SM İle E-posta Hack

#!/Usr/Bin/Python
# -*- Coding: Utf-8 -*-
 
 
__VERSION__ = '0.1'
__AUTHOR__ = 'Galkan'
__DATE__ = '30.10.2013'
 
 
Try:
      Import Urllib2
      Import Sys
      Import Re
      Import Random
      Import Argparse
      Import Time
Except ImportError,Err:
      Import Sys
      Sys.Stdout.Write("%S\N" %Err)
      Sys.Exit(1)
 
 
 
Class Crawl:
 
 Def __init__(Self, Url_opt, Mail_opt, Time = 0):
 
  Self.HEADERS = {
   'User-Agent': 'Mozilla/5.0',
   'Accept': 'Text/Html,Application/Xhtml+Xml,Application/Xml;Q=0.9,*/*;Q=0.8',
   'Accept-Encoding': 'Gzip, Deflate',
   'Connection': 'Close',
   'DNT': '1'
  }
 
  Self.UAS = [
   'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, Like Gecko) Chrome/23.0.1271.97 Safari/537.11',
   'Mozilla/5.0 (Windows NT 6.1; WOW64; Rv:17.0) Gecko/20100101 Firefox/17.0',
   'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_2) AppleWebKit/536.26.17 (KHTML, Like Gecko) Version/6.0.2 Safari/536.26.17',
   'Mozilla/5.0 (Linux; U; Android 2.2; Fr-Fr; Desire_A8181 Build/FRF91) App3leWebKit/53.1 (KHTML, Like Gecko) Version/4.0 Mobile Safari/533.1',
   'Mozilla/4.0 (Compatible; MSIE 6.0; Windows NT 5.1; SV1; FunWebProducts; .NET CLR 1.1.4322; PeoplePal 6.2)',
   'Mozilla/5.0 (Windows NT 5.1; Rv:13.0) Gecko/20100101 Firefox/13.0.1',
   'Opera/9.80 (Windows NT 5.1; U; En) Presto/2.10.289 Version/12.01',
   'Mozilla/5.0 (Windows NT 5.1; Rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
   'Mozilla/4.0 (Compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; Mozilla/4.0 (Compatible; MSIE 6.0; Windows NT 5.1; SV1) ; .NET CLR 3.5.30729)'
      ]
 
  Self.Time = Time
  Self.Url_opt = Url_opt
  Self.Mail_opt = Mail_opt
 
  Self.Url_reg = Re.Compile("Href\S*=\S*\"([^\"]+)\"")
  If Not Self.Mail_opt == "All":
   Self.Email_reg = Re.Compile("[\D\W\-\_\.]+@%S"% (Self.Mail_opt))
  Else:
   Self.Email_reg = Re.Compile("[\D\W\-\_\.]+@[\D\W\-\_\.]+")
  Self.Site_reg = Re.Compile("(Https?|Ftp://)|(Javascript|Mailto)")
 
 
 Def Crawl(Self, Html):
   
  Ret_list = []
  For Node In Html:
   If Re.Findall(Self.Url_reg, Node):
    Resp = Re.Findall(Self.Url_reg, Node)
    For Elem In Resp:
     If Not Re.Match(Self.Site_reg, Elem):
      If Not Elem In Ret_list:
       Ret_list.Append(Elem)
 
  Return Ret_list
 
 
 Def Extract_email(Self, Html):
 
  Email_res = []
  For Node In Html:
   If Re.Findall(Self.Email_reg, Node):
    Email = Re.Findall(Self.Email_reg, Node)
    For Node In Email:
     If Node Not In Email_res:
      Email_res.Append(Node)
 
  Return Email_res
 
 
 Def Get_webpage(Self, Url):
  
  Html = None 
 
  Request = Urllib2.Request(Url)
  Self.HEADERS['User-Agent'] = Random.Choice(Self.UAS)
  Request.Add_header('User-Agent', Self.HEADERS)
 
  Response = Urllib2.Urlopen(Request)
                Html = Response.Readlines()
 
  Return Html
 
 
 Def Main(Self, Url):
 
  Hostname = Url.Split("/")[2]
  Html = Self.Get_webpage(Url)
 
  If Not Html == None:
   If Self.Url_opt == "Url":
    Response_list = Self.Extract_email(Html)
    For Node In Response_list:
     Print Node
   Elif Self.Url_opt == "Url-All":
    Crawled_url = Self.Crawl(Html)
    For Url In Crawled_url:
     New_url = ""
     If Not Re.Match("/", Url):
      New_url = "Https://" + Hostname + "/" + Url
     Else:
      New_url = "Https://" + Hostname + Url
 
    Email_list = []
    For Url In Crawled_url:
     New_url = ""
     If Not Re.Match("/", Url):
      New_url = "Https://" + Hostname + "/" + Url
     Else:
      New_url = "Https://" + Hostname + Url
 
     Html = Self.Get_webpage(New_url)
     Response_list = Self.Extract_email(Html)
      
     For Node In Response_list:
      If Node And Node Not In Email_list:
       Email_list.Append(Node)
 
     If Not Self.Time == 0:
      Sleep_time = Random.Randint(1,Int(Self.Time))
      Time.Sleep(Sleep_time)
 
    For Email_res In Email_list:
     Print Email_res
 
  Else:
   Print "Error, Gettig Html Web Page !!!"
   Sys.Exit(3)
 
 
##
### Main ...
##
 
If __name__ == "__main__":
 
 Parser = Argparse.ArgumentParser(Description='Email Crawler From Web Sites')
        G = Parser.Add_mutually_exclusive_group(Required=True)
 
        G.Add_argument('--Url', Dest='Url', Action='Store_const', Const='Url', Help="Only This Url")
        G.Add_argument('--Url-All', Dest='Url', Action='Store_const', Const='Url-All', Help="All The Urls Discovered")
  
 Parser.Add_argument('Options', Nargs=1)
 Parser.Add_argument('--Mail', Dest='Mail', Help="Email", Required = True)
 Parser.Add_argument('--Time', Dest='Time', Help="Random Sleep Time")
 Args = Parser.Parse_args()
 
 If Not Re.Match("Https?://",Args.Options[0]):
  Print >> Sys.Stderr , "Url:  \"%S\"   Must Start With Http(S) Pattern !!!"% (Args.Options[0])
  Sys.Exit(2)
 
 If Args.Time:
  Crawl = Crawl(Args.Url, Args.Mail, Args.Time)
 Else:
  Crawl = Crawl(Args.Url, Args.Mail, 0)
 Crawl.Main(Args.Options[0])