all: Use ->remove() instead of ->outertext = ''

simplehtmldom 1.9 introduced new functions to recursively remove
nodes from the DOM. This allows removing elements without the need
to re-load the document by using $html->load($html->save()), which
is very inefficient.

Find more information about remove() at
https://simplehtmldom.sourceforge.io/docs/1.9/api/simple_html_dom_node/remove/

bridges/AsahiShimbunAJWBridge.php

@@ -50,18 +50,18 @@ class AsahiShimbunAJWBridge extends BridgeAbstract {
 			$e_lead = $element->find('span.Lead', 0);
 			if ($e_lead) {
 				$item['content'] = $e_lead->innertext;
-				$e_lead->outertext = '';
+				$e_lead->remove();
 			} else {
 				$item['content'] = $element->innertext;
 			}
 			$e_date = $element->find('span.EnDate', 0);
 			if ($e_date) {
 				$item['timestamp'] = strtotime($e_date->innertext);
-				$e_date->outertext = '';
+				$e_date->remove();
 			}
 			$e_video = $element->find('span.EnVideo', 0);
 			if ($e_video) {
-				$e_video->outertext = '';
+				$e_video->remove();
 				$element->innertext = "VIDEO: $element->innertext";
 			}
 			$item['title'] = $element->innertext;

bridges/BundesbankBridge.php

@@ -55,7 +55,7 @@ class BundesbankBridge extends BridgeAbstract {
 			$title = $study->find('.teasable__title div.h2', 0);
 
 			foreach($title->children as &$child) {
-				$child->outertext = '';
+				$child->remove();
 			}
 
 			$item['title'] = $title->innertext;

bridges/CastorusBridge.php

@@ -58,7 +58,7 @@ class CastorusBridge extends BridgeAbstract {
 			returnServerError('Cannot find nodes!');
 
 		foreach($nodes as $node) {
-			$node->outertext = '';
+			$node->remove();
 		}
 
 		return strtotime($activity->innertext);

bridges/DauphineLibereBridge.php

@@ -50,7 +50,7 @@ class DauphineLibereBridge extends FeedExpander {
 	private function extractContent($url){
 		$html2 = getSimpleHTMLDOMCached($url);
 		foreach ($html2->find('.noprint, link, script, iframe, .shareTool, .contentInfo') as $remove) {
-			$remove->outertext = '';
+			$remove->remove();
 		}
 		return $html2->find('div.content', 0)->innertext;
 	}

bridges/EconomistBridge.php

@@ -29,16 +29,16 @@ class EconomistBridge extends BridgeAbstract {
 			// Remove newsletter subscription box
 			$newsletter = $content->find('div[class="newsletter-form__message"]', 0);
 			if ($newsletter)
-				$newsletter->outertext = '';
+				$newsletter->remove();
 
 			$newsletterForm = $content->find('form', 0);
 			if ($newsletterForm)
-				$newsletterForm->outertext = '';
+				$newsletterForm->remove();
 
 			// Remove next and previous article URLs at the bottom
 			$nextprev = $content->find('div[class="blog-post__next-previous-wrapper"]', 0);
 			if ($nextprev)
-				$nextprev->outertext = '';
+				$nextprev->remove();
 
 			$section = [ $article->find('h3[itemprop="articleSection"]', 0)->plaintext ];
 

bridges/FacebookBridge.php

@@ -584,7 +584,7 @@ EOD;
 
 						foreach($content_filters as $filter) {
 							foreach($content->find($filter) as $subject) {
-								$subject->outertext = '';
+								$subject->remove();
 							}
 						}
 

bridges/HaveIBeenPwnedBridge.php

@@ -50,7 +50,7 @@ class HaveIBeenPwnedBridge extends BridgeAbstract {
 			$permalink = $breach->find('p', 1)->find('a', 0)->href;
 
 			// Remove permalink
-			$breach->find('p', 1)->find('a', 0)->outertext = '';
+			$breach->find('p', 1)->find('a', 0)->remove();
 
 			$item['title'] = $breach->find('h3', 0)->plaintext . ' - ' . $accounts[1] . ' breached accounts';
 			$item['dateAdded'] = strtotime($dateAdded[1]);

bridges/JustETFBridge.php

@@ -239,16 +239,16 @@ class JustETFBridge extends BridgeAbstract {
 			or returnServerError('Article body not found!');
 
 		// Remove teaser image
-		$element->find('img.teaser-img', 0)->outertext = '';
+		$element->find('img.teaser-img', 0)->remove();
 
 		// Remove self advertisements
 		foreach($element->find('.call-action') as $adv) {
-			$adv->outertext = '';
+			$adv->remove();
 		}
 
 		// Remove tips
 		foreach($element->find('.panel-edu') as $tip) {
-			$tip->outertext = '';
+			$tip->remove();
 		}
 
 		// Remove inline scripts (used for i.e. interactive graphs) as they are
@@ -318,7 +318,7 @@ class JustETFBridge extends BridgeAbstract {
 		$description = $description->parent();
 
 		foreach($description->find('div') as $div) {
-			$div->outertext = '';
+			$div->remove();
 		}
 
 		$quote = $html->find('div.infobox div.val', 0)

bridges/NextgovBridge.php

@@ -61,7 +61,7 @@ class NextgovBridge extends FeedExpander {
 			return 'Could not request Nextgov: ' . $url;
 
 		$contents = $article->find('div.wysiwyg', 0);
-		$contents->find('svg.content-tombstone', 0)->outertext = '';
+		$contents->find('svg.content-tombstone', 0)->remove();
 		$contents = $contents->innertext;
 		$contents = stripWithDelimiters($contents, '<div class="ad-container">', '</div>');
 		$contents = stripWithDelimiters($contents, '<div', '</div>'); //ad outer div

bridges/OsmAndBlogBridge.php

@@ -51,7 +51,7 @@ class OsmAndBlogBridge extends BridgeAbstract {
 
 	private function cleanupContent($content, ...$removeItems) {
 		foreach ($removeItems as $obj) {
-			if ($obj) $obj->outertext = '';
+			if ($obj) $obj->remove();
 		}
 		foreach ($content->find('img') as $obj) {
 			$obj->src = $this->filterURL($obj->src);

bridges/PikabuBridge.php

@@ -63,7 +63,7 @@ class PikabuBridge extends BridgeAbstract {
 
 			foreach($el_to_remove_selectors as $el_to_remove_selector) {
 				foreach($post->find($el_to_remove_selector) as $el) {
-					$el->outertext = '';
+					$el->remove();
 				}
 			}
 

bridges/RadioMelodieBridge.php

@@ -38,20 +38,17 @@ class RadioMelodieBridge extends BridgeAbstract {
 				$imgs = $textDOM->find('img[src^="http://www.radiomelodie.com/image.php]');
 				foreach($imgs as $img) {
 					$img->src = $this->rewriteImage($img->src);
-					$article->save();
 				}
 
 				// Remove Google Ads
 				$ads = $article->find('div[class=adInline]');
 				foreach($ads as $ad) {
-					$ad->outertext = '';
-					$article->save();
+					$ad->remove();
 				}
 
 				// Remove Radio Melodie Logo
 				$logoHTML = $article->find('div[id=logoArticleRM]', 0);
-				$logoHTML->outertext = '';
-				$article->save();
+				$logoHTML->remove();
 
 				$author = $article->find('p[class=AuthorName]', 0)->plaintext;
 
@@ -65,8 +62,7 @@ class RadioMelodieBridge extends BridgeAbstract {
 				$header = '<img src="' . $picture[0] . '"/>';
 
 				// Remove the Date and Author part
-				$textDOM->find('div[class=AuthorDate]', 0)->outertext = '';
-				$article->save();
+				$textDOM->find('div[class=AuthorDate]', 0)->remove();
 				$text = $textDOM->innertext;
 				$item['content'] = '<h1>' . $item['title'] . '</h1>' . $date . '<br/>' . $header . $text;
 				$this->items[] = $item;

bridges/SIMARBridge.php

@@ -48,7 +48,7 @@ class SIMARBridge extends BridgeAbstract {
 					foreach($e_item->find('p') as $paragraph) {
 						/* Remove empty paragraphs */
 						if (preg_match('/^(\W| )+$/', $paragraph->innertext) == 1) {
-							$paragraph->outertext = '';
+							$paragraph->remove();
 						}
 					}
 					if ($e_item) {

bridges/ScmbBridge.php

@@ -18,7 +18,7 @@ class ScmbBridge extends BridgeAbstract {
 			$item['title'] = $article->find('header h1 a', 0)->innertext;
 
 			// remove text "En savoir plus" from anecdote content
-			$article->find('span.read-more', 0)->outertext = '';
+			$article->find('span.read-more', 0)->remove();
 			$content = $article->find('p.summary a', 0)->innertext;
 
 			// remove superfluous spaces at the end

bridges/TwitterBridge.php

@@ -171,7 +171,7 @@ class TwitterBridge extends BridgeAbstract {
 
 			// remove 'invisible' content
 			foreach($tweet->find('.invisible') as $invisible) {
-				$invisible->outertext = '';
+				$invisible->remove();
 			}
 
 			// Skip protmoted tweets

bridges/VkBridge.php

@@ -62,9 +62,8 @@ class VkBridge extends BridgeAbstract
 			$this->pageName = htmlspecialchars_decode($pageName);
 		}
 		foreach ($html->find('div.replies') as $comment_block) {
-			$comment_block->outertext = '';
+			$comment_block->remove();
 		}
-		$html->load($html->save());
 
 		$pinned_post_item = null;
 		$last_post_id = 0;
@@ -82,7 +81,7 @@ class VkBridge extends BridgeAbstract
 
 			if (is_object($post->find('a.wall_post_more', 0))) {
 				//delete link "show full" in content
-				$post->find('a.wall_post_more', 0)->outertext = '';
+				$post->find('a.wall_post_more', 0)->remove();
 			}
 
 			$content_suffix = '';
@@ -114,7 +113,7 @@ class VkBridge extends BridgeAbstract
 
 			foreach($external_link_selectors_to_remove as $sel) {
 				if (is_object($post->find($sel, 0))) {
-					$post->find($sel, 0)->outertext = '';
+					$post->find($sel, 0)->remove();
 				}
 			}
 
@@ -140,7 +139,7 @@ class VkBridge extends BridgeAbstract
 					$content_suffix .= "<br><img src='" . $matches[1] . "'>";
 				}
 				$content_suffix .= "<br>Article: <a href='$article_link'>$article_title ($article_author)</a>";
-				$article->outertext = '';
+				$article->remove();
 			}
 
 			// get video on post
@@ -150,7 +149,7 @@ class VkBridge extends BridgeAbstract
 				$video_title = $video->find('div.post_video_title', 0)->plaintext;
 				$video_link = $video->find('a.lnk', 0)->getAttribute('href');
 				$this->appendVideo($video_title, $video_link, $content_suffix, $post_videos);
-				$video->outertext = '';
+				$video->remove();
 				$main_video_link = $video_link;
 			}
 
@@ -161,14 +160,14 @@ class VkBridge extends BridgeAbstract
 				if (count($temp) > 1) $video_title = $temp[1];
 				$video_link = $a->getAttribute('href');
 				if ($video_link != $main_video_link) $this->appendVideo($video_title, $video_link, $content_suffix, $post_videos);
-				$a->outertext = '';
+				$a->remove();
 			}
 
 			// get all photos
 			foreach($post->find('div.wall_text > a.page_post_thumb_wrap') as $a) {
 				$result = $this->getPhoto($a);
 				if ($result == null) continue;
-				$a->outertext = '';
+				$a->remove();
 				$content_suffix .= "<br>$result";
 			}
 
@@ -177,7 +176,7 @@ class VkBridge extends BridgeAbstract
 				$a = $el->find('.page_album_link', 0);
 				$album_title = $a->find('.page_album_title_text', 0)->getAttribute('title');
 				$album_link = $a->getAttribute('href');
-				$el->outertext = '';
+				$el->remove();
 				$content_suffix .= "<br>Album: <a href='$album_link'>$album_title</a>";
 			}
 
@@ -200,7 +199,7 @@ class VkBridge extends BridgeAbstract
 
 				}
 
-				$a->outertext = '';
+				$a->remove();
 			}
 
 			// get other documents
@@ -217,7 +216,7 @@ class VkBridge extends BridgeAbstract
 
 				}
 
-				$div->outertext = '';
+				$div->remove();
 			}
 
 			// get polls
@@ -227,14 +226,14 @@ class VkBridge extends BridgeAbstract
 				foreach($div->find('div.page_poll_text') as $poll_stat_title) {
 					$content_suffix .= '<br>- ' . $poll_stat_title->innertext;
 				}
-				$div->outertext = '';
+				$div->remove();
 			}
 
 			// get sign
 			$post_author = $pageName;
 			foreach($post->find('a.wall_signed_by') as $a) {
 				$post_author = $a->innertext;
-				$a->outertext = '';
+				$a->remove();
 			}
 
 			if (is_object($post->find('div.copy_quote', 0))) {
@@ -243,7 +242,7 @@ class VkBridge extends BridgeAbstract
 				}
 				$copy_quote = $post->find('div.copy_quote', 0);
 				if ($copy_post_header = $copy_quote->find('div.copy_post_header', 0)) {
-					$copy_post_header->outertext = '';
+					$copy_post_header->remove();
 				}
 				$copy_quote_content = $copy_quote->innertext;
 				$copy_quote->outertext = "<br>Reposted: <br>$copy_quote_content";

bridges/WikipediaBridge.php

@@ -141,7 +141,7 @@ class WikipediaBridge extends BridgeAbstract {
 	$anchorFallbackIndex = 0){
 		// Clean the bottom of the featured article
 		if ($element->find('div', -1))
-			$element->find('div', -1)->outertext = '';
+			$element->find('div', -1)->remove();
 
 		// The title and URI of the article can be found in an anchor containing
 		// the string '...' in most wikis ('full article ...')
@@ -202,10 +202,10 @@ class WikipediaBridge extends BridgeAbstract {
 		// Let's remove a couple of things from the article
 		$table = $content->find('#toc', 0); // Table of contents
 		if(!$table === false)
-			$table->outertext = '';
+			$table->remove();
 
 		foreach($content->find('ol.references') as $reference) // References
-			$reference->outertext = '';
+			$reference->remove();
 
 		return str_replace('href="/', 'href="' . $this->getURI() . '/', $content->innertext);
 	}

bridges/WordPressBridge.php

@@ -50,7 +50,7 @@ class WordPressBridge extends FeedExpander {
 
 		foreach ($article->find('h1.entry-title') as $title)
 			if ($title->plaintext == $item['title'])
-				$title->outertext = '';
+				$title->remove();
 
 		$article_image = $article_html->find('img.wp-post-image', 0);
 		if(!empty($item['content']) && (!is_object($article_image) || empty($article_image->src))) {

bridges/WorldOfTanksBridge.php

@@ -44,7 +44,7 @@ class WorldOfTanksBridge extends FeedExpander {
 
 		// Remove the scripts, please
 		foreach($content->find('script') as $script) {
-			$script->outertext = '';
+			$script->remove();
 		}
 
 		return $content->innertext;

bridges/XenForoBridge.php

@@ -193,7 +193,7 @@ class XenForoBridge extends BridgeAbstract {
 
 			// Remove script tags
 			foreach($content->find('script') as $script) {
-				$script->outertext = '';
+				$script->remove();
 			}
 
 			$item['content'] = $content->innertext;

lib/html.php

@@ -36,7 +36,7 @@ function sanitize($html,
 		if(in_array($element->tag, $text_to_keep)) {
 			$element->outertext = $element->plaintext;
 		} elseif(in_array($element->tag, $tags_to_remove)) {
-			$element->outertext = '';
+			$element->remove();
 		} else {
 			foreach($element->getAllAttributes() as $attributeName => $attribute) {
 				if(!in_array($attributeName, $attributes_to_keep))