PDF-o-matic Source
| Home · HTMLDOC | MyESP: Login |
| HTMLDOC · Basic · Site · Developer · Open Source · Documentation · Download · Examples · Screenshots · Support | Cart: Empty |
Easy Software Products is closed September 6, 2010 for Labor Day. We wish you a safe and pleasant holiday! Online orders continue to be processed.
PDF-o-matic is a simple PHP script (view page) that uses HTMLDOC to convert the web page of your choice.
"pdf-o-matic.php":
<?
//
// "$Id: pdf-o-matic.php 554 2009-01-08 17:00:17Z mike $"
//
// Convert a web page to PDF, or show a form to get the URL...
//
// Copyright 2001-2005 by Easy Software Products. This code may be
// freely used, and distributed under the terms of the HTMLDOC
// software license.
//
// HTML functions for HTMLDOC pages...
//
// This include file contains the following functions:
//
// htmldoc_header($title = "")
// html_footer()
//
// Both just put out a standard web page header (<html><body>)
// and trailer (</body></html>) - provide your own implementation
// if you use this script, e.g.:
//
// function
// htmldoc_header($title = "") // I - Title string
// {
// print("<html><head><title>$title - Fooware</title></head><body>\n");
// }
//
// function
// html_footer()
// {
// print("</body></html>\n");
// }
include_once "../phplib/htmldoc.php";
// Globals...
global $_GET; // Form variables
global $_SERVER; // Server variables
global $PHP_SELF; // Local URL for this page
//
// 'show_form()' - Show a form for converting a URL to PDF.
//
function
show_form()
{
global $PHP_SELF;
print("<p class='box'>This page is provided as a demonstration of "
."HTMLDOC and may not be used for commercial purposes. Violators "
."will be permanently banned from accessing this site!</p>\n");
print("<p>PDF-o-matic is a simple PHP script "
."(<a href='pdf-o-matic.php?source'>view source</a>) "
."that uses HTMLDOC to convert the web page of your choice. "
."Enter a URL to be converted to PDF and click on the "
."<var>Create PDF</var> button:</p>\n"
."<form method='GET' action='$PHP_SELF'>\n"
."<center><input type='text' name='URL' size='40' value='http://'>"
."<input type='submit' value='Create PDF'>\n");
// The following hidden variable fixes a HUGE bug in Microsoft
// Internet Explorer (all versions) where MSIE ignores the
// Content-Type field and instead uses the "extension" on the
// end of the URL...
print("<input type='hidden' name='FORMAT' value='.pdf'>"
."</center></form>\n");
print("<p>Please make sure that your HTML code is error free and that all "
."the elements are supported with HTMLDOC. "
."<a href='htmldoc.html#HTMLREF'>Chapter 6</a> of the HTMLDOC "
."Users Manual lists the elements that are supported.</p>\n");
print("<center><table border='1' bgcolor='#cccccc'>\n"
."<tr>"
."<th align='right'>Server:</th>"
."<td>3.0GHz Pentium D with 2GB RAM running Linux</td>"
."</tr>\n"
."<tr>"
."<th align='right'>Status:</th><td>");
system("ps -A | awk '{print $4}' | grep htmldoc | wc -l");
print("copies of HTMLDOC running<br>System load average = ");
system("uptime | awk '{printf(\"%.2f\", ($10 + $11 + $12) / 3)}'");
print("</td></tr>\n"
."</table></center>\n");
}
//
// 'bad_url()' - See if the URL contains bad characters...
//
function // O - 1 if the URL is bad, 0 otherwise
bad_url($url) // I - URL to check
{
// See if the URL starts with http: or https:...
if (strncmp($url, "http://", 7) != 0 &&
strncmp($url, "https://", 8) != 0)
{
return (1);
}
// Check for bad characters in the URL...
$len = strlen($url);
for ($i = 0; $i < $len; $i ++) {
if (!strchr("~_*()/:%?+-&@;=,$.0123456789"
."abcdefghijklmnopqrstuvwxyz"
."ABCDEFGHIJKLMNOPQRSTUVWXYZ", $url[$i]))
{
return (1);
}
}
return (0);
}
//
// 'topdf()' - Convert the named file/URL to PDF.
//
function
topdf($filename, // I - File/URL to convert
$options = "") // I - Additional command-line options
{
# Write the content type to the client...
header("Content-Type: application/pdf");
header("Content-Disposition: inline; filename=\"pdf-o-matic.pdf\"");
flush();
# Run HTMLDOC to provide the PDF file to the user...
# Use the --no-localfiles option for enhanced security!
# Use ulimit to limit the maximum amount of memory used by each instance!
passthru("ulimit -m 16384 -t 5; htmldoc --no-localfiles --no-compression -t pdf14 --quiet "
."--jpeg --webpage $options '$filename'");
}
//
// MAIN ENTRY - see if we have form data...
//
if ($argc && $argv[0] == "source")
{
// Show source...
htmldoc_header("PDF-o-matic Source");
?>
<p>PDF-o-matic is a simple PHP script (<a
href='pdf-o-matic.php'>view page</a>) that uses HTMLDOC to
convert the web page of your choice.</p>
<?php
print("<pre>\"pdf-o-matic.php\":\n");
highlight_file("pdf-o-matic.php");
print("</pre>\n");
html_footer();
}
else if (array_key_exists("URL", $_GET))
{
// Yes, see if the URL is a valid URL and not a filename (security...)
$url = $_GET["URL"];
$options = "";
if (array_key_exists("HTTPS", $_SERVER) && $_SERVER["HTTPS"] == "on")
$self = "https://$_SERVER[HTTP_HOST]$PHP_SELF";
else
$self = "http://$_SERVER[HTTP_HOST]$PHP_SELF";
if (bad_url($url))
{
// Write the standard header...
htmldoc_header("PDF-o-matic");
// Show a form for the URL...
show_form();
// Show an error message...
print("<p><b>Error!</b></p>\n"
."<p>\"$url\" is not a valid URL. Unable to process!</p>\n");
// Show the standard footer...
html_footer();
}
else if (array_key_exists("HTTP_REFERER", $_SERVER) &&
$self != $_SERVER["HTTP_REFERER"])
{
// Write the standard header...
htmldoc_header("PDF-o-matic");
// Show an error message - no remote linking!
print("<h1>PDF-o-matic</h1>\n"
."<p><b>Error!</b></p>\n"
."<p>PDF-o-matic was linked from a remote site "
."($_SERVER[HTTP_REFERRER]), which is not allowed.</p>\n");
// Show the standard footer...
html_footer();
}
else
topdf($url, "--header t.D --footer ./. --size letter --left 0.5in");
}
else
{
// Write the standard header...
htmldoc_header("PDF-o-matic");
// Show a form for the URL...
show_form();
// Show the standard footer...
html_footer();
}
?>