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/Controllers/subscriptionController.php | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

(limited to 'app/Controllers/subscriptionController.php')

diff --git a/app/Controllers/subscriptionController.php b/app/Controllers/subscriptionController.php
index 7d2c58714..8fa468b8e 100644
--- a/app/Controllers/subscriptionController.php
+++ b/app/Controllers/subscriptionController.php
@@ -192,8 +192,26 @@ class FreshRSS_subscription_Controller extends FreshRSS_ActionController {
 
 			$feed->_filtersAction('read', preg_split('/[\n\r]+/', Minz_Request::param('filteractions_read', '')));
 
+			$feed_kind = Minz_Request::param('feed_kind', FreshRSS_Feed::KIND_RSS);
+			if ($feed_kind == FreshRSS_Feed::KIND_HTML_XPATH) {
+				$xPathSettings = [];
+				if (Minz_Request::param('xPathFeedTitle', '') != '') $xPathSettings['feedTitle'] = Minz_Request::param('xPathFeedTitle', '', true);
+				if (Minz_Request::param('xPathItem', '') != '') $xPathSettings['item'] = Minz_Request::param('xPathItem', '', true);
+				if (Minz_Request::param('xPathItemTitle', '') != '') $xPathSettings['itemTitle'] = Minz_Request::param('xPathItemTitle', '', true);
+				if (Minz_Request::param('xPathItemContent', '') != '') $xPathSettings['itemContent'] = Minz_Request::param('xPathItemContent', '', true);
+				if (Minz_Request::param('xPathItemUri', '') != '') $xPathSettings['itemUri'] = Minz_Request::param('xPathItemUri', '', true);
+				if (Minz_Request::param('xPathItemAuthor', '') != '') $xPathSettings['itemAuthor'] = Minz_Request::param('xPathItemAuthor', '', true);
+				if (Minz_Request::param('xPathItemTimestamp', '') != '') $xPathSettings['itemTimestamp'] = Minz_Request::param('xPathItemTimestamp', '', true);
+				if (Minz_Request::param('xPathItemThumbnail', '') != '') $xPathSettings['itemThumbnail'] = Minz_Request::param('xPathItemThumbnail', '', true);
+				if (Minz_Request::param('xPathItemCategories', '') != '') $xPathSettings['itemCategories'] = Minz_Request::param('xPathItemCategories', '', true);
+				if (!empty($xPathSettings)) {
+					$feed->_attributes('xpath', $xPathSettings);
+				}
+			}
+
 			$values = array(
 				'name' => Minz_Request::param('name', ''),
+				'kind' => $feed_kind,
 				'description' => sanitizeHTML(Minz_Request::param('description', '', true)),
 				'website' => checkUrl(Minz_Request::param('website', '')),
 				'url' => checkUrl(Minz_Request::param('url', '')),
-- 
cgit v1.2.3