Merge pull request #73 from andreskrey/development

v2.0.1

Author: andreskrey

src/Readability.php

@@ -287,10 +287,10 @@ private function getMetadata()
 
         $values = [];
         // property is a space-separated list of values
-        $propertyPattern = '/\s*(dc|dcterm|og|twitter)\s*:\s*(author|creator|description|title)\s*/i';
+        $propertyPattern = '/\s*(dc|dcterm|og|twitter)\s*:\s*(author|creator|description|title|image)\s*/i';
 
         // name is a single value
-        $namePattern = '/^\s*(?:(dc|dcterm|og|twitter|weibo:(article|webpage))\s*[\.:]\s*)?(author|creator|description|title)\s*$/i';
+        $namePattern = '/^\s*(?:(dc|dcterm|og|twitter|weibo:(article|webpage))\s*[\.:]\s*)?(author|creator|description|title|image)\s*$/i';
 
         // Find description tags.
         foreach ($this->dom->getElementsByTagName('meta') as $meta) {

test/ReadabilityTest.php

@@ -59,7 +59,7 @@ public function testHTMLParserParsesImages($html, $expectedResult, $expectedMeta
         $readability = new Readability($configuration);
         $readability->parse($html);
 
-        $this->assertSame($expectedImages, json_encode($readability->getImages()));
+        $this->assertSame(json_decode($expectedImages, true), $readability->getImages());
     }
 
     public function getSamplePages()

test/test-pages/001/expected-images.json

@@ -1 +1,3 @@
-["http:\/\/fakehost\/static\/code\/2013\/blanket-coverage.png"]
+[
+    "http:\/\/fakehost\/static\/code\/2013\/blanket-coverage.png"
+]

test/test-pages/001/expected-metadata.json

@@ -1,5 +1,7 @@
 {
-  "Title": "Get your Frontend JavaScript Code Covered | Code",
-  "Author": "Nicolas Perriault —",
-  "Excerpt": "Nicolas Perriault's homepage."
-}
+    "Title": "Get your Frontend JavaScript Code Covered | Code",
+    "Author": "Nicolas Perriault —",
+    "Excerpt": "Nicolas Perriault's homepage.",
+    "Direction": null,
+    "Image": null
+}

test/test-pages/002/expected-metadata.json

@@ -1,5 +1,7 @@
 {
-  "Title": "This API is so Fetching!",
-  "Author": "Nikhil Marathe",
-  "Excerpt": "For more than a decade the Web has used XMLHttpRequest (XHR) to achieve asynchronous requests in JavaScript. While very useful, XHR is not a very ..."
-}
+    "Title": "This API is so Fetching!",
+    "Author": "Nikhil Marathe",
+    "Excerpt": "For more than a decade the Web has used XMLHttpRequest (XHR) to achieve asynchronous requests in JavaScript. While very useful, XHR is not a very ...",
+    "Direction": null,
+    "Image": null
+}

test/test-pages/003-metadata-preferred/expected-metadata.json

@@ -1,5 +1,7 @@
 {
-  "Title": "Dublin Core property title",
-  "Author": "Dublin Core property author",
-  "Excerpt": "Dublin Core property description"
-}
+    "Title": "Dublin Core property title",
+    "Author": "Dublin Core property author",
+    "Excerpt": "Dublin Core property description",
+    "Direction": null,
+    "Image": null
+}

test/test-pages/004-metadata-space-separated-properties/expected-metadata.json

@@ -1,5 +1,7 @@
 {
-  "Title": "Preferred title",
-  "Author": "Creator Name",
-  "Excerpt": "Preferred description"
-}
+    "Title": "Preferred title",
+    "Author": "Creator Name",
+    "Excerpt": "Preferred description",
+    "Direction": null,
+    "Image": null
+}

test/test-pages/aclu/expected-images.json

@@ -1 +1,3 @@
-[]
+[
+    "https:\/\/www.aclu.org\/sites\/default\/files\/styles\/metatag_og_image_1200x630\/public\/field_share_image\/web18-facebook-socialshare-1200x628-v02.png?itok=p77cQjOm"
+]

test/test-pages/aclu/expected-metadata.json

@@ -1,5 +1,7 @@
 {
-  "Title": "Facebook Is Tracking Me Even Though I’m Not on Facebook",
-  "Author": "By Daniel Kahn Gillmor, Senior Staff Technologist, ACLU Speech, Privacy, and Technology Project",
-  "Excerpt": "I don't use Facebook. I'm not technophobic — I'm a geek. I've been using email since the early 1990s, I have accounts on hundreds of services around the net, and I do software development and internet protocol design both for work and for fun. I believe that a globe-spanning communications network like the internet can be a positive social force, and I publish much of my own work on the open web."
-}
+    "Title": "Facebook Is Tracking Me Even Though I’m Not on Facebook",
+    "Author": "By Daniel Kahn Gillmor, Senior Staff Technologist, ACLU Speech, Privacy, and Technology Project",
+    "Excerpt": "I don't use Facebook. I'm not technophobic — I'm a geek. I've been using email since the early 1990s, I have accounts on hundreds of services around the net, and I do software development and internet protocol design both for work and for fun. I believe that a globe-spanning communications network like the internet can be a positive social force, and I publish much of my own work on the open web.",
+    "Image": "https:\/\/www.aclu.org\/sites\/default\/files\/styles\/metatag_og_image_1200x630\/public\/field_share_image\/web18-facebook-socialshare-1200x628-v02.png?itok=p77cQjOm",
+    "Direction": "ltr"
+}

test/test-pages/ars-1/expected-images.json

@@ -1 +1,3 @@
-["http:\/\/cdn.arstechnica.net\/wp-content\/uploads\/2015\/04\/server-crash-640x426.jpg"]
+[
+    "http:\/\/cdn.arstechnica.net\/wp-content\/uploads\/2015\/04\/server-crash-640x426.jpg"
+]