From 1fe66ad020ca8f0560bb9c6e311852ed77228f78 Mon Sep 17 00:00:00 2001
From: Alexandre Alapetite <alexandre@alapetite.fr>
Date: Mon, 28 Feb 2022 20:22:43 +0100
Subject: Implement Web scraping "HTML + XPath" (#4220)

* More PHP type hints for Fever
Follow-up of https://github.com/FreshRSS/FreshRSS/pull/4201
Related to https://github.com/FreshRSS/FreshRSS/issues/4200

* Detail

* Draft

* Progress

* More draft

* Fix thumbnail PHP type hint
https://github.com/FreshRSS/FreshRSS/issues/4215

* More types

* A bit more

* Refactor FreshRSS_Entry::fromArray

* Progress

* Starts to work

* Categories

* Fonctional

* Layout update

* Fix relative URLs

* Cache system

* Forgotten files

* Remove a debug line

* Automatic form validation of XPath expressions

* data-leave-validation

* Fix reload action

* Simpler examples

* Fix column type for PostgreSQL

* Enforce HTTP encoding

* Readme

* Fix get full content

* target="_blank"

* gitignore

* htmlspecialchars_utf8

* Implement HTML <base>
And fix/revert `xml:base` support in SimplePie https://github.com/simplepie/simplepie/commit/e49c578817aa504d8d05cd7f33857aeda9d41908

* SimplePie upstream PR merged
https://github.com/simplepie/simplepie/pull/723
---
 app/i18n/he/sub.php | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

(limited to 'app/i18n/he/sub.php')

diff --git a/app/i18n/he/sub.php b/app/i18n/he/sub.php
index 1f4dc019f..6068a63c0 100644
--- a/app/i18n/he/sub.php
+++ b/app/i18n/he/sub.php
@@ -61,6 +61,49 @@ return array(
 		),
 		'information' => 'מידע',
 		'keep_min' => 'מסםר מינימלי של מאמרים לשמור',
+		'kind' => array(
+			'_' => 'Type of feed source',	// TODO
+			'html_xpath' => array(
+				'_' => 'HTML + XPath (Web scraping)',	// TODO
+				'feed_title' => array(
+					'_' => 'feed title',	// TODO
+					'help' => 'Example: <code>//title</code> or a static string: <code>"My custom feed"</code>',	// TODO
+				),
+				'help' => '<dfn><a href="https://www.w3.org/TR/xpath-10/" target="_blank">XPath 1.0</a></dfn> is a standard query language for advanced users, and which FreshRSS supports to enable Web scraping.',	// TODO
+				'item' => array(
+					'_' => 'finding news <strong>items</strong><br /><small>(most important)</small>',	// TODO
+					'help' => 'Example: <code>//div[@class="news-item"]</code>',	// TODO
+				),
+				'item_author' => array(
+					'_' => 'item author',	// TODO
+					'help' => 'Can also be a static string. Example: <code>"Anonymous"</code>',	// TODO
+				),
+				'item_categories' => 'items tags',	// TODO
+				'item_content' => array(
+					'_' => 'item content',	// TODO
+					'help' => 'Example to take the full item: <code>.</code>',	// TODO
+				),
+				'item_thumbnail' => array(
+					'_' => 'item thumbnail',	// TODO
+					'help' => 'Example: <code>descendant::img/@src</code>',	// TODO
+				),
+				'item_timestamp' => array(
+					'_' => 'item date',	// TODO
+					'help' => 'The result will be parsed by <a href="https://php.net/strtotime" target="_blank"><code>strtotime()</code></a>',	// TODO
+				),
+				'item_title' => array(
+					'_' => 'item title',	// TODO
+					'help' => 'Use in particular the <a href="https://developer.mozilla.org/docs/Web/XPath/Axes" target="_blank">XPath axis</a> <code>descendant::</code> like <code>descendant::h2</code>',	// TODO
+				),
+				'item_uri' => array(
+					'_' => 'item link (URL)',	// TODO
+					'help' => 'Example: <code>descendant::a/@href</code>',	// TODO
+				),
+				'relative' => 'XPath (relative to item) for:',	// TODO
+				'xpath' => 'XPath for:',	// TODO
+			),
+			'rss' => 'RSS / Atom (default)',	// TODO
+		),
 		'maintenance' => array(
 			'clear_cache' => 'Clear cache',	// TODO
 			'clear_cache_help' => 'Clear the cache for this feed.',	// TODO
-- 
cgit v1.2.3