function clean_url($url)
{
$bits = crack_url($url);
// force http (but allow https too)
if (strtolower($bits['scheme']) != 'https') {
$bits['scheme'] = 'http';
}
return glue_url($bits);
}
function buildurl($url = false, $qs = '')
{
$url or $url = $_SERVER["REQUEST_URI"];
$urlA = parse_url($url);
parse_str($urlA['query'], $query1);
$query2 = $qs;
is_array($qs) or parse_str($qs, $query2);
$query = array_merge($query1, $query2);
$urlA['query'] = http_build_query($query);
$nurl = glue_url($urlA);
return $nurl ? $nurl : $url;
}
/**
* Enter description here...
*
* @param unknown_type $base
* @param unknown_type $url
* @return unknown
* @author adrian-php at sixfingeredman dot net
*/
function resolve_url($base, $url)
{
if (!strlen($base)) {
return $url;
}
// Step 2
if (!strlen($url)) {
return $base;
}
// Step 3
if (preg_match('!^[a-z]+:!i', $url)) {
return $url;
}
$base = parse_url($base);
if ($url[0] == "#") {
// Step 2 (fragment)
$base['fragment'] = substr($url, 1);
return unparse_url($base);
}
unset($base['fragment']);
unset($base['query']);
if (substr($url, 0, 2) == "//") {
// Step 4
return unparse_url(array('scheme' => $base['scheme'], 'path' => substr($url, 2)));
} else {
if ($url[0] == "/") {
// Step 5
$base['path'] = $url;
} else {
// Step 6
$path = explode('/', $base['path']);
$url_path = explode('/', $url);
// Step 6a: drop file from base
array_pop($path);
// Step 6b, 6c, 6e: append url while removing "." and ".." from
// the directory portion
$end = array_pop($url_path);
foreach ($url_path as $segment) {
if ($segment == '.') {
// skip
} else {
if ($segment == '..' && $path && $path[sizeof($path) - 1] != '..') {
array_pop($path);
} else {
$path[] = $segment;
}
}
}
// Step 6d, 6f: remove "." and ".." from file portion
if ($end == '.') {
$path[] = '';
} else {
if ($end == '..' && $path && $path[sizeof($path) - 1] != '..') {
$path[sizeof($path) - 1] = '';
} else {
$path[] = $end;
}
}
// Step 6h
$base['path'] = join('/', $path);
}
}
// Step 7
return glue_url($base);
}
function no_password_proxy_url($http_proxy) {
if ($p = @parse_url($http_proxy)
AND $p['pass']) {
$p['pass'] = '******';
$http_proxy = glue_url($p);
}
return $http_proxy;
}
/**
* Get PukiWiki Page Source via http using cmd=source
* @access public
* @param string $url Page URL
* @return mixed PukiWiki Page Source. FALSE if HTTP GET failed.
* @uses PKWKSourceHandler
* @uses PEAR XML/XML_HTMLSax.php
*/
function &pkwk_get_source($url)
{
// pkwk source (cmd=source&page=PAGE)
$parsed = parse_url($url);
$queries = array();
parse_str($parsed['query'], $queries);
// rawurldecode
$page = isset($queries['page']) ? $queries['page'] : rawurldecode($parsed['query']);
$queries = array();
$queries['cmd'] = 'source';
$queries['page'] = $page;
$parsed['query'] = glue_str($queries);
$url = glue_url($parsed);
if (($html = http_get_contents($url, $GLOBALS['USERNAME'], $GLOBALS['USERPASS'])) === FALSE) {
return FALSE;
}
require_once 'XML/XML_HTMLSax.php';
$parser = new XML_HTMLSax();
$handler = new PKWKSourceHandler();
$parser->set_object($handler);
$parser->set_element_handler('openHandler', 'closeHandler');
$parser->set_data_handler('dataHandler');
$parser->parse($html);
return $handler->source;
}
function parse_wordpress($url, $page_source)
{
// feed url
$url_parsed = parse_url($url);
if (isset($url_parsed['query'])) {
$url_parsed['query'] .= '&feed=rss&withoutcomments=1';
} else {
$url_parsed['query'] = 'feed=rss2&withoutcomments=1';
}
$single_post_feed_url = glue_url($url_parsed);
// get feed source
$single_post_feed_source = get_source_width_curl($single_post_feed_url);
$single_post_feed_source = $single_post_feed_source["content"];
// fallback parser if not full content in single post feed
if (!stristr($single_post_feed_source, "<content:encoded>")) {
return fallback_parser($url, $page_source);
} else {
// content
$xml_parsed = simplexml_load_string($single_post_feed_source, null, LIBXML_NOCDATA);
$link = $xml_parsed->channel->item->link;
$h1 = $xml_parsed->channel->item->title;
$title = $xml_parsed->channel->title;
$content_decoded = $xml_parsed->channel->item->children('content', true)->encoded;
// parse content
$content = str_get_html((string) $content_decoded[0]);
// remove facebook iframes
$i = 0;
foreach ($content->find("iframe") as $iframe) {
if (strstr($iframe->src, 'facebook.com')) {
$content->find("iframe", $i)->outertext = '';
}
$i++;
}
// remove flattr-links
$i = 0;
foreach ($content->find("a") as $a) {
if (strstr($a->href, 'flattrss_redirect')) {
$content->find("a", $i)->outertext = '';
}
$i++;
}
// remove wordpress.com feeds
$i = 0;
foreach ($content->find("a") as $a) {
if (strstr($a->href, 'feeds.wordpress.com')) {
$content->find("a", $i)->outertext = '';
}
$i++;
}
// loop through elements and do stuff
function do_stuff($element)
{
// remove all attributes, except href and src
foreach ($element->attr as $name => $attr) {
if ($name != 'src' && $name != 'href') {
$element->removeAttribute($name);
}
}
// we keep a, img, object, embed, h1, h2, h3, h4, h5, h6, i, em, b, strong, blockquote
// all other converted to p
if ($element->tag != 'img' && $element->tag != 'span' && $element->tag != 'a' && $element->tag != 'li' && $element->tag != 'ul' && $element->tag != 'ol' && $element->tag != 'object' && $element->tag != 'embed' && $element->tag != 'h1' && $element->tag != 'h2' && $element->tag != 'h3' && $element->tag != 'h4' && $element->tag != 'h5' && $element->tag != 'h6' && $element->tag != 'i' && $element->tag != 'em' && $element->tag != 'b' && $element->tag != 'strong' && $element->tag != 'blockquote') {
$element->tag = 'p';
}
// remove p:s without innertext
if ($element->tag == 'p' && $element->innertext == null) {
$element->outertext = '';
}
// remove a:s without innertext
if ($element->tag == 'a' && $element->innertext == null) {
$element->outertext = '';
}
// remove wordpress.com stats
if (strstr($element->src, 'stats.wordpress.com')) {
$element->outertext = '';
}
}
$content->set_callback('do_stuff');
$content = $content->save();
// no indent before image, if first in p
$content = str_replace('<p><a', '<p> <a', $content);
$content = str_replace('<p><img', '<p> <img', $content);
// wrap in article structure
return '<div class="article"><h1>' . $h1 . '</h1>' . $content . '<address><a href="' . $link . '">' . $title . '</a></address></div>';
}
}
/**
* Get absolute URL
*
* PHP Extension
*
* @access public
* @param string $base base url
* @param string $url relative url
* @return string absolute url
* @see parse_url()
* @see realpath()
* @uses glue_url()
*/
function realurl($base, $url)
{
if (!strlen($base)) {
return $url;
}
if (!strlen($url)) {
return $base;
}
if (preg_match('!^[a-z]+:!i', $url)) {
return $url;
}
$base = parse_url($base);
if ($url[0] == "#") {
// fragment
$base['fragment'] = substr($url, 1);
return glue_url($base);
}
unset($base['fragment']);
unset($base['query']);
if (substr($url, 0, 2) == "//") {
// FQDN
$base = array('scheme' => $base['scheme'], 'path' => substr($url, 2));
return glue_url($base);
} elseif ($url[0] == "/") {
// absolute path reference
$base['path'] = $url;
} else {
// relative path reference
$path = explode('/', $base['path']);
$url_path = explode('/', $url);
// drop file from base
array_pop($path);
// append url while removing "." and ".." from
// the directory portion
$end = array_pop($url_path);
foreach ($url_path as $segment) {
if ($segment == '.') {
// skip
} elseif ($segment == '..' && $path && $path[sizeof($path) - 1] != '..') {
array_pop($path);
} else {
$path[] = $segment;
}
}
// remove "." and ".." from file portion
if ($end == '.') {
$path[] = '';
} elseif ($end == '..' && $path && $path[sizeof($path) - 1] != '..') {
$path[sizeof($path) - 1] = '';
} else {
$path[] = $end;
}
$base['path'] = join('/', $path);
}
return glue_url($base);
}
