X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=include%2FScrape.php;h=ff98992526314474b6dcc7aa20386a92f114c332;hb=b7292bc673bc7983b1fd933070bc9d6a0a155dbb;hp=e4f7a0878c71016332f7f28bee75b1f97bef8bf1;hpb=08d6fe5ae74cc223e4385344f8e0edfde4208a23;p=friendica.git

diff --git a/include/Scrape.php b/include/Scrape.php
index e4f7a0878c..ff98992526 100644
--- a/include/Scrape.php
+++ b/include/Scrape.php
@@ -5,12 +5,31 @@ require_once('library/HTML5/Parser.php');
 if(! function_exists('scrape_dfrn')) {
 function scrape_dfrn($url) {
 
+	$a = get_app();
+
 	$ret = array();
+
+	logger('scrape_dfrn: url=' . $url);
+
 	$s = fetch_url($url);
 
 	if(! $s) 
 		return $ret;
 
+	$headers = $a->get_curl_headers();
+	logger('scrape_dfrn: headers=' . $headers, LOGGER_DEBUG);
+
+
+	$lines = explode("\n",$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(! $dom)
@@ -77,12 +96,31 @@ function validate_dfrn($a) {
 if(! function_exists('scrape_meta')) {
 function scrape_meta($url) {
 
+	$a = get_app();
+
 	$ret = array();
+
+	logger('scrape_meta: url=' . $url);
+
 	$s = fetch_url($url);
 
 	if(! $s) 
 		return $ret;
 
+	$headers = $a->get_curl_headers();
+	logger('scrape_meta: headers=' . $headers, LOGGER_DEBUG);
+
+	$lines = explode("\n",$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(! $dom)
@@ -105,12 +143,27 @@ function scrape_meta($url) {
 if(! function_exists('scrape_vcard')) {
 function scrape_vcard($url) {
 
+	$a = get_app();
+
 	$ret = array();
+
+	logger('scrape_vcard: url=' . $url);
+
 	$s = fetch_url($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(! $dom)
@@ -142,12 +195,33 @@ function scrape_vcard($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();
+	logger('scrape_feed: headers=' . $headers, LOGGER_DEBUG);
+
+	$lines = explode("\n",$headers);
+	if(count($lines)) {
+		foreach($lines as $line) {				
+			if(stristr($line,'content-type:')) {
+				if(stristr($line,'application/atom+xml') || stristr($s,'<feed')) {
+					$ret['feed_atom'] = $url;
+					return $ret;
+				}
+ 				if(stristr($line,'application/rss+xml') || stristr($s,'<rss')) {
+					$ret['feed_rss'] = $url;
+					return ret;
+				}
+			}
+		}
+	}
+
 	$dom = HTML5_Parser::parse($s);
 
 	if(! $dom)