zrashwani / news-scrapper

src/NewsScrapper/Adapters/AbstractAdapter.php

Spacing +7 added lines, -7 removed lines

@@ -42,10 +42,10 @@ 
                 $link = pathinfo($baseUrl, PATHINFO_DIRNAME).'/'.$link;
         } elseif (preg_match('@^http(s?)://.*$@', $link) === 0) { //is not absolute
             $urlParts = parse_url($baseUrl);
-            $scheme = isset($urlParts['scheme'])===true?$urlParts['scheme']:'http';
-            $host = isset($urlParts['host'])===true?$urlParts['host']:'';
+            $scheme = isset($urlParts['scheme']) === true ? $urlParts['scheme'] : 'http';
+            $host = isset($urlParts['host']) === true ? $urlParts['host'] : '';
             if (strpos($link, '//') === 0) { //begins with //
-                $link = $scheme . ':' . $link;
+                $link = $scheme.':'.$link;
             } elseif (strpos($link, '/') === 0) { //begins with /
                 $link = $scheme.'://'.$host.$link;
             } else {
@@ -71,7 +71,7 @@ 
             return $raw_html;
         }
         
-        $disallowed_tags = ['script', 'style', 'meta','form','aside'];
+        $disallowed_tags = ['script', 'style', 'meta', 'form', 'aside'];
                 
         $xmlDoc = new \DOMDocument();
         libxml_use_internal_errors(true);
@@ -100,7 +100,7 @@ 
      */
     public function normalizeBodyLinks($html)
     {
-        if (empty($html)===true) { //if html is empty, do nothing
+        if (empty($html) === true) { //if html is empty, do nothing
             return $html;
         }
         
@@ -159,7 +159,7 @@ 
         
         $ret = '';
         $html_crawler->filter('body')->each(
-            function (Crawler $node) use (&$ret) {
+            function(Crawler $node) use (&$ret) {
                 $ret = $node->html();
             }
         );
@@ -177,7 +177,7 @@ 
     protected function getSrcByImgSelector(Crawler $crawler, $selector)
     {
         $ret = null;
-        $imgExtractClosure = function (Crawler $node) use (&$ret) {
+        $imgExtractClosure = function(Crawler $node) use (&$ret) {
             $ret = $node->attr('src');
         };
         if (Selector::isXPath($selector)) {

src/NewsScrapper/Adapters/CustomAdapter.php

Spacing +1 added lines, -1 removed lines

@@ -158,7 +158,7 @@
 
         $ret = null;
         if ($extractClosure === null) {
-            $extractClosure = function (Crawler $node) use (&$ret) {
+            $extractClosure = function(Crawler $node) use (&$ret) {
                 $ret = $node->html();
             };
         }

src/NewsScrapper/Adapters/DefaultAdapter.php

Spacing +7 added lines, -7 removed lines

@@ -22,7 +22,7 @@ 
 
         $crawler->filterXPath('//head/title')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                             $ret = $node->text();
                 }
             );
@@ -42,7 +42,7 @@ 
 
         $crawler->filterXPath('//img')
             ->each(
-                function (Crawler $node) use (&$ret, $theAdapter) {
+                function(Crawler $node) use (&$ret, $theAdapter) {
                         $img_src = $theAdapter->normalizeLink($node->attr('src'));
                         $width_org = $height_org = 0;
                     
@@ -77,7 +77,7 @@ 
 
         $crawler->filterXPath("//head/meta[@name='description']")
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                             $ret = $node->attr('content');
                 }
             );
@@ -96,7 +96,7 @@ 
 
         $crawler->filterXPath("//head/meta[@name='keywords']")
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                             $node_txt = trim($node->attr('content'));
                     if (!empty($node_txt)) {
                         $ret = explode(',', $node_txt);
@@ -119,7 +119,7 @@ 
 
         $crawler->filterXPath("//article")
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
 
                             $node_txt = $node->text();
                     if (strlen($node_txt) > strlen($ret)) {
@@ -142,7 +142,7 @@ 
 
         $crawler->filterXPath("//meta[@name='pubdate']")
             ->each(
-                function (Crawler $node) use (&$date_str) {
+                function(Crawler $node) use (&$date_str) {
                     if (empty($date_str) === true) {
                         $date_str = $node->attr('content');
                     }
@@ -172,7 +172,7 @@ 
         $ret = null;
         $crawler->filterXPath("//head/meta[@name='author']")
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                             $ret = $node->attr('content');
                 }
             );

src/NewsScrapper/Adapters/HAtomAdapter.php

Spacing +6 added lines, -6 removed lines

@@ -17,7 +17,7 @@ 
 
         $crawler->filter('.hentry .entry-title')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret = $node->text();
                 }
             );
@@ -38,7 +38,7 @@ 
 
         $crawler->filter('.hentry .entry-summary')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret = $node->text();
                 }
             );
@@ -52,7 +52,7 @@ 
 
         $crawler->filter('.hentry a[rel="tag"]')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret[] = $node->text();
                 }
             );
@@ -65,7 +65,7 @@ 
         $ret = null;
         $crawler->filter(".hentry .entry-content")
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret = $this->normalizeHtml($node->html());
                 }
             );
@@ -79,7 +79,7 @@ 
 
         $crawler->filter('time.published, .hentry .entry-date')
             ->each(
-                function (Crawler $node) use (&$date_str) {
+                function(Crawler $node) use (&$date_str) {
                         $date_str = $node->attr('datetime');
                 }
             );
@@ -95,7 +95,7 @@ 
         $ret = null;
         $crawler->filter('.hentry .author.vcard')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret = $node->text();
                 }
             );

src/NewsScrapper/Adapters/JsonLDAdapter.php

Spacing +5 added lines, -5 removed lines

@@ -17,7 +17,7 @@ 
     public function extractTitle(Crawler $crawler)
     {
         $article_data = $this->getJsonData($crawler);
-        $ret = isset($article_data['headline'])?$article_data['headline']:null;
+        $ret = isset($article_data['headline']) ? $article_data['headline'] : null;
 
         return $ret;
     }
@@ -39,7 +39,7 @@ 
     public function extractDescription(Crawler $crawler)
     {
         $article_data = $this->getJsonData($crawler);
-        $ret = isset($article_data['description'])?$article_data['description']:null;
+        $ret = isset($article_data['description']) ? $article_data['description'] : null;
         
         return $ret;
     }
@@ -47,7 +47,7 @@ 
     public function extractKeywords(Crawler $crawler)
     {
         $article_data = $this->getJsonData($crawler);
-        $ret = isset($article_data['keywords'])?$article_data['keywords']:array();
+        $ret = isset($article_data['keywords']) ? $article_data['keywords'] : array();
         
         if (!is_array($ret)) {
             $ret = explode(',', $ret);
@@ -137,7 +137,7 @@ 
         
         $ret = array();
         $crawler->filterXPath('//script[@type="application/ld+json"]')
-                ->each(function (Crawler $node) use (&$ret) {
+                ->each(function(Crawler $node) use (&$ret) {
                     $json_content = trim($node->text());
                     if (empty($json_content) === true && $node->attr('src')) {
                         $script_path = $this->normalizeLink($node->attr('src'));
@@ -171,7 +171,7 @@ 
                 'APIReference'];
         
         if (isset($article_data['@context']) &&
-                $article_data['@context']=='http://schema.org' &&
+                $article_data['@context'] == 'http://schema.org' &&
                 isset($article_data['@type']) &&
                 in_array($article_data['@type'], $article_types)) {
             return true;

src/NewsScrapper/Adapters/MicrodataAdapter.php

Spacing +8 added lines, -8 removed lines

@@ -22,7 +22,7 @@ 
 
         $crawler->filterXPath('//*[@itemprop="headline"]')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                             $ret = trim($node->text());
                 }
             );
@@ -44,7 +44,7 @@ 
 
         $crawler->filterXPath('//*[@itemprop="description"]')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                     if ($node->nodeName() === 'meta') {
                         $ret = trim($node->attr('content'));
                     } else {
@@ -67,7 +67,7 @@ 
 
         $crawler->filterXPath('//*[@itemprop="keywords"]')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                     if ($node->nodeName() === 'meta') {
                         $keyword_txt = trim($node->attr('content'));
                     } else {
@@ -89,7 +89,7 @@ 
 
         $crawler->filterXPath('//*[@itemprop="articleBody"]')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret .= $node->html();
                 }
             );
@@ -106,7 +106,7 @@ 
                     "//*[@itemtype='http://schema.org/$article_type']"
                 )
                     ->each(
-                        function (Crawler $node) use (&$ret) {
+                        function(Crawler $node) use (&$ret) {
                                     $ret .= $node->html();
                         }
                     );
@@ -128,7 +128,7 @@ 
 
         $crawler->filterXPath('//*[@itemprop="datePublished"]')
             ->each(
-                function (Crawler $node) use (&$date_str) {
+                function(Crawler $node) use (&$date_str) {
                     if ($node->nodeName() === 'meta') {
                         $date_str = $node->attr('content');
                     } elseif ($node->attr('datetime')) {
@@ -157,7 +157,7 @@ 
             'and @itemtype="http://schema.org/Person"]//*[@itemprop="name"]'
         )
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                             $ret = $node->text();
                 }
             );
@@ -165,7 +165,7 @@ 
         if (is_null($ret)) {
             $crawler->filterXPath('//*[@itemprop="author"]')
                 ->each(
-                    function (Crawler $node) use (&$ret) {
+                    function(Crawler $node) use (&$ret) {
                         if ($node->nodeName() === 'meta') {
                                 $ret = $node->attr('content');
                         } else {

src/NewsScrapper/Adapters/OpenGraphAdapter.php

Spacing +9 added lines, -9 removed lines

@@ -22,7 +22,7 @@ 
 
         $crawler->filterXPath("//head/meta[@property='og:title']")
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret = $node->attr('content');
                 }
             );
@@ -31,7 +31,7 @@ 
         if (empty($ret) === true) {
             $crawler->filterXPath('//h1')
                 ->each(
-                    function (Crawler $node) use (&$ret) {
+                    function(Crawler $node) use (&$ret) {
                             $ret = $node->text();
                     }
                 );
@@ -40,7 +40,7 @@ 
         if (empty($ret) === true) {
             $crawler->filterXPath('//head/title')
                 ->each(
-                    function (Crawler $node) use (&$ret) {
+                    function(Crawler $node) use (&$ret) {
                             $ret = $node->text();
                     }
                 );
@@ -61,7 +61,7 @@ 
 
         $crawler->filterXPath("//head/meta[@property='og:image']")
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret = $node->attr('content');
                 }
             );
@@ -69,7 +69,7 @@ 
         if (empty($ret) === true) {
             $crawler->filterXPath('//img')
                 ->each(
-                    function (Crawler $node) use (&$ret, $theAdapter) {
+                    function(Crawler $node) use (&$ret, $theAdapter) {
                         $img_src = $theAdapter->normalizeLink($node->attr('src'));
                         $width_org = $height_org = 0;
                     
@@ -106,7 +106,7 @@ 
 
         $crawler->filterXPath("//head/meta[@property='og:description']")
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret = $node->attr('content');
                 }
             );
@@ -125,7 +125,7 @@ 
 
         $crawler->filterXPath("//head/meta[@property='og:keywords']")
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                 
                         $node_txt = trim($node->attr('content'));
                     if (!empty($node_txt)) {
@@ -150,7 +150,7 @@ 
 
         $crawler->filterXPath("//head/meta[@property='article:published_time']")
             ->each(
-                function (Crawler $node) use (&$date_str) {
+                function(Crawler $node) use (&$date_str) {
                         $date_str = $node->attr('content');
                 }
             );
@@ -168,7 +168,7 @@ 
         $ret = null;
         $crawler->filterXPath("//head/meta[@property='article:author']")
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret = $node->attr('content');
                 }
             );

src/NewsScrapper/Adapters/ParselyAdapter.php

Spacing +5 added lines, -5 removed lines

@@ -18,7 +18,7 @@ 
 
         $crawler->filterXPath('//meta[@name="parsely-title"]')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret = $node->attr('content');
                 }
             );
@@ -33,7 +33,7 @@ 
 
         $crawler->filterXPath('//meta[@name="parsely-image-url"]')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret = $node->attr('content');
                 }
             );
@@ -55,7 +55,7 @@ 
 
         $crawler->filterXPath('//meta[@name="parsely-tags"]')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret = explode(',', $node->attr('content'));
                 }
             );
@@ -74,7 +74,7 @@ 
 
         $crawler->filterXPath('//meta[@name="parsely-pub-date"]')
             ->each(
-                function (Crawler $node) use (&$date_str) {
+                function(Crawler $node) use (&$date_str) {
                         $date_str = $node->attr('content');
                 }
             );
@@ -90,7 +90,7 @@ 
         $ret = null;
         $crawler->filterXPath('//meta[@name="parsely-author"]')
             ->each(
-                function (Crawler $node) use (&$ret) {
+                function(Crawler $node) use (&$ret) {
                         $ret = $node->attr('content');
                 }
             );

src/NewsScrapper/Client.php

Spacing +19 added lines, -19 removed lines

@@ -32,12 +32,12 @@ 
         
         $this->scrapClient->followRedirects();
         $this->scrapClient->getClient()->setDefaultOption(
-            'config/curl/' .
+            'config/curl/'.
             CURLOPT_SSL_VERIFYHOST,
             false
         );
         $this->scrapClient->getClient()->setDefaultOption(
-            'config/curl/' .
+            'config/curl/'.
             CURLOPT_SSL_VERIFYPEER,
             false
         );
@@ -61,7 +61,7 @@ 
      */
     public function setAdapter($adapter_name)
     {
-        $adapterClass = "\Zrashwani\NewsScrapper\Adapters\\" . $adapter_name . "Adapter";
+        $adapterClass = "\Zrashwani\NewsScrapper\Adapters\\".$adapter_name."Adapter";
         if (class_exists($adapterClass)) {
             $this->adapter = new $adapterClass();
         } else {
@@ -88,11 +88,11 @@ 
         $theAdapter->currentUrl = $baseUrl;
 
         $isXpath = Selector::isXPath($linkSelector);
-        $method = ($isXpath ===false)?'filter':'filterXPath';
+        $method = ($isXpath === false) ? 'filter' : 'filterXPath';
         
         $crawler->$method($linkSelector)
             ->each(
-                function (Crawler $link_node) use (&$scrap_result, $theAdapter, &$limit) {
+                function(Crawler $link_node) use (&$scrap_result, $theAdapter, &$limit) {
                     if (!is_null($limit) && count($scrap_result) >= $limit) {
                         return;
                     }
@@ -147,21 +147,21 @@ 
     ) {
         $adapter->currentUrl = $article_info->url; //associate link url to adapter
         
-        $article_info->title = empty($article_info->title) === true?
-                    $adapter->extractTitle($pageCrawler):$article_info->title;
-        $article_info->image = empty($article_info->image) === true?
-                $adapter->extractImage($pageCrawler, $article_info->url):$article_info->image;
-        $article_info->description = empty($article_info->description) === true?
-                $adapter->extractDescription($pageCrawler):$article_info->description;
-        $article_info->keywords = !isset($article_info->keywords) || count($article_info->keywords) === 0?
-                $adapter->extractKeywords($pageCrawler):$article_info->keywords;
+        $article_info->title = empty($article_info->title) === true ?
+                    $adapter->extractTitle($pageCrawler) : $article_info->title;
+        $article_info->image = empty($article_info->image) === true ?
+                $adapter->extractImage($pageCrawler, $article_info->url) : $article_info->image;
+        $article_info->description = empty($article_info->description) === true ?
+                $adapter->extractDescription($pageCrawler) : $article_info->description;
+        $article_info->keywords = !isset($article_info->keywords) || count($article_info->keywords) === 0 ?
+                $adapter->extractKeywords($pageCrawler) : $article_info->keywords;
         
-        $article_info->author = empty($article_info->author) === true?
-                $adapter->extractAuthor($pageCrawler):$article_info->author;
-        $article_info->publishDate = empty($article_info->publishDate) === true?
-                $adapter->extractPublishDate($pageCrawler):$article_info->publishDate;
-        $article_info->body = empty($article_info->body) === true?
-                $adapter->extractBody($pageCrawler):$article_info->body;
+        $article_info->author = empty($article_info->author) === true ?
+                $adapter->extractAuthor($pageCrawler) : $article_info->author;
+        $article_info->publishDate = empty($article_info->publishDate) === true ?
+                $adapter->extractPublishDate($pageCrawler) : $article_info->publishDate;
+        $article_info->body = empty($article_info->body) === true ?
+                $adapter->extractBody($pageCrawler) : $article_info->body;
         
     }
 }