function HTMLDocument($input, $insert='', $inject=false, $footer='') {
//
// Apply parsing that only needs to be done once..
//
// Remove titles if option is enabled
if ( $this->htmlOptions['stripTitle'] ) {
$input = preg_replace('##is', '', $input, 1);
}
// Remove and record a href
$input = preg_replace_callback('#]{1,1000}))(?(1)\\1|)[^>]*>#i', 'html_stripBase', $input, 1);
// Proxify url= values in meta redirects
$input = preg_replace_callback('#content\s*=\s*(["\\\'])?[0-9]+\s*;\s*url=([\\\'"]|&\#39;)?((?(?<=")[^"]+|(?(?<=\\\')[^\\\']+|[^\\\'" >]+)))(?(2)\\2|)(?(1)\\1|)#i', 'html_metaRefresh', $input, 1);
// Process forms
$input = preg_replace_callback('#]*)>(.*?)#is', 'html_form', $input);
// Remove scripts blocks (avoids individual processing below)
if ( $this->htmlOptions['strJS'] ) {
$input = preg_replace('#]*>.*?#is', '', $input);
}
//
// Split up the document into its different types and parse them
//
// Build up new document into this var
$new = '';
$offset = 0;
// Find instances of script or style blocks
while ( preg_match('#<(s(?:cript|tyle))[^>]*>#i', $input, $match, PREG_OFFSET_CAPTURE, $offset) ) {
// What type of block is this?
$block = strtolower($match[1][0]);
// Start position of content
$outerStart = $match[0][1];
$innerStart = $outerStart + strlen($match[0][0]);
// Determine type of end tag and find it's position
$endTag = "";
$innerEnd = stripos($input, $endTag, $innerStart);
$outerEnd = $innerEnd + strlen($endTag);
// Parse everything up till here and add to the new document
$new .= $this->HTML(substr($input, $offset, $innerStart - $offset));
// Find parsing function
$parseFunction = $block == 'style' ? 'CSS' : 'JS' ;
// Add the parsed block
$new .= $this->$parseFunction(substr($input, $innerStart, $innerEnd - $innerStart));
// Move offset to new position
$offset = $innerEnd;
}
// And add the final chunk (between last script/style block and end of doc)
$new .= $this->HTML(substr($input, $offset));
// Replace input with the updated document
$input = $new;
// Encode the page
if ( $this->htmlOptions['encp'] ) {
$input = encodePage($input);
}
//
// Now add our own code bits
//
// Insert our mini form after the
if ( $insert !== false ) {
// Check for a frameset
if ( ( $useFrames = stripos($input, ']+src\s*=\s*([\\\'"])?((?(1)(?(?<=")[^"]{1,1000}|[^\\\']{1,1000})|[^\s"\\\'>]{1,1000}))(?(1)\\1|)#i', 'html_flagFrames', $input);
}
// Attempt to add after body
$input = preg_replace('#(]*>)#i', '$1' . $insert, $input, 1, $tmp);
// Check it inserted and append (if not a frameset)
if ( ! $tmp && ! $useFrames ) {
$input = $insert . $input;
}
}
// Insert our javascript library
if ( $inject ) {
// Generate javascript to insert
$inject = injectionJS();
// Add our proxy javascript after
$input = preg_replace('#(]*>)#i', '$1' . $inject, $input, 1, $tmp);
// If no , just prepend
if ( ! $tmp ) {
$input = $inject . $input;
}
}
// Add anything to the footer?
if ( $footer ) {
$input = preg_replace('#(]*>)#i', $footer . '$1', $input, 1, $tmp);
// If no , just append the footer
if ( ! $tmp ){
$input .= $footer;
}
}
// Return new document
return $input;
}
// Parse HTML sections
function HTML($input) {
// Removing objects? Follow spec and display inner content of object tags instead.
if ( $this->htmlOptions['strFlash'] ) {
// Remove all object tags (including those deprecated but still common)
$input = preg_replace('#<(?>object|applet|param|embed)[^>]*>#i', '', $input, -1, $tmp);
// Found any? Remove the corresponding end tags
if ( $tmp ) {
$input = preg_replace('#object|applet|param|embed)>#i', '', $input, $tmp);
}
} else {
// Parse tags
$input = preg_replace_callback('#]+value\s*=\s*([\\\'"])?((?(1)(?(?<=")[^"]{1,1000}|[^\\\']{1,1000})|[^\s"\\\'>]{1,1000}))(?(1)\\1|)[^>]*>#i', 'html_paramValue', $input);
// To do: proxify object related URLs
}
// Show content within