Intro
This is a PERL script that logs you into Orkut and allows you to scrap yiur friends. Following is the program and beneath it lies the manual to use the program. I assume that you already have PERL installed on your system with the required modules:
Program#! /usr/bin/perl -w
use WWW::Mechanize;
use HTTP::Cookies;
use HTTP::Request::Common;
use subs qw(print_c login logout home grab proces scrap);
#autoflush STDOUT 1;
printf ("%45s","Command Line Orkut\n");
printf ("%50s","By http://digitalpbk.blogspot.com\n");
#inits
$cj=HTTP::Cookies->new(file => "cookie.jar",autosave=>1,ignore_discard=>1);
$mech = WWW::Mechanize->new(cookie_jar => $cj);
@prc = ("\n","[FAILED]","[ OK ]\n");
#main loop
print_c;
while(<STDIN>)
{
chomp;
@args = split(/ /);
if(@args)
{
exit 0 if($args[0] eq "exit" || $args[0] eq "q");
if($args[0] eq "login") {login(@args);}
elsif($args[0] eq "home") {home(@args);}
elsif($args[0] eq "logout") {logout(@args);}
elsif($args[0] eq "grab") {grab(@args);}
elsif($args[0] eq "process") {proces(@args);}
elsif($args[0] eq "scrap") {scrap(@args);}
elsif($args[0] eq "populate") {populate(@args);}
elsif($args[0] eq "captchaget") {captchaget(@args);}
elsif($args[0] eq "clear") {system("clear");}
print "\n";
}
print_c;
}
exit 0;
sub print_c
{
print "";
print "> ";
print "";
}
sub login
{
print "\nGmail iD : ";
$email = <STDIN>;
print "Password : ";
$pass = <STDIN>;
print $prc[0];
chomp $email;chomp $pass;
RELOGIN:
for($i=3; $i>=0;$i--)
{
printf("%-60s","GET /Home.aspx");
$mech->get("http://www.orkut.com/Home.aspx");
last if($mech->success());
printf("%10s",$prc[1]);
print " Retry (",$i,")".$prc[0] if($i);
}
return if($i<=0);
print $prc[2];
$cnt = $mech->response->as_string;
$cnt =~ s/\n|\s+/ /g;
if($mech->title =~ m/orkut.*home/i)
{
print "\nAlready Logged In",$prc[0];
$cnt =~ m/<b>(.*)\@gmail.com<\/b>/;
print "\nLogout $1?[n] : ";
$com=<STDIN>;chomp $com;
if($com eq "y")
{
logout;
goto RELOGIN;
}
else
{
return;
}
}
$cnt = $mech->response->as_string;
$cnt =~ s/\n|\s+/ /g;
printf("%-60.59s","Parsing for Login Page ");
#print $cnts;
if($cnt !~ m/id='liframe'.*?src='(.*)'/)
{
printf("%10s",$prc[1]);
print " Login page URL Not Found!\nTry Again OR Update the script! ".$prc[0];
return;
}
print $prc[2];
$url = $1;
$j=3;
REDO:
for($i=3;$i>=0;$i--)
{
printf("%-60.59s","GET $url");
$mech->get($url);
last if($mech->success());
printf("%10s",$prc[1]);
print " Retry (",$i,")".$prc[0] if($i);
}
return if($i<=0);
print $prc[2];
$cnt = $mech->response->as_string;
$cnt =~ s/\n|\s+/ /g;
$mech->form_number(1);
$mech->field("Email",$email."\@gmail.com");
$mech->field("Passwd",$pass);
printf("%-60.59s","Logging In ... ");
$mech->click("null");
$j--;
if($j && !$mech->success())
{
printf("%10s\n",$prc[1]);
goto REDO;
}
return unless($j);
$cnt = $mech->response->as_string;
$cnt =~ s/\n|\s+/ /g;
if(!$mech->find_link(text => "click here to continue"))
{
printf("%10s",$prc[1]);
print "\nWrong Usename or Password!",$prc[0];
return;
}
print $prc[2];
for($i=3;$i>=0;$i--)
{
printf("%-60.59s","Continuing ...");
$mech->follow_link(text => "click here to continue");
last if($mech->success());
printf("%10s",$prc[1]);
print " Retry (",$i,")".$prc[0] if($i);
}
return if($i<=0);
print $prc[2];
printf("%-60s","Parsing REDIRECT URL");
$cnt = $mech->response->as_string;
$cnt =~ s/\n|\s+/ /g;
if($cnt !~ m/location.replace\("(.*)"\)/)
{
printf("%10s",$prc[1]);
print "\nRedirect script missing!",$prc[0];
return;
}
$url = $1;
$url =~ s/\\u003d/=/g;
print $prc[2];
for($i=3;$i>=0;$i--)
{
printf("%-60.59s","GET $url");
$mech->get($url);
last if($mech->success());
printf("%10s",$prc[1]);
print " Retry (",$i,")".$prc[0] if($i);
}
return if($i<=0);
print $prc[2];
print "Logged In!";
#for($i=3; $i>=0;$i--)
#{
# printf("\n%-60s","GET /Home.aspx");
# $mech->get("http://www.orkut.com/Home.aspx");
# last if($mech->success());
#
# printf("%10s",$prc[1]);
# print " Retry (",$i,")".$prc[0] if($i);
#}
#return if($i<=0);
#print $prc[2];
}
sub logout
{
printf("%-60s","Parsing Logout");
if(!$mech->find_link(text => "Logout"))
{
printf("%10s",$prc[1]);
print "\nNot Logged In?",$prc[0];
return;
}
print $prc[2];
for($i=3;$i>=0;$i--)
{
printf("%-60.59s","Logging Out ...");
$mech->follow_link(text => "Logout");
last if($mech->success());
printf("%10s",$prc[1]);
print " Retry (",$i,")".$prc[0] if($i);
}
return if($i<=0);
print $prc[2];
}
sub home
{
REHOME:
for($i=3; $i>=0;$i--)
{
printf("%-60s","GET /Home.aspx");
$mech->get("http://www.orkut.com/Home.aspx");
last if($mech->success());
printf("%10s",$prc[1]);
print " Retry (",$i,")".$prc[0] if($i);
}
if($i<=0)
{
print $mech->response->as_string;
return;
}
print $prc[2];
if($mech->title !~ m/orkut.*home/i)
{
print $mech->response->as_string;
print "Not Logged In!",$prc[0];
print "\nLogin? [y] : ";
$com=<STDIN>;chomp $com;
if(not($com eq "n"))
{
login;
goto REHOME;
}
else
{
return;
}
}
#$mech->save_content("home.html");
$cnt = $mech->response->as_string;
$cnt =~ s/\n|\s+/ /g;
if($cnt =~ m/You are connected to <b>(.*)<\/b> people through <b>(.*)<\/b> friends./){
printf("\n%-20s: %0s (%0s)","Friends",$2,$1);}
if($cnt =~ m/([0-9]+) fans/){
printf("\n%-20s: %0s","Fans",$1);}
if($cnt =~ m/<b>([0-9]+)<\/b> scraps/i){
printf("\n%-20s: %0s","Scraps",$1);}
$cnt =~ m/my friends/g;
print "\nRecent : ";
while($cnt =~ m/Profile\.aspx\?uid=(.*?)">(<b>)*([^<]+)(<\/b>)*<\/a>/g)
{
print "\n\t$3";
}
}
sub grab_community
{
$comid = shift;
unless($file = shift)
{
print "\nFile to store : ";
$file = <STDIN>;
chomp $file;
}
$url = "/CommMembers.aspx?cmm=$comid";
for($i=3; $i>=0;$i--)
{
printf("%-60s","GET $url");
$mech->get("http://www.orkut.com$url");
last if($mech->success());
printf("%10s",$prc[1]);
print " Retry (",$i,")".$prc[0] if($i);
}
return 0 if($i<=0);
print $prc[2];
if($mech->title !~ m/orkut.*Community.*Members/)
{
print "Unexpected Page ! : ",$mech->title;
return 0;
}
$cnt = $mech->response->as_string;
#$cnt =~ m/showing <b>1-15<\/b> of (.*?)<\/b>/g;
#print " $1";
open APP,">$file";
$grabed=0;
printf("%-25s","Grabbed: $grabed ");
for($page=2;;$page++)
{
while($cnt =~ m/Profile\.aspx\?uid=(.*?)">(<b>)*([^<]+)(<\/b>)*<\/a>/g)
{
$grabed++;
print APP "\n$1>$3";
}
print "\e[25D";
printf("%-25s","Grabbed: $grabed ");
sleep(3);
if($mech->find_link(text_regex => qr/next/i))
{
$mech->follow_link(text_regex => qr/next/i);
}
else
{
last;
}
last if(!$mech->success());
$cnt = $mech->response->as_string;
}
print "\nSaved to \"$file\"".$prc[0];
close APP;
return $grabed;
}
sub grab_flist
{
$comid = shift;
unless($file = shift)
{
print "\nFile to store : ";
$file = <STDIN>;
chomp $file;
}
$url = "/FriendsList.aspx?uid=$comid";
for($i=3; $i>=0;$i--)
{
printf("%-60s","GET $url");
$mech->get("http://www.orkut.com$url");
last if($mech->success());
printf("%10s",$prc[1]);
print " Retry (",$i,")".$prc[0] if($i);
}
return 0 if($i<=0);
print $prc[2];
if($mech->title !~ m/orkut - (.*) Friends/)
{
print "Unexpected Page ! : ",$mech->title;
return 0;
}
print "$1 Friends : ".$prc[0];
$cnt = $mech->response->as_string;
#$cnt =~ m/showing <b>1-15<\/b> of (.*?)<\/b>/g;
#print " $1";
#$file =~ s/>//;
open APP,">$file";
$grabed=0;
printf("%-25s","Grabbed: $grabed ");
for($page=2;;$page++)
{
$cnt =~ m/Profile\.aspx\?uid=(.*?)">(<b>)*([^<]+)(<\/b>)*<\/a>/g;
while($cnt =~ m/Profile\.aspx\?uid=(.*?)">(<b>)*([^<]+)(<\/b>)*<\/a>/g)
{
$grabed++;
print APP "\n$1>$3";
}
print "\e[25D";
printf("%-25s","Grabbed: $grabed ");
sleep(3);
if($mech->find_link(text=> $page))
{
$mech->follow_link(text => $page);
}
else
{
last;
}
last if(!$mech->success());
$cnt = $mech->response->as_string;
}
print "\nSaved to \"$file\"".$prc[0];
close APP;
return $grabed;
}
sub grab_wild
{
$limit = shift;
$got = 0;
my $file;
unless($file=shift)
{
print "\nFile to store : ";
$file = <STDIN>;
chomp $file;
}
print "\nCommunity ID : ";
$comid = <STDIN>;chomp $comid;
open APP4, ">>$file";
print APP4 "\n<comment>CommMem $comid</comment>";
close APP4;
if($comid)
{
$got = grab_community($comid,">$file");
}
else
{
print "\nFriend ID : ";
$comid=<STDIN>;chomp $comid;
print $comid;
return 0 unless($comid);
open APP3, ">>$file";
print APP3 "\n<comment>FriendOf $comid</comment>";
close APP3;
$got = grab_flist($comid,">$file");
}
return 0 unless($got);
$offset=0;
$visits=0;
RESPIDER:
$file =~ s/>//;
open DLL, "$file";
@uids = <DLL>;
close DLL;
$cnt = join("\n",@uids);
$cnt =~ s/<comment>.*?<\/comment>//g;
@uids = split(/\n/,$cnt);
@uids = @uids[$offset..$#uids];
foreach $userid (@uids)
{
if($userid =~ m/([0-9]+)>/)
{
$file =~ s/>//;
if(open APP2, ">>$file")
{
print APP2 "\n<comment>FriendOf $1</comment>";
close APP2;
}
else {print $!," $file";exit}
$got+= grab_flist($1,">$file");
$visits++;
print " Got $got ".$prc[0];
last if($limit < $got);
}
}
if($limit > $got)
{
$offset = $#uids + 1;
goto RESPIDER;
}
print "\n Spider Results : ".$prc[0];
printf("%-30s : %0s\n","Indexed",$got);
printf("%-30s : %0s\n","Spidered",$visits);
print " Tip : Dont forget to simplify the uid file ".$prc[0];
}
sub grab
{
shift;
$what = shift;
$where = shift;
$file = shift;
if(!($what && $where))
{
print "\nArguments missing".$prc[0];
return;
}
if(lc($what) eq "comm" || lc($what) eq "community") {grab_community($where,$file);}
elsif(lc($what) eq "flist" || lc($what) eq "friendlist") {grab_flist($where,$file);}
elsif(lc($what) eq "wild") {grab_wild($where,$file);}
}
sub process_uids
{
my $file;
unless($file=shift)
{
print "\nFile to read : ";
$file = <STDIN>;
chomp $file;
}
open DLL, "$file";
@uids = <DLL>;
close DLL;
$cnt = join("\n",@uids);
$cnt =~ s/<comment>.*?<\/comment>\n//g;
$cnt =~ s/[\n]+/>/g;
$cnt =~ s/>//;
%hc = split(/>/,$cnt);
$file .= ".s";
if($dest = shift) {$file=$dest;}
open DLL,">$file" or die("$!");
$inx=0;
foreach $key (sort keys %hc)
{
$val = $hc{$key};
$inx++;
printf("%6d %28s %0s\n",$inx,"$key","$val");
print DLL "$key>$val>";
}
close DLL;
}
sub proces
{
shift;
$what = shift;
$file = shift;
$extra = shift;
unless($what)
{
print "\nArguments missing".$prc[0];
return;
}
if(lc($what) eq "uids") {process_uids($file,$extra); }
}
sub scrap
{
shift;
$pat = shift;
unless($source=shift)
{
print "\nFile to read : ";
$source = <STDIN>;
chomp $source;
}
if(!open FILE,"$source")
{
print " File not found!".$prc[0];
return;
}
@contents = <FILE>;
close FILE;
chomp @contents;
$cnts = join("",@contents);
$cnts =~ s/<//g;
%hc = split(/>/,$cnts);
$no = 1;
$scrapall=0;
$sc_start=0;
$sc_end=0;
@fkeys=();
$pat = ".*" unless($pat);
foreach $key (sort keys %hc)
{
$val = $hc{$key};
if($val =~ m/$pat/i)
{
printf("%6d %28s %0s\n",$no,"$key","$val");
$no++;
push @fkeys, $key;
}
}
if($no==0)
{
print " Friend Not found !".$prc[0];
}
print "Enter Friend # : ";
$myc = <STDIN>;
chomp $myc;
#todos ...
if($myc =~ m/([0-9]+)-([0-9]+)/)
{
$scrapall=1;
$myc=$sc_start=$1;
$sc_end=$2;
}
if($myc > $no)
{
print "Invalid Response!!!".$prc[0];return;
}
print "Enter Scrap Text : ";
$sctext = <STDIN>;
$sctext =~ s/\\n/\n/g;
#PS: Please do not remove the following if you really like this .... :)
#Please post a link to my website http://digitalpbk.blogspot.com
#thank you :)
$sctext = $sctext."\n[red](Powered by [blue]digitalpbk[/blue].blogspot.com)";
chomp $sctext;
SCRAPNEXT:
$friendid = $fkeys[$myc-1];
print " Scrapping $myc $friendid [$hc{$friendid}]".$prc[0];
sleep(4);
$url = "/Scrapbook.aspx?uid=$friendid";
for($i=3; $i>=0;$i--)
{
printf("%-60s","GET $url");
$mech->get("http://www.orkut.com$url");
last if($mech->success());
printf("%10s",$prc[1]);
print " Retry (",$i,")".$prc[0] if($i);
}
return 0 if($i<=0);
print $prc[2];
$cnt= $mech->response->as_string;
$cnt =~ s/\n|\s+/ /g;
if(($mech->title()) =~ m/orkut.*login/i)
{
print "Not Logged In!",$prc[0];
print "\nLogin? [y] : ";
$com=<STDIN>;chomp $com;
if(not($com eq "n"))
{
login;
goto SCRAPNEXT;
}
else
{
return;
}
sleep(3);
goto SCRAPNEXT;
}
if($cnt =~ m/"POST_TOKEN" value="(.*?)"/){
$post_token = $1;}
#print $post_token," ";
if($cnt =~ m/"signature" value="(.*?)"/){
$signature=$1;}
#print $signature;
sleep(3);
for($i=3;$i>=0;$i--)
{
printf( "%-60s","POST scrap");
#$mech->agent_alias("Linux Mozilla");
$mech->request(POST "http://www.orkut.com$url",["POST_TOKEN"=>$post_token,"signature"=>$signature,"scrapText"=>$sctext,"Action.writeScrapBasic"=>"Submit+Query"]);
last if($mech->success());
printf("%10s",$prc[1]);
print " Retry (",$i,")".$prc[0] if($i);
}
return 0 if($i<=0);
print $prc[2];
if($scrapall && $myc < $sc_end)
{
$myc++;
goto SCRAPNEXT;
}
print " Done.".$prc[0];
}
sub populate
{
shift;
$pat = shift;
unless($source=shift)
{
print "\nFile to read : ";
$source = <STDIN>;
chomp $source;
}
if(!open FILE,"$source")
{
print " File not found!".$prc[0];
return;
}
@contents = <FILE>;
close FILE;
chomp @contents;
$cnts = join("",@contents);
$cnts =~ s/<//g;
%hc = split(/>/,$cnts);
$no = 1;
$scrapall=0;
$sc_start=0;
$sc_end=0;
@fkeys=();
$pat = ".*" unless($pat);
foreach $key (sort keys %hc)
{
$val = $hc{$key};
if($val =~ m/$pat/i)
{
printf("%6d %28s %0s\n",$no,"$key","$val");
$no++;
push @fkeys, $key;
}
}
if($no==0)
{
print " Friend Not found !".$prc[0];
}
print "Enter Friend # : ";
$myc = <STDIN>;
chomp $myc;
#todos ...
if($myc =~ m/([0-9]+)-([0-9]+)/)
{
$scrapall=1;
$myc=$sc_start=$1;
$sc_end=$2;
}
if($myc > $no)
{
print "Invalid Response!!!".$prc[0];return;
}
ADDNEXT:
$friendid = $fkeys[$myc-1];
print " Adding $myc $friendid [$hc{$friendid}]".$prc[0];
sleep(4);
$url = "/FriendAdd.aspx?uid=$friendid";
for($i=3; $i>=0;$i--)
{
printf("%-60s","GET $url");
$mech->get("http://www.orkut.com$url");
last if($mech->success());
printf("%10s",$prc[1]);
print " Retry (",$i,")".$prc[0] if($i);
}
return 0 if($i<=0);
print $prc[2];
$cnt= $mech->response->as_string;
$cnt =~ s/\n|\s+/ /g;
if(($mech->title()) =~ m/orkut.*login/i)
{
print "Not Logged In!",$prc[0];
print "\nLogin? [y] : ";
$com=<STDIN>;chomp $com;
if(not($com eq "n"))
{
login;
goto ADDNEXT;
}
else
{
return;
}
sleep(3);
goto ADDNEXT;
}
if($cnt =~ m/"POST_TOKEN" value="(.*?)"/){
$post_token = $1;}
#print $post_token," ";
if($cnt =~ m/"signature" value="(.*?)"/){
$signature=$1;}
#print $signature;
sleep(3);
for($i=3;$i>=0;$i--)
{
printf( "%-60s","POST add");
#$mech->agent_alias("Linux Mozilla");
$mech->request(POST "http://www.orkut.com$url",["POST_TOKEN"=>$post_token,"signature"=>$signature,"level"=>"3","Action.yes"=>"Submit+Query"]);
last if($mech->success());
printf("%10s",$prc[1]);
print " Retry (",$i,")".$prc[0] if($i);
}
return 0 if($i<=0);
print $prc[2];
if($scrapall && $myc < $sc_end)
{
$myc++;
goto ADDNEXT;
}
print " Done.".$prc[0];
}
sub captchaget
{
$mech->request(GET "http://www.orkut.com/CaptchaImage.aspx");
open JPEG, ">captcha.jpg";
print JPEG $mech->response->content;
close JPEG;
}
Installing and ExecutingTo Install Copy the above full program. Paste it in a new text file and rename it as
orkut.pl.
To Execute the program open a terminal / DOS Prompt and navigate to the folder where you have the
orkut.pl.
Then type
perl orkut.pl
Getting StartedOnce you execute the program you get a screen as follows
Command Line Orkut
By http://digitalpbk.blogspot.com
>
Quick Start Scrap all your friends
Command Line Orkut
By http://digitalpbk.blogspot.com
> login
> home
> grab flist [uid here Profile.aspx?uid=some numbers right? copy that numbers here]
Enter File : myfriends
> process uids myfriends
> scrap
Enter File : myfreinds.s
1
2
3
4
.
.
.
N
Enter Friend Number: 1-N
Enter Scrap text : This is coooool.
Avaliable commands- login: This command is used to Login into Orkut.com, you will have to enter a valid Username and Password to enter the site. If someone is already logged in the command asks your confirmation to logout that person and log you in or to continue with the existing.
> login
Gmail ID : example@example.com
Password : Password
GET /Home.aspx [ OK ]
Parsing for Login Page [ OK ]
GET https://www.google.com/accounts/ServiceLoginBox?service [ OK ]
Logging In ... [ OK ]
Continuing ... [ OK ]
Parsing REDIRECT URL [ OK ]
GET http://www.orkut.com/RedirLogin.aspx?msg=0&page=http%3A [ OK ]
Logged In!
- home: This command parses the Home.aspx file and gives you a summary of the page as shown below. If you are not logged in the command executes the login and continues if successful.
> home
GET /Home.aspx [ OK ]
Friends : 291 (57,431,788)
Fans : 138
Scraps : 4
Recent :
abcd (305)
xyz (391)
def (151)
I maybe wrong... (301)
fghhh (376)
someone (289)
exmple (673)
real (679)
The number in brackets in friends indicate the total number of people in orkut.
Recent shows the recently online friends on orkut. All others mean what they stand for.
- grab what from [to] : Before you can start scrapping or do anything further, you must first build a database of friends or list of orkut id's. The Grab function is used to make the database. It takes two parameters and an optional third parameter:
- what where: can take values [comm or community | flist or friendlist | wild ]
comm or community : indicates that the list of friends is going to be grabbed from a community. In this case the from specifies a community id. (Community.aspx?cmm=ID)
flist or friendlist: indicates that the list of friends is going to be from a friend's friends. In this case the from specifies the Orkut uid (FriendsList.aspx?uid=ID)
wild : this is a combo of the above and grabs as much people specified by second parameter.
- to : is an optional parameter that specifies the file to store the grabbed id's. If this parameter is left out, you will be asked to enter the file. If the file exists the new data is appended to the old file.
- process uids : The grabbed ids by grab is not well formatted and may contain duplicates the process uids command formats the database and makes a final file. This command asks for the source file and makes a new destination file named by appending a .s extension to the original file. The formatted database is displayed.
- scrap [filter] [source db] : is used to scrap multiple people. It takes 2 optional arguments.
1. Filter : filters the source db according to the name. If skiped all persons in the database will be marked for scrapping.
2. Source DB : The .s file that is required. If skiped you will be asked to enter location.
> scrap just
File to read : sample.id.s
1 12312312313123123123 Just for keepin the communities
Enter Friend # : 1
Enter Scrap Text : hii \n how are you?
Scrapping 1 12312312313123123123 [Just for keepin the communities]
GET /Scrapbook.aspx?uid=12312312313123123123 [ OK ]
POST scrap [FAILED] Retry (3)
POST scrap [ OK ]
Done.
Enter Friend #: Takes a number or a format like X-X where X is a number. When X-X format is given all people between those two numbers will be marked for scrapping.
Enter Scrap Text: The scrap text to be entered. To add new lines type \n and the scrap will have newlines when scrapped.
- populate [Filter] [Source DB]: Same as scrap but this time its used to add the specified people as your friends.
- captchaget : Just to read a Captcha and store the image as captcha.jpg
LicenseYou are free to modify and edit by retaining a link or reference to this site.
There is no warranty what so ever. Any incidents of Orkut Banning you, or similar events shall not be my responsibility. Provided solely for education purpose. Any damage or inconvenience caused by the script is deeply regretted.You have been warned.
Winding up...I know this manual was too brief. I have tried as much to describe the Script. You will have confusions and doubts regarding the usage so please post your questions as a comment. I will be more than glad to answer them. If you really loved it or got it working or was helpful to you let me know. And dont forget to place a link to this page, if you are submitting to another site or forum.
Thanx Happy Orkutting...
:)
PS: If you noticed the Perl script colour coded, and like that
check this out.
