#!/usr/bin/perl
use LWP::UserAgent;
use HTTP::Request::Common qw(GET POST);
use HTML::Parser; use URI;
use HTML::Entities;

use constant MAINPAGE =>
  'http://en.wikipedia.org/wiki/Wikipedia:Tutorial_%28Keep_in_mind%29/sandbox';
use constant EDITPAGE => 'http://en.wikipedia.org/w/index.php'
  . '?title=Wikipedia:Tutorial_%28Keep_in_mind%29/sandbox';

# These are form inputs we care about on the edit page
my @wpTags = qw(wpEditToken wpAutoSummary wpStarttime wpEdittime wpSave );

sub findPageData {
    my ( $self, $tag, $attr ) = @_;
    # signal to the endHandler handler if we find the text
    if ( $attr->{name} eq "wpTextbox1" ) {
        $main::wpTextboxFound = 1;
        return;
    }
    elsif ( grep( /$attr->{name}/, @wpTags ) > 0 ) {
    # if it's one of the form parameters we care about,
    # record the parameter's value for use in our submission later.
        $main::parms{ $attr->{name} } = $attr->{value};
        return;
    }
}

# This is called on closing tags like 
sub endHandler {
    next unless $main::wpTextboxFound;
    my ( $self, $tag, $attr, $skipped ) = @_;
    if ( $tag eq "textarea" ) {
        $main::parms{"wpTextbox1"} = $skipped;
        undef $main::wpTextboxFound;
    }
}

sub checkError {
    my $resp = shift;
    if ( ( $resp->code() < 200 ) || ( $resp->code() >= 400 ) ) {
        print "Error: " . $resp->status_line . "\n";
        exit 1;
    }
}

###
### MAIN
###

# First, fetch the main wikipedia sandbox page. This just confirms
# our connectivity and makes sure it really works.
$UA   = LWP::UserAgent->new();
$req  = HTTP::Request->new( GET => MAINPAGE );
$resp = $UA->request($req);

checkError($resp);

# Now fetch the edit version of that page
$req->uri( EDITPAGE . '&action=edit' );
$resp = $UA->request($req);

checkError($resp);

# Build a parser to parse the edit page and find the text on it.
my $p = HTML::Parser->new(
    api_version   => 3,
    start_h       => [ \&findPageData, "self,tagname,attr" ],
    end_h         => [ \&endHandler, "self,tagname,attr,skipped_text" ],
    unbroken_text => 1,
    attr_encoded  => 0,
    report_tags   => [qw(textarea input)]
);
$p->parse( $resp->content );
$p->eof;

# The text will have entities encoded (e.g., < instead of <)
# We have to decode them and submit raw characters.
$main::parms{wpTextbox1} = decode_entities($main::parms{wpTextbox1});

# make our trivial edit. append text to whatever was already there.
$main::parms{wpTextbox1} .= "\r\n\r\n===Test 1===\r\n\r\n"
  . "ISBN: 9780596514839\r\n\r\nThis is a test.\r\n\r\n";

# POST our edit
$req = HTTP::Request::Common::POST(
    EDITPAGE,
    Content_Type => 'form-data',
    Content      => \%main::parms
);
$req->uri( EDITPAGE . '&action=submit' );

$resp = $UA->request($req);
checkError($resp);
# We expect a 302 redirection if it is successful.