X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=include%2FScrape.php;h=bb42c3bdd3474946db9325ad4fb6846141c5571e;hb=968e8bb9c4a1183483e487a1c1ac557fa9c21ad0;hp=8478ea40714d389365522d02d685c7befbe51307;hpb=5be98e3ec8b0475dc67504967cac695d9e4a129a;p=friendica.git

diff --git a/include/Scrape.php b/include/Scrape.php
index 8478ea4071..bb42c3bdd3 100644
--- a/include/Scrape.php
+++ b/include/Scrape.php
@@ -5,12 +5,25 @@ require_once('library/HTML5/Parser.php');
 if(! function_exists('scrape_dfrn')) {
 function scrape_dfrn($url) {
 
+	$a = get_app();
+
 	$ret = array();
 	$s = fetch_url($url);
 
 	if(! $s) 
 		return $ret;
 
+	$headers = $a->get_curl_headers();
+	$lines = explode("\n",$headers);
+	if(count($lines)) {
+		foreach($lines as $line) {				
+			// don't try and run feeds through the html5 parser
+			if(stristr($line,'content-type:') && ((stristr($line,'application/atom+xml')) || (stristr($line,'application/rss+xml'))))
+				return ret;
+		}
+	}
+
+
 	$dom = HTML5_Parser::parse($s);
 
 	if(! $dom)
@@ -77,12 +90,26 @@ function validate_dfrn($a) {
 if(! function_exists('scrape_meta')) {
 function scrape_meta($url) {
 
+	$a = get_app();
+
 	$ret = array();
 	$s = fetch_url($url);
 
 	if(! $s) 
 		return $ret;
 
+	$headers = $a->get_curl_headers();
+	$lines = explode("\n",$headers);
+	if(count($lines)) {
+		foreach($lines as $line) {				
+			// don't try and run feeds through the html5 parser
+			if(stristr($line,'content-type:') && ((stristr($line,'application/atom+xml')) || (stristr($line,'application/rss+xml'))))
+				return ret;
+		}
+	}
+
+
+
 	$dom = HTML5_Parser::parse($s);
 
 	if(! $dom)
@@ -105,12 +132,24 @@ function scrape_meta($url) {
 if(! function_exists('scrape_vcard')) {
 function scrape_vcard($url) {
 
+	$a = get_app();
+
 	$ret = array();
 	$s = fetch_url($url);
 
 	if(! $s) 
 		return $ret;
 
+	$headers = $a->get_curl_headers();
+	$lines = explode("\n",$headers);
+	if(count($lines)) {
+		foreach($lines as $line) {				
+			// don't try and run feeds through the html5 parser
+			if(stristr($line,'content-type:') && ((stristr($line,'application/atom+xml')) || (stristr($line,'application/rss+xml'))))
+				return ret;
+		}
+	}
+
 	$dom = HTML5_Parser::parse($s);
 
 	if(! $dom)
@@ -142,12 +181,31 @@ function scrape_vcard($url) {
 if(! function_exists('scrape_feed')) {
 function scrape_feed($url) {
 
+	$a = get_app();
+
 	$ret = array();
 	$s = fetch_url($url);
 
 	if(! $s) 
 		return $ret;
 
+	$headers = $a->get_curl_headers();
+	$lines = explode("\n",$headers);
+	if(count($lines)) {
+		foreach($lines as $line) {				
+			if(stristr($line,'content-type:')) {
+				if(stristr($line,'application/atom+xml')) {
+					$ret['feed_atom'] = $url;
+					return $ret;
+				}
+ 				if(stristr($line,'application/rss+xml')) {
+					$ret['feed_rss'] = $url;
+					return ret;
+				}
+			}
+		}
+	}
+
 	$dom = HTML5_Parser::parse($s);
 
 	if(! $dom)
@@ -161,6 +219,8 @@ function scrape_feed($url) {
 		$x = $item->getAttribute('rel');
 		if(($x === 'alternate') && ($item->getAttribute('type') === 'application/atom+xml'))
 			$ret['feed_atom'] = $item->getAttribute('href');
+		if(($x === 'alternate') && ($item->getAttribute('type') === 'application/rss+xml'))
+			$ret['feed_rss'] = $item->getAttribute('href');
 	}
 
 	return $ret;