joe....
the following sample perl might be usefull... the pieces of code
might/should help... i'm including the entire apps so you can get a feel for
what they're doing.. the 1st app gets into the utaustin.edu site and
extracts information. this site requires the use of a user/passwd..
the code is ugly, as it has comments, etc.. and can easily be tightened, but
it gives you an idea of what's going on...
#############################################################
#
# utaustin.pl. test perl app to extract/parse class schedule
# from the utaustin.edu registrar site...
#
#
#
#############################################################
#!/usr/bin/perl -w
use HTML::TreeBuilder;
use LWP::UserAgent;
use WWW::Mechanize;
my $b = WWW::Mechanize->new();
$ua = new LWP::UserAgent;
$ua->timeout(30);
$ua->agent("AgentName/0.1 " . $ua->agent);
my $cstr;
#
# get the top level university class site
#
my $base_url = "http://www.utexas.edu/student/registrar/schedules/";
my $req = new HTTP::Request GET => $base_url;
$req->content_type('application/x-www-form-urlencoded');
my $res = $ua->request($req);
my $q1c = $res->content;
print $q1c;
# get 046/049/etc...
@_sessions = &getsessions($res->content);
#
# we'll parse the returned contents and use them to get to the
# next page...
#
$sched_url = $base_url . "046/";
$req = new HTTP::Request GET => $sched_url;
$res = $ua->request($req);
$q1c = $res->content;
print $q1c;
$ut_tree = HTML::TreeBuilder->new_from_content($res->content); # empty
tree
# should be only one.. need to get the schedules..
@_sem_td = $ut_tree->look_down("_tag"=>"td", "bgcolor"=>"#eeeeee");
@_sem_a = $_sem_td[0]->look_down("_tag"=>"a");
$sem_page_url = $_sem_a[0]->attr('href');
print "href# $sem_page_url\n";
#
# now it get's tricky.. we parse the returned contents and use
# them to get to the next page. however, the next page is now the
# ut logon page.
#
# this requires that we get the returned results of the logon page
# and that we fill in the user/password...
#
# we should probably use mechanize.. if it works..
#
#Configuration:#########################
#my
$ut_url="https://utdirect.utexas.edu/registrar/clavnew/clav3.WBX?s_semester=
su2004";
my $ut_url=$sem_page_url;
my $username="foo"; <<<<<<<<<< these would be your own!!!!!!! >>>>>>>>
my $password="cat"; <<<<<<<<<< these would be your own!!!!!!! >>>>>>>>
#End Configuration######################
use Crypt::SSLeay;
my $b = WWW::Mechanize->new();
my $agent = WWW::Mechanize->new();
# Retrieve main page
$agent->get($ut_url);
my $login = $agent->form_name('logonform2');
if ( ! $login ) {
warn "Nothing came back";
exit;
}
$agent->set_fields('LOGON' => $username,
'PASSWORDS' => $password
);
$agent->click_button('value' => 'Log In');
print "qqqqqqqq..\n";
# for now, we assume that this is the returned javascript dialog...
# it should be checked.. to see if it really is
# the app should include error checking...
#
print $agent->content();
#assuming that we got a good dialog.. means the login
#was good, go ahead and resend the registration page again...
#this gets the app to the course schedule page..
# now we begin to extract the information
# !!
#
$agent->get($ut_url);
print "7777777777777777777777..\n\n\n\n";
print $agent->content();
open(F, ">out.html");
print F $agent->content();
close(F);
$filename = "out.html";
#
# go ahead and get the levels (grad/under/etc...
# and the list of depts...
#
@_level_array = &getlevels($filename);
@_dept_array = &getdepts($filename);
#
# begin to parse the top section to get a list of the classes..
#
my
$ut_base_class_url="https://utdirect.utexas.edu/registrar/clavnew/clav3_resu
lts.wb";
my $dept = "?c-key=";
my $class_str =
"&c-crs=%20&c-unique-single=&c-unique-begin=&c-unique-end=&c-cmd=lc";
my $semester = "&c-sem=";
my $level = "&c-sub=";
####
#test vars.. these vars will be in a loop..
#####
my $semester_var = "su2004";
my $level_var = "l";
my $dept_var ="ACC";
#
# start the loop for depts/levels
#
#
print "level = ". scalar @_level_array ."\n";
print "dept = " . scalar @_dept_array ."\n";
$filename = "out.html";
foreach $_lcnt (@_level_array)
{
foreach $_dcnt (@_dept_array)
{
#####
#
# the url--> ut_base_class + $dept.$dept_var + $class_str +
# $semester + $semester_var + $level + $level_var
#
######
$class_url = $class_url . $ut_base_class_url;
$class_url = $class_url . $dept. $_dcnt;
$class_url = $class_url . $class_str;
$class_url = $class_url . $semester .$semester_var;
$class_url = $class_url . $level . $_lcnt;
print "$class_url \n";
$agent->get($class_url);
print "5555555555555555..\n\n\n\n";
print $agent->content();
open(F, ">$filename");
print F $agent->content();
close(F);
@_class_array = &getclasses($filename);
$class_url = "";
}
}
print "we're here...\n";
die;
#################################
#
#
#################################
sub getsessions
{
my ($res) = @_;
my $ut_tree = HTML::TreeBuilder->new_from_content($res); # empty tree
# should be only one.. need to get the schedules..
@_semester_tbl = $ut_tree->look_down("_tag"=>"table", "class"=>"tbg");
print "tbl ".$_semester_tbl[0]->dump()."\n";
@_semester_td = $_semester_tbl[0]->look_down("_tag"=>"td",
"align"=>"center");
@_semester_a = $_semester_td[0]->look_down("_tag"=>"a");
print "<a ".$_semester_a[1]->dump()."\n";
$_ndx=0;
foreach $a (@_semester_a)
{
$_semester[$_ndx++] = $a->attr('href');
}
#quickly strip extraneous chars...
for ($i=0;$i<$_ndx;$i++)
{
$_semester[$i] =~ tr:\.\/::d;
}
return(@_semester);
}
#
# get the class information from the given page content
# return the class_array/class_hash
#
sub getclasses
{
my ($filename) = @_;
my @level_array;
my $tree = HTML::TreeBuilder->new(); # empty tree
# add a "," to aid in processing...
#
#<p class="tbtx"> --> '<p class="tbtx">,'<<<<<
#
$_arg = "perl -i -p -e 's:\<p class\=\"tbtx\"\>:\<p class\=\"tbtx\"\>,:g;'
$filename";
system($_arg);
$tree->parse_file($filename);
@tree_test = $tree->look_down("_tag"=>"table", "cellpadding"=>"2",
"bgcolor"=>"#cccccc");
@tbtx_tree = $tree_test[0]->look_down("_tag"=>"tr");
#iterate through the list...
#skip the 1st one.. it's the header
#get the class name/section information
foreach $q (@tbtx_tree)
{
#print "tree tbtx = ". $q->as_HTML() ."\n";
# parse the html for hdr/name/section...
if ($q->as_HTML =~ /class\=\"tbh\"/)
{
# do nothing.. go ahead and skip
}
elsif($q->as_HTML() =~ /class\=\"em\"/)
{
$q1 = $q->as_HTML();
$q1 =~ /em\"\>([^\<]+)\<[^\>]+\>([^\<]+)/;
$classnumber = $1;
$classname = $2;
$classnumber =~ s/ //;
}
elsif($q->as_HTML() =~ /\<a href\=\"clavcdet/)
{
$q1 = $q->as_text;
print "number = $classnumber name = $classname\n";
print "q = $q1\n";
}
}
}
# }
# get the levels (under/grad/etc...)
# return the level_array
#
sub getlevels
{
my ($filename) = @_;
my @level_array;
my $tree = HTML::TreeBuilder->new(); # empty tree
$tree->parse_file($filename);
@tree_test = $tree->look_down("_tag"=>"input", "type"=>"radio",
"name"=>"s_course_level");
my $_ndx=0;
foreach $a (@tree_test)
{
$level_array[$_ndx++]=$a->attr('value');
}
return(@level_array);
}
#
# get the depts (/etc...)
# return the depts_array
#
sub getdepts
{
my ($filename) = @_;
my @dept_array;
my $tree = HTML::TreeBuilder->new(); # empty tree
# prepare file for use
#
# we insert a "," to aid in data extraction
#
#perl -i -p -e 's///g;' out.html;
#<p class="tbtx"> ==> '<p class="tbtx">,'
$_arg = "perl -i -p -e 's/\<p class\=\"tbtx\"\>/\<p class\=\"tbtx\"\>,/g;'
". $filename;
system($_arg);
$tree->parse_file($filename);
@tree_test = $tree->look_down("_tag"=>"select",
"name"=>"s_dept_abbr_select", "size"=>"1");
@option_tree = $tree_test[0]->look_down("_tag"=>"option");
my $_ndx=0;
foreach $a (@option_tree)
{
$dept_array[$_ndx]=$a->attr('value');
$dept_array[$_ndx]=~ s: :%20:g; # sub/replace for " "s...
print "-----> $dept_array[$_ndx] \n";
$_ndx++;
}
return(@dept_array);
}
=========================================================================
=========================================================================
=========================================================================
=========================================================================
this is a cookie app......
#############################################################
#
# auburn.pl. test perl app to extract/parse class
# schedule from the auburn.edu
# registrar site...
#
#GET /ia-bin/tsrvweb.exe?
#
#
# todo.. need to create the getinfo routine to parse the
# class information, and write it out
#
#############################################################
#!/usr/bin/perl -w
use strict;
use HTML::TreeBuilder;
use LWP::UserAgent;
use URI::Escape;
use WWW::Mechanize;
use LWP::Simple;
use URI::URL;
use HTTP::Cookies;
#
# get the top level university class site
#
my $registrar_url = "https://tideguide.ua.edu/";
my $host_url = "https://oasis.auburn.edu";
my $base_url = "https://oasis.auburn.edu/ia-bin/tsrvweb.exe?";
my $semester_query =
"tserve_trans_config=rclsterm-l.cfg&tserve_host_code=HostZero&tserve_tiphost
_code=TipZero";
my $dept_url1 =
"tserve_host_code=HostZero&tserve_tiphost_code=TipZero&WID=W&ReqNum=1&tserve
_tip_write=%7C%7CWID%7CTerm%7CReqNum&tserve_trans_config=rclsavl1-l.cfg&Term
";
# go ahead and get the selection page within the frame..
# use www::machanize
my $agent = WWW::Mechanize->new();
$agent->cookie_jar({});
$agent->get($base_url.$semester_query);
#
# get term
# get subject/dept
# get course
# get class/sections...
#
#
#
#
# iterate through the terms/depts/classes
my ($semester_val, $semester_name, $semester);
my ($dept_val, $dept_name, $dept);
my ($course_val, $course_name, $course);
my $content;
# semester
my ($s, $f) = &getSemesterAttribs($base_url.$semester_query);
my (@semesters) = @$s;
my (@FormAttribs) = @$f;
foreach $semester (@semesters)
{
$semester_name = $semester->{'name'};
$semester_val = $semester->{'val'};
my $url = $base_url.$semester_query;
# my $dept_url = &getSemesterForm(\$semester_val, [EMAIL PROTECTED],
\$url);
#use dept list
#my ($d, $f1) = &getDeptAttribs($base_url.$dept_url);
my ($d, $f1) =
&getDeptAttribs($base_url.$dept_url1."=".$semester_val);
my @depts = @$d;
my @deptFormAttribs = @$f1;
foreach $dept (@depts)
{
$dept_name = $dept->{'name'};
$dept_val = $dept->{'val'};
#my $durl = $base_url.$dept_url;
my $durl = $base_url.$dept_url1."=".$semester_val;
my $course_url = &getDeptForm(\$dept_val, [EMAIL PROTECTED],
\$durl);
#use course list
my ($d, $f1) = &getCourseAttribs($base_url.$course_url);
my @courses = @$d;
my @courseFormAttribs = @$f1;
foreach $course (@courses)
{
$course_name = $course->{'name'};
$course_val = $course->{'val'};
my $durl = $base_url.$course_url;
my $content = &getCourseForm(\$course_val, [EMAIL PROTECTED],
\$durl);
print "content = $content\n";
print "semester $semester_val dept $dept_val course
$course_val\n";
&getClassInformation($content);
}
}
}
print "we're here...\n";
die;
#################################
#
#
#################################
sub getSemesterAttribs
{
my ($url) = @_;
my (@semesterArray, @nameArray);
$agent->get($url);
my $q1c = $agent->content;
#print "q $q1c\n";
print "semester url $url\n";
my $_tree = HTML::TreeBuilder->new_from_content($agent->content);
#
# get the form
#
my @_form = $_tree->look_down("_tag"=>"Form");
#
# get the semester list information
#
# get the specific "sel"
my @_sel = $_form[0]->look_down("_tag"=>"select", "name"=>"Term");
my @_opt = $_sel[0]->look_down("_tag"=>"option");
my $a;
foreach $a (@_opt)
{
#get the "a" list
my (%semester);
$semester{'val'} = $a->attr('value');
$semester{'name'} = $a->as_text();
push (@semesterArray, \%semester);
}
#
# get the hidden name information for the form
#
# get the specific "input"
my @_in = $_form[0]->look_down("_tag"=>"input", "type"=>"hidden");
my $a;
foreach $a (@_in)
{
#get the "a" list
my (%name);
$name{'val'} = $a->attr('value');
$name{'name'} = $a->attr('name');
push (@nameArray, \%name);
}
return([EMAIL PROTECTED], [EMAIL PROTECTED]);
}
#################################
#
# the auburn semester uses "put" on the form instead of
# "post"... which causes the "mech" object to have
# issues... can't seem to quickly figure out how to
# get around this..so we're going to cheat for now...
#
# come back to this later if we figure out how to use
# "put" as an action method for "mech"...
#
#################################
sub getSemesterForm
{
my ($t, $f, $u) = @_;
my ($term, @FormArray, $url) ;
$term = $$t;
@FormArray = @$f;
$url = $$u;
# $agent->get($url);
#
# use the global agent/cookie for the
# session setup...
my $agent1 = WWW::Mechanize->new() ;
$agent1->get($url);
print "url = $url\n";
my $_form = $agent1->form_number(1);
if (!$_form) {
warn "Nothing came back";
exit;
}
# $agent1->request()->headers->method("POST");
my $tmp;
foreach $tmp (@FormArray)
{
$agent1->field($tmp->{'name'}, $tmp->{'val'});
print "name = ".$tmp->{'name'}." val = ".$tmp->{'val'}."\n";
}
$agent1->field("Term", $term);
print " ...............\n";
$agent1->submit();
print "--+++++ ".$agent1->content(). "\n";
my $url2 = $agent1->response()->request()->content();
print "url = ".$url2."\n";
my $q1 = $url2;
return($url2);
}
#################################
#
#
#################################
sub getDeptAttribs
{
my ($url) = @_;
my (@deptArray, @nameArray);
my $res = $agent->get($url);
# my $req = new HTTP::Request GET => ($url);
# my $res = $ua->request($req);
#my $q1c = $res->content;
my $q1c = $agent->content;
#print "q $q1c\n";
#print "semester url $url\n";
my $_tree = HTML::TreeBuilder->new_from_content($agent->content);
#
# get the form
#
my @_form = $_tree->look_down("_tag"=>"form", "method"=>"post");
#
# get the dept list information
#
# get the specific "sel"
my @_sel = $_form[0]->look_down("_tag"=>"select", "name"=>"Subject");
my @_opt = $_sel[0]->look_down("_tag"=>"option");
my $a;
foreach $a (@_opt)
{
#get the "a" list
my (%dept);
$dept{'val'} = $a->attr('value');
$dept{'name'} = $a->as_text();
push (@deptArray, \%dept);
}
#
# get the hidden name information for the form
#
# get the specific "input"
my @_in = $_form[0]->look_down("_tag"=>"input", "type"=>"hidden");
my $a;
foreach $a (@_in)
{
#get the "a" list
my (%name);
$name{'val'} = $a->attr('value');
$name{'name'} = $a->attr('name');
push (@nameArray, \%name);
}
return([EMAIL PROTECTED], [EMAIL PROTECTED]);
}
#################################
#
#
#################################
sub getDeptForm
{
my ($s, $f, $u) = @_;
my ($subject, @FormArray, $url) ;
$subject = $$s;
@FormArray = @$f;
$url = $$u;
# $req = new HTTP::Request GET => $url;
# $req->content_type('application/x-www-form-urlencoded');
# my $res = $ua->request($req);
# go ahead and get the selection page within the frame..
# use www::machanize
#my $agent = WWW::Mechanize->new();
$agent->get($url);
print "url = $url\n";
my $_form = $agent->form_number(1);
if (!$_form) {
warn "Nothing came back";
exit;
}
my $tmp;
foreach $tmp (@FormArray)
{
$agent->field($tmp->{'name'}, $tmp->{'val'});
}
$agent->field("Subject", $subject);
$agent->submit();
print "-- ".$agent->content(). "\n";
my $url2 = $agent->response()->request()->content();
print "url = ".$url2."\n";
my $q1 = $url2;
return($url2);
}
#################################
#
#
#################################
sub getCourseAttribs
{
my ($url) = @_;
my (@courseArray, @nameArray);
$agent->get($url);
#my $req = new HTTP::Request GET => ($url);
#my $res = $ua->request($req);
#my $q1c = $res->content;
#print "q $q1c\n";
print "semester url $url\n";
my $_tree = HTML::TreeBuilder->new_from_content($agent->content);
#
# get the form
#
my @_form = $_tree->look_down("_tag"=>"form", "method"=>"post");
#
# get the dept list information
#
# get the specific "sel"
my @_sel = $_form[0]->look_down("_tag"=>"select", "name"=>"CourseID");
my @_opt = $_sel[0]->look_down("_tag"=>"option");
my $a;
foreach $a (@_opt)
{
#get the "a" list
my (%course);
$course{'val'} = $a->attr('value');
$course{'name'} = $a->as_text();
push (@courseArray, \%course);
}
#
# get the hidden name information for the form
#
# get the specific "input"
my @_in = $_form[0]->look_down("_tag"=>"input", "type"=>"hidden");
my $a;
foreach $a (@_in)
{
#get the "a" list
my (%name);
$name{'val'} = $a->attr('value');
$name{'name'} = $a->attr('name');
push (@nameArray, \%name);
}
return([EMAIL PROTECTED], [EMAIL PROTECTED]);
}
#################################
#
#
#################################
sub getCourseForm
{
my ($c, $f, $u) = @_;
my ($course, @FormArray, $url) ;
$course = $$c;
@FormArray = @$f;
$url = $$u;
#$agent->get($url);
#$req = new HTTP::Request GET => $url;
#$req->content_type('application/x-www-form-urlencoded');
#my $res = $ua->request($req);
# go ahead and get the selection page within the frame..
# use www::machanize
#my $agent = WWW::Mechanize->new();
my $res = $agent->get($url);
print "url = $url\n";
my $_form = $agent->form_number(1);
if (!$_form) {
warn "Nothing came back";
exit;
}
my $tmp;
foreach $tmp (@FormArray)
{
$agent->field($tmp->{'name'}, $tmp->{'val'});
}
$agent->field("CourseID", $course);
$agent->submit();
print "-- ".$agent->content(). "\n";
my $url2 = $agent->response()->request()->content();
print "url = ".$url2."\n";
my $q1 = $url2;
return($agent->content());
}
#######################
#
#
#######################
sub getClassInformation
{
my (@classlistArray);
my ($content) = @_;
my $_tree = HTML::TreeBuilder->new_from_content($content);
# need to create the page parsing/information gathering...
# functions...
#
# get each class via the "table"
#
my @_tbl = $_tree->look_down("_tag"=>"table", "class"=>"display");
# return if we don't have any class information
if (!$_tbl[0])
{
return();
}
my @_tr = $_tbl[0]->look_down("_tag"=>"tr");
my $table;
my ($section, $session, $course_title, $prof, $date, $time, $course) ;
my $_tmp;
my $i;
#print "tbl dump = ".$_tbl[0]->dump()."\n";
#print "tbl cnt = "[EMAIL PROTECTED]"\n";
# skip the 1st/2nd tr...
for ($i=2;$i<[EMAIL PROTECTED];$i++)
{
my @_td = $_tr[$i]->look_down("_tag"=>"td");
#print "tr dump = ".$_tr[$i]->dump()."\n";
#print "tr cnt = "[EMAIL PROTECTED]"\n";
if($_td[0])
{
$section = $_td[0]->as_text();
}
if($_td[1])
{
$session = $_td[1]->as_text();
}
if($_td[2])
{
$course_title = $_td[2]->as_text();
}
if($_td[7])
{
$date = $_td[7]->as_text();
}
if($_td[8])
{
$time = $_td[8]->as_text();
}
if($_td[11])
{
$prof = $_td[11]->as_text();
}
print "section = $section \n title = $course_title\n";
}
}
#
# extracts the content from the class/section page for
# the given class
#
# basic flow...
# @td = list of ->
# <<TD height="30" rowspan="2" class="text8" valign="top"
align="left">
#
# foreach $a (td)
#
# @td_ = $a->look(td)
#
# iterate through each td_ array and get the items...
#
#
sub extractContent
{
my ($res) = @_;
my ($a);
print "inside ex...\n";
print "res = $res\n";
#die;
my $_tree = HTML::TreeBuilder->new_from_content($res);
my @_td = $_tree->look_down("_tag"=>"td", "height"=>"30",
"class"=>"text8", "align"=>"left");
print "td count = "[EMAIL PROTECTED]"\n";
my $b;
my $name;
for $a (@_td)
{
print "course name ".$a->as_text()."\n"; #class/course name
$b = $a->right();
print "section ".$b->as_text()."\n"; #section
$b = $b->right();
print "course # ".$b->as_text()."\n"; #course #
$b = $b->right();
print "name ".$b->as_text()."\n"; #class name
$b = $b->right();
print "prof ".$b->as_text()."\n"; #prof
$b = $b->right(); #seats
$b = $b->right(); #free
$b = $b->right(); #bldg
$b = $b->right(); #room
$b = $b->right(); #date
print "date ".$b->as_text()."\n"; #date
$b = $b->right(); #start
print "starttime ".$b->as_text()."\n"; #starttime
#die;
}
#die;
}
good luck... hope this helps!!!!
-----Original Message-----
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]
Sent: Monday, August 23, 2004 1:49 AM
To: [EMAIL PROTECTED]
Subject: LWP::UserAgent and cookie_jar
I am trying to use LWP::UserAgent and cookie_jar, obviously according to the
subject of this email.
Anyhow, I cannot get my code to work, can someone look at it and tell me if
I am just using it wrong?
I'll show my code and the response I get...
I would really appreciate any help someone can offer.
Code: (Of course I changed all real domains and user/membership info...)
my $ua = LWP::UserAgent->new;
$ua->agent("Mozilla/8.0"); # pretend we are very capable browser
$ua->requests_redirectable;
$ua->cookie_jar(HTTP::Cookies->new(file => "lwpcookies.txt",
autosave => 1));
my $req = HTTP::Request->new(POST =>
'http://www1.somedomain.com/weborder/xt_shopper_lookup.asp');
$req->content_type('application/x-www-form-urlencoded');
$req->content('shopper_memno=12345124&shopper_password=somepass&submit1=Cont
inue');
$req->referer('http://www1.somedomain.com/weborder/xt_shopper_lookup.asp');
# Pass request to the user agent and get a response back
my $res = $ua->request($req);
# Check the outcome of the response
if ($res->is_success) {
my $ua = LWP::UserAgent->new;
$ua->agent("Mozilla/8.0"); # pretend we are very capable browser
$ua->cookie_jar(HTTP::Cookies->new(file => "lwpcookies.txt",
autosave => 1));
$req = HTTP::Request->new(GET =>
"http://ftp.thedomainsftpsite.com/default.asp?memno=12345124");
$req->referer('http://www1.somedomain.com/weborder/xt_shopper_lookup.asp');
# Pass request to the user agent and get a response back
my $res = $ua->request($req);
if($res->is_success) { # Check to see if I can access the FTP site...
# Yep, it appears to have let me login... This is where I'm getting the
error that, "Login Required"...
# When I go to the website and login manually, I can just click on the
FTP site to go download files from there, like txt descriptions and stuff,
one at a time.
# So this SHOULD work with the cookie jar...
$sth = $dbh->prepare (qq{ SELECT * FROM `my_items` ORDER BY `id` });
$sth->execute();
my $_cntr = 0;
while($rs = $sth->fetchrow_hashref()) {
$_pid = $rs->{pid};
$file_name = "/home/userid/files/Descriptions/" . $_pid . ".txt";
if(!-e "/$file_name/i") {# Ok it does not already exist, so go get
it...
$_sub_folder = Return_Sub_Folder($_pid); # Get the folder it
would be in, based upon the ID number of it...
my $ua = LWP::UserAgent->new;
$ua->agent("Mozilla/8.0"); # pretend we are very capable browser
$ua->cookie_jar(HTTP::Cookies->new(file => "lwpcookies.txt",
autosave => 1));
$req = HTTP::Request->new(GET =>
"http://ftp.thedomainsftpsite.com/items/descriptions/$_sub_folder/$_pid.txt"
);
# $req->header('Accept' => 'text/plain'); # Don't want to
use this right now...
$req->referer("http://ftp.thedomainsftpsite.com/items/descriptions/$_sub_fol
der/");
# send request
$res = $ua->request($req);
if ($res->is_success) { # Check if it can get the .txt file
description to save it to my account for later use...
# COOL IT WORKED!!!
$ctypeb = $res->content;
$_output_filename = "/home/userid/files/Descriptions/" .
$_pid . ".txt";
open (OUTFILE,">$_output_filename");
print OUTFILE $ctypeb; # SAVE IT!
close(OUTFILE);
} else {
#Nope still did not work. Maybe it's .TXT instead of
.txt lets try again with the .TXT extension
my $ua = LWP::UserAgent->new;
$ua->agent("Mozilla/8.0"); # pretend we are very capable
browser
$ua->cookie_jar(HTTP::Cookies->new(file => "lwpcookies.txt",
autosave => 1));
$req = HTTP::Request->new(GET =>
"http://ftp.thedomainsftpsite.com/items/descriptions/$_sub_folder/$_pid.TXT"
);
# $req->header('Accept' => 'text/plain'); # Don't want
to use this right now...
$req->referer("http://ftp.thedomainsftpsite.com/items/descriptions/$_sub_fol
der/");
# send request
$res1 = $ua->request($req);
if ($res1->is_success) {
$ctypeb = $res1->content;
$_output_filename = "/home/userid/files/Descriptions/" .
$_pid . ".txt";
open (OUTFILE,">$_output_filename");
print OUTFILE $ctypeb;
close(OUTFILE);
} else {# Nope still did not work, please send me the error
via email:
$_mail_message .= qq~I could not find $_pid.txt on
ourmemebersite.com so I could not add it to the directory.\n\nRun number 3:
Content says:\n$res1->content\n\nStatus Line says:\n$res->status_line\n\n~;
}
}
}
....
Response:
bash$ perl text_desc_dl.cgi
Content-type: text/html/
Login Failed....
Thank you.
Richard