Article css filtering (#4501)

* Update feedController.php

* Update subscriptionController.php

* Update DatabaseDAO.php

* Update Entry.php

* Update Feed.php

* Update FeedDAO.php

* Update install.sql.mysql.php

* Update install.sql.pgsql.php

* Update install.sql.sqlite.php

* Update sub.php

* Update opml.phtml

* Update ImportService.php

* Update update.phtml

* Update feed.js

* Update install.sql.mysql.php

* Update install.sql.pgsql.php

* Update install.sql.sqlite.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update sub.php

* Update FeedDAO.php

* Update feedController.php

* Update subscriptionController.php

* Update Entry.php

* Update Feed.php

* Update feedController.php

* Update subscriptionController.php

* Update ImportService.php

* Update opml.phtml

* Update update.phtml

* Update update.phtml

* Update update.phtml

* Update DatabaseDAO.php

* Update app/Models/Entry.php

Co-authored-by: Alexandre Alapetite <alexandre@alapetite.fr>

* Update app/i18n/fr/sub.php

Co-authored-by: Alexandre Alapetite <alexandre@alapetite.fr>

* Update p/scripts/feed.js

Co-authored-by: Alexandre Alapetite <alexandre@alapetite.fr>

* Update app/Controllers/feedController.php

* make fix-all

* Update documentation

* css_path_filter help message

* i18n en-us ignore

Co-authored-by: Alexandre Alapetite <alexandre@alapetite.fr>

app/Controllers/feedController.php

@@ -916,12 +916,15 @@ class FreshRSS_feed_Controller extends FreshRSS_ActionController {
 			return;
 		}
 
+		$attributes = $feed->attributes();
+		$attributes['path_entries_filter'] = trim(Minz_Request::param('selector_filter', ''));
+
 		//Fetch & select content.
 		try {
 			$fullContent = FreshRSS_Entry::getContentByParsing(
 				htmlspecialchars_decode($entry->link(), ENT_QUOTES),
 				$content_selector,
-				$feed->attributes()
+				$attributes
 			);
 
 			if ($fullContent != '') {

app/Controllers/subscriptionController.php

@@ -209,6 +209,8 @@ class FreshRSS_subscription_Controller extends FreshRSS_ActionController {
 				}
 			}
 
+			$feed->_attributes('path_entries_filter', Minz_Request::param('path_entries_filter', ''));
+
 			$values = array(
 				'name' => Minz_Request::param('name', ''),
 				'kind' => $feed->kind(),

app/Models/Entry.php

@@ -558,6 +558,12 @@ class FreshRSS_Entry extends Minz_Model {
 			$nodes = $xpath->query(new Gt\CssXPath\Translator($path));
 			if ($nodes != false) {
 				foreach ($nodes as $node) {
+					if (!empty($attributes['path_entries_filter'])) {
+						$filterednodes = $xpath->query(new Gt\CssXPath\Translator($attributes['path_entries_filter']), $node);
+						foreach ($filterednodes as $filterednode) {
+							$filterednode->parentNode->removeChild($filterednode);
+						}
+					}
 					$content .= $doc->saveHtml($node) . "\n";
 				}
 			}

app/Services/ImportService.php

@@ -169,6 +169,7 @@ class FreshRSS_Import_Service {
 				if (is_array($value) && !empty($value['value']) && ($value['namespace'] ?? '') === FreshRSS_Export_Service::FRSS_NAMESPACE) {
 					switch ($key) {
 						case 'cssFullContent': $feed->_pathEntries($value['value']); break;
+						case 'cssFullContentFilter': $feed->_attributes('path_entries_filter', $value['value']); break;
 						case 'filtersActionRead': $feed->_filtersAction('read', preg_split('/[\n\r]+/', $value['value'])); break;
 						case 'xPathItem': $xPathSettings['item'] = $value['value']; break;
 						case 'xPathItemTitle': $xPathSettings['itemTitle'] = $value['value']; break;

app/i18n/cz/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Příklad: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'Načte oříznuté kanály RSS (pozor, náročnější na čas!)',
 		'css_path' => 'Přepínač CSS článku na původních webových stránkách',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'Popis',
 		'empty' => 'Tento kanál je prázdný. Ověřte prosím, zda je stále udržován.',
 		'error' => 'Vyskytl se problém s kanálem. Ověřte prosím, že je vždy dostupný, pak ho aktualizujte.',

app/i18n/de/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Beispiel: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'Ruft bei gekürzten RSS-Feeds den vollständigen Artikelinhalt ab (Achtung, benötigt mehr Zeit!)',
 		'css_path' => 'CSS-Selektor des Artikelinhaltes auf der Original-Webseite',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'Beschreibung',
 		'empty' => 'Dieser Feed ist leer. Bitte stellen Sie sicher, dass er noch gepflegt wird.',
 		'error' => 'Dieser Feed ist auf ein Problem gestoßen. Bitte stellen Sie sicher, dass er immer lesbar ist und aktualisieren Sie ihn dann.',

app/i18n/en-us/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Example: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',	// IGNORE
 		'css_help' => 'Retrieves truncated RSS feeds (caution, requires more time!)',	// IGNORE
 		'css_path' => 'Article CSS selector on original website',	// IGNORE
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// IGNORE
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// IGNORE
+		),
 		'description' => 'Description',	// IGNORE
 		'empty' => 'This feed is empty. Please verify that it is still maintained.',	// IGNORE
 		'error' => 'This feed has encountered a problem. Please verify that it is always reachable then update it.',	// IGNORE

app/i18n/en/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Example: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'Retrieves truncated RSS feeds (caution, requires more time!)',
 		'css_path' => 'Article CSS selector on original website',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'Description',
 		'empty' => 'This feed is empty. Please verify that it is still maintained.',
 		'error' => 'This feed has encountered a problem. Please verify that it is always reachable then update it.',

app/i18n/es/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Ejemplo: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'Recibir fuentes RSS truncadas (aviso, ¡necesita más tiempo!)',
 		'css_path' => 'Ruta a la CSS de los artículos en la web original',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'Descripción',
 		'empty' => 'La fuente está vacía. Por favor, verifica que siga activa.',
 		'error' => 'Hay un problema con esta fuente. Por favor, veritica que esté disponible y prueba de nuevo.',

app/i18n/fr/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Exemple : <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'Permet de récupérer les flux tronqués (attention, demande plus de temps !)',
 		'css_path' => 'Sélecteur CSS des articles sur le site d’origine',
+		'css_path_filter' => array(
+			'_' => 'Sélecteur CSS des éléments à supprimer',
+			'help' => 'Un sélecteur CSS peut être une liste comme : <kbd>.footer, .aside</kbd>',
+		),
 		'description' => 'Description',	// IGNORE
 		'empty' => 'Ce flux est vide. Veuillez vérifier qu’il est toujours maintenu.',
 		'error' => 'Ce flux a rencontré un problème. Veuillez vérifier qu’il est toujours accessible puis actualisez-le.',

app/i18n/he/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Example: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',	// TODO
 		'css_help' => 'קבלת הזנות RSS קטומות	(זהירות, לוקח זמן רב יותר!)',
 		'css_path' => 'נתיב הCSS של המאמר באתר המקורי',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'תיאור',
 		'empty' => 'הזנה זו ריקה. אנא ודאו שהיא עדיין מתוחזקת.',
 		'error' => 'הזנה זו נתקלה בשגיאה, אנא ודאו שהיא תקינה ואז נסו שנית.',

app/i18n/it/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Example: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',	// TODO
 		'css_help' => 'In caso di RSS feeds troncati (attenzione, richiede molto tempo!)',
 		'css_path' => 'Percorso del foglio di stile CSS del sito di origine',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'Descrizione',
 		'empty' => 'Questo feed non contiene articoli. Per favore verifica il sito direttamente.',
 		'error' => 'Questo feed ha generato un errore. Per favore verifica se ancora disponibile.',

app/i18n/ja/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => '例: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'あきらめられたRSSフィードを取得します (注意してください、より多くの時間が必要になるでしょう!)',
 		'css_path' => '元のwebサイトの記事のCSS',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => '説明',
 		'empty' => 'このフィードは空です。運営されているかどうかを確認してみてください。',
 		'error' => 'このフィードに問題が発生しました。ここにいつでもアクセスできるかどうかを確認して更新してみてください。',

app/i18n/ko/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => '예시: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => '글의 일부가 포함된 RSS 피드를 가져옵니다 (주의, 시간이 좀 더 걸립니다!)',
 		'css_path' => '웹사이트 상의 글 본문에 해당하는 CSS 경로',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => '설명',
 		'empty' => '이 피드는 비어있습니다. 피드가 계속 운영되고 있는지 확인하세요.',
 		'error' => '이 피드에 문제가 발생했습니다. 이 피드에 접근 권한이 있는지 확인하세요.',

app/i18n/nl/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Voorbeeld: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'Haalt onvolledige RSS-feeds op (attentie, heeft meer tijd nodig!)',
 		'css_path' => 'CSS-pad van artikelen op originele website',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'Omschrijving',
 		'empty' => 'Deze feed is leeg. Controleer of deze nog actueel is.',
 		'error' => 'Deze feed heeft problemen. Verifieer a.u.b het doeladres en actualiseer het.',

app/i18n/oc/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Exemple : <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'Permet de recuperar los fluxes troncats (atencion, demanda mai de temps !)',
 		'css_path' => 'Selector CSS dels articles sul site d’origina',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'Descripcion',	// IGNORE
 		'empty' => 'Aqueste flux es void. Assegurats-vos qu’es totjorn mantengut.',
 		'error' => 'Aqueste flux a rescontrat un problèma. Volgatz verificar que siá totjorn accessible puèi actualizatz-lo.',

app/i18n/pl/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Przykład: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'Pozwala na ograniczenie zawartości kanałów (uwaga, wymaga więcej czasu!)',
 		'css_path' => 'Selektor CSS dla wiadomości na pierwotnej stronie',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'Opis',
 		'empty' => 'Ten kanał jest pusty. Należy sprawdzić czy kanał w dalszym ciągu działa.',
 		'error' => 'Napotkano problem podczas dostępu do tego kanału. Należy sprawdzić czy kanał jest zawsze dostępny, a następnie go odświeżyć.',

app/i18n/pt-br/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Exemplo: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'Retorna RSS feeds truncados (atenção, requer mais tempo!)',
 		'css_path' => 'Caminho do CSS do artigo no site original',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'Descrição',
 		'empty' => 'Este feed está vazio. Por favor verifique ele ainda é mantido.',
 		'error' => 'Este feed encontra-se com problema. Por favor verifique se ele ainda está disponível e atualize-o.',

app/i18n/ru/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Пример: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'Получает усечённые RSS-ленты (осторожно, требует больше времени!)',
 		'css_path' => 'CSS селектор статьи на сайте',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'Описание',
 		'empty' => 'Лента пустая. Пожалуйста, убедитесь, что её до сих пор обслуживают.',
 		'error' => 'С этой лентой возникла проблема. Пожалуйста, убедитесь, что она всегда досягаема. Затем снова обновите её.',

app/i18n/sk/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Príklad: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'Stiahnuť skrátenú verziu RSS kanála (pozor, vyžaduje viac času!)',
 		'css_path' => 'Pôvodný CSS súbor článku z webovej stránky',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'Popis',
 		'empty' => 'Tento kanál je prázdny. Overte, prosím, či je ešte spravovaný autorom.',
 		'error' => 'Vyskytol sa problém s týmto kanálom. Overte, prosím, či kanál stále existuje, potom ho obnovte.',

app/i18n/tr/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => 'Örnek: <kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => 'Dikkat, daha çok zaman gerekir!',
 		'css_path' => 'Makaleleri kendi CSS görünümü ile göster',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => 'Tanım',
 		'empty' => 'Bu akış boş. Lütfen akışın aktif olduğuna emin olun.',
 		'error' => 'Bu akışda bir hatayla karşılaşıldı. Lütfen akışın sürekli ulaşılabilir olduğuna emin olun.',

app/i18n/zh-cn/sub.php

@@ -57,6 +57,10 @@ return array(
 		'css_cookie_help' => '例：<kbd>foo=bar; gdpr_consent=true; cookie=value</kbd>',
 		'css_help' => '用于获取全文（注意，这将耗费更多时间！）',
 		'css_path' => '原文的 CSS 选择器',
+		'css_path_filter' => array(
+			'_' => 'CSS selector of the elements to remove',	// TODO
+			'help' => 'A CSS selector may be a list such as: <kbd>.footer, .aside</kbd>',	// TODO
+		),
 		'description' => '描述',
 		'empty' => '此源为空。请确认它是否正常更新。',
 		'error' => '此源遇到一些问题。请在确认是否能正常访问后重试。',

app/views/helpers/export/opml.phtml

@@ -40,6 +40,9 @@ function feedsToOutlines($feeds, $excludeMutedFeeds = false): array {
 		if ($feed->pathEntries() != '') {
 			$outline['frss:cssFullContent'] = ['namespace' => FreshRSS_Export_Service::FRSS_NAMESPACE, 'value' => $feed->pathEntries()];
 		}
+		if ($feed->attributes('path_entries_filter') != '') {
+			$outline['frss:cssFullContentFilter'] = ['namespace' => FreshRSS_Export_Service::FRSS_NAMESPACE, 'value' => $feed->attributes('path_entries_filter')];
+		}
 		$outlines[] = $outline;
 	}
 	return $outlines;

app/views/helpers/feed/update.phtml

@@ -491,12 +491,26 @@
 					<input type="text" name="path_entries" id="path_entries" class="w100" value="<?= $this->feed->pathEntries() ?>"
 						data-leave-validation="<?= $this->feed->pathEntries() ?>" placeholder="<?= _t('gen.short.blank_to_disable') ?>" />
 					<a id="popup-preview-selector" class="btn" href="<?=
-						_url('feed', 'contentSelectorPreview', 'id', $this->feed->id(), 'selector', 'selector-token', '#', 'slider') ?>"><?= _i('look') ?></a>
+						_url('feed', 'contentSelectorPreview', 'id', $this->feed->id(), 'selector', 'selector-token', 'selector_filter', 'selector-filter-token', '#', 'slider') ?>"><?= _i('look') ?></a>
 				</div>
 				<p class="help"><?= _i('help') ?> <?= _t('sub.feed.css_help') ?></p>
 			</div>
 		</div>
 
+		<div class="form-group">
+			<?php
+				$path_entries_filter = Minz_Helper::htmlspecialchars_utf8($this->feed->attributes('path_entries_filter'));
+			?>
+			<label class="group-name" for="path_entries_filter"><?= _t('sub.feed.css_path_filter') ?></label>
+			<div class="group-controls">
+				<div class="stick w100">
+					<input type="text" name="path_entries_filter" id="path_entries_filter" class="w100" value="<?= $path_entries_filter ?>"
+						data-leave-validation="<?= $path_entries_filter ?>" placeholder="<?= _t('gen.short.blank_to_disable') ?>" />
+				</div>
+				<p class="help"><?= _i('help') ?> <?= _t('sub.feed.css_path_filter.help') ?></p>
+			</div>
+		</div>
+
 		<div class="form-group">
 			<label class="group-name" for="curl_params_cookie"><?= _t('sub.feed.css_cookie') ?></label>
 			<div class="group-controls">

docs/en/developers/OPML.md

@@ -43,7 +43,9 @@ The following attributes are using similar naming conventions than [RSS-Bridge](
 ### Miscellaneous
 
 * `frss:cssFullContent`: [CSS Selector](https://developer.mozilla.org/en-US/docs/Web/CSS/CSS_Selectors) to enable the download and extraction of the matching HTML section of each articles’ Web address.
-	* Example: `div.main`
+	* Example: `div.main, .summary`
+* `frss:cssFullContentFilter`: [CSS Selector](https://developer.mozilla.org/en-US/docs/Web/CSS/CSS_Selectors) to remove the matching HTML elements from the full content retrieved by `frss:cssFullContent`.
+	* Example: `.footer, .aside`
 * `frss:filtersActionRead`: List (separated by a new line) of search queries to automatically mark a new article as read.
 
 ### Dynamic OPML (reading lists)

p/scripts/feed.js

@@ -56,7 +56,9 @@ function init_popup_preview_selector() {
 
 	link.addEventListener('click', function (ev) {
 		const selector_entries = document.getElementById('path_entries').value;
-		const href = link.href.replace('selector-token', encodeURIComponent(selector_entries));
+		const selector_entries_filter = document.getElementById('path_entries_filter').value;
+		const href = link.href.replace('selector-token', encodeURIComponent(selector_entries))
+			.replace('selector-filter-token', encodeURIComponent(selector_entries_filter));
 
 		openPopupWithSource(href);