Merge pull request #221 from j0k3r/fix/meta-refresh-url

Handle meta refresh when attributes are reversed
j0k3r · Jan 23, 2020 · 6b3e53b · 6b3e53b
2 parents 1630960 + 4889175
commit 6b3e53b
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/src/Extractor/HttpClient.php b/src/Extractor/HttpClient.php
@@ -515,7 +515,10 @@ private function getMetaRefreshURL($url, $html)
 
         // <meta HTTP-EQUIV="REFRESH" content="0; url=http://www.bernama.com/bernama/v6/newsindex.php?id=943513">
         if (!preg_match('!<meta http-equiv=["\']?refresh["\']? content=["\']?[0-9];\s*url=["\']?([^"\'>]+)["\']?!i', $html, $match)) {
-            return false;
+            // let's try in a reverse mode (switch content & http-equiv attributes)
+            if (!preg_match('!<meta content=["\']?[0-9];\s*url=["\']?([^"\'>]+)["\']? http-equiv=["\']?refresh["\']?!i', $html, $match)) {
+                return false;
+            }
         }
 
         $redirectUrl = str_replace('&amp;', '&', trim($match[1]));

diff --git a/tests/Extractor/HttpClientTest.php b/tests/Extractor/HttpClientTest.php
@@ -136,6 +136,11 @@ public function dataForMetaRefresh()
                 '<html><meta HTTP-EQUIV="REFRESH" content="0; url=http://www.bernama.com/bernama/v6/newsindex.php?id=943513"></html>',
                 'http://www.bernama.com/bernama/v6/newsindex.php?id=943513',
             ],
+            [
+                'https://www.google.com/url?sa=t&source=web&rct=j&url=https://databox.com/google-my-business-seo',
+                '<html><meta content="0;url=https://databox.com/google-my-business-seo" http-equiv="refresh"></html>',
+                'https://databox.com/google-my-business-seo',
+            ],
             [
                 'http://www.example.com/wiki/Copyright',
                 '<html><meta HTTP-EQUIV="REFRESH" content="0; url=/bernama/v6/newsindex.php?id=943513"></html>',