sen,seng,sha,shai,shan,shang,shao,she,shei,shen,sheng,shi,shou,shu,shua,shuai,shuan,shuang,shui,shun,shuo,si,song,sou,su,suan,sui,sun,suo,ta,tai,tan,tang,tao,te,tei,teng,ti,tian,tiao,tie,ting,tong,tou,tu,tuan,tui,tun,tuo,wa,wai,wan,wang,wei,wen,weng,wo,wong,wu,xi,xia,xian,xiang,xiao,xie,xin,xing,xiong,xiu,xu,xuan,xue,xun,ya,yan,yang,yao,ye,yi,yin,ying,yo,yong,you,yu,yuan,yue,yun,za,zai,zan,zang,zao,ze,zei,zen,zeng,zha,zhai,zhan,zhang,zhao,zhe,zhei,zhen,zheng,zhi,zhong,zhou,zhu,zhua,zhuai,zhuan,zhuang,zhui,zhun,zhuo,zi,zong,zou,zu,zuan,zui,zun,zuo".split(",")

def whois(domain):
    c = subprocess.Popen(["whois", domain], stdout=subprocess.PIPE)
    ret = c.stdout.read()
    regested = True
    if 'No match for' in ret:
        print('Good Domain: {0}'.format(domain))
        regested = False
    else:
        print('Regested Domain: {0}'.format(domain))
    return domain, regested

def get_or_create(domain_name):
    con = None
    created = False
    try:
        con = psycopg2.connect(database='testdb', user='liwei', password='liwei')
        cur = con.cursor()
        cur.execute("SELECT name, regested FROM domain_names WHERE name='{0}'".format(domain_name))
        rows = cur.fetchall()
        if rows:
            return rows[0][0], rows[0][1], created

        if not created:
            cur.execute("INSERT INTO domain_names (name, regested) VALUES ('{0}', '{1}')".format(domain_name, True))
            con.commit()
            created = True
            return domain_name, True, created

    except psycopg2.DatabaseError, e:
        if con:
            con.rollback()
        print 'Error %s' % e    
    finally:
        if con:
            con.close()

def update(domain):
    con = None
    created = False
    try:
        con = psycopg2.connect(database='testdb', user='liwei', password='liwei')
        cur = con.cursor()
        cur.execute("UPDATE domain_names SET regested=False WHERE name='{0}'".format(domain))
        con.commit()
    except psycopg2.DatabaseError, e:
        if con:
            con.rollback()
        print 'Error %s' % e    
    finally:
        if con:
            con.close()
    

if __name__ == '__main__':
    # ret = [whois("%s%s" % ("".join(i), ".com")) for i in itertools.product(dc, dc)]
    domain = 'g.com'
    for domain_name in itertools.product(dc, dc):
        domain = "{0}{1}".format("".join(domain_name), ".com")
        domain, regested, created = get_or_create(domain)
        if created:
            domain, regested = whois(domain)
            if not regested:
                update(domain)
        else:
            print "Skiped DB Cache: {0}".format(domain)