From 2880524dfc7685985fde8429c1dcb85387f4ba14 Mon Sep 17 00:00:00 2001
From: Dag <me@dvikan.no>
Date: Fri, 13 Oct 2023 01:59:05 +0200
Subject: [PATCH] refactor: remove parent calls to parseItem (#3747)
---
bridges/AcrimedBridge.php | 4 +-
bridges/ArsTechnicaBridge.php | 4 +-
bridges/BleepingComputerBridge.php | 4 +-
bridges/CNETFranceBridge.php | 4 +-
bridges/CaschyBridge.php | 4 +-
bridges/CommonDreamsBridge.php | 3 +-
bridges/CourrierInternationalBridge.php | 4 +-
bridges/DarkReadingBridge.php | 4 +-
bridges/DauphineLibereBridge.php | 3 +-
bridges/DeutscheWelleBridge.php | 4 +-
bridges/DeveloppezDotComBridge.php | 4 +-
bridges/EconomistBridge.php | 3 +-
bridges/EngadgetBridge.php | 4 +-
bridges/EsquerdaNetBridge.php | 4 +-
bridges/FeedExpanderTestBridge.php | 6 +-
bridges/FilterBridge.php | 4 +-
bridges/FolhaDeSaoPauloBridge.php | 4 +-
bridges/ForGifsBridge.php | 4 +-
bridges/FreeCodeCampBridge.php | 4 +-
bridges/FuturaSciencesBridge.php | 4 +-
bridges/GizmodoBridge.php | 4 +-
bridges/GolemBridge.php | 3 +-
bridges/HardwareInfoBridge.php | 4 +-
bridges/HeiseBridge.php | 4 +-
bridges/IGNBridge.php | 4 +-
bridges/KoreusBridge.php | 4 +-
bridges/LeMondeInformatiqueBridge.php | 4 +-
bridges/ListverseBridge.php | 3 +-
bridges/MediapartBridge.php | 4 +-
bridges/MsnMondeBridge.php | 4 +-
bridges/NYTBridge.php | 4 +-
bridges/NextInpactBridge.php | 4 +-
bridges/NextgovBridge.php | 4 +-
bridges/NiceMatinBridge.php | 4 +-
bridges/OnVaSortirBridge.php | 3 +-
bridges/PhoronixBridge.php | 4 +-
bridges/QwantzBridge.php | 6 +-
bridges/RaceDepartmentBridge.php | 4 +-
bridges/ScribbleHubBridge.php | 4 +-
bridges/SplCenterBridge.php | 4 +-
bridges/TapasBridge.php | 4 +-
bridges/TheGuardianBridge.php | 4 +-
bridges/TwitterEngineeringBridge.php | 4 +-
bridges/VarietyBridge.php | 4 +-
bridges/ViceBridge.php | 4 +-
bridges/WeLiveSecurityBridge.php | 4 +-
bridges/WiredBridge.php | 4 +-
bridges/WordPressBridge.php | 4 +-
bridges/WorldOfTanksBridge.php | 3 +-
bridges/ZDNetBridge.php | 4 +-
bridges/ZeitBridge.php | 4 +-
docs/05_Bridge_API/03_FeedExpander.md | 90 ++++++-------------------
docs/05_Bridge_API/index.md | 2 +-
lib/FeedExpander.php | 88 +++++-------------------
lib/FeedParser.php | 8 +--
55 files changed, 96 insertions(+), 293 deletions(-)
diff --git a/bridges/AcrimedBridge.php b/bridges/AcrimedBridge.php
index 93890f35..f7bbd58e 100644
--- a/bridges/AcrimedBridge.php
+++ b/bridges/AcrimedBridge.php
@@ -25,10 +25,8 @@ class AcrimedBridge extends FeedExpander
$this->collectExpandableDatas($url, $limit);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$articlePage = getSimpleHTMLDOM($item['uri']);
$article = sanitize($articlePage->find('article.article1', 0)->innertext);
$article = defaultLinkTo($article, static::URI);
diff --git a/bridges/ArsTechnicaBridge.php b/bridges/ArsTechnicaBridge.php
index 98e5566b..d15cfb4f 100644
--- a/bridges/ArsTechnicaBridge.php
+++ b/bridges/ArsTechnicaBridge.php
@@ -33,10 +33,8 @@ class ArsTechnicaBridge extends FeedExpander
$this->collectExpandableDatas($url);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$item_html = getSimpleHTMLDOMCached($item['uri'] . '&');
$item_html = defaultLinkTo($item_html, self::URI);
$item['content'] = $item_html->find('.amp-wp-article-content', 0);
diff --git a/bridges/BleepingComputerBridge.php b/bridges/BleepingComputerBridge.php
index bad78561..79d84176 100644
--- a/bridges/BleepingComputerBridge.php
+++ b/bridges/BleepingComputerBridge.php
@@ -13,10 +13,8 @@ class BleepingComputerBridge extends FeedExpander
$this->collectExpandableDatas($feed);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$article_html = getSimpleHTMLDOMCached($item['uri']);
if (!$article_html) {
$item['content'] .= '<p><em>Could not request ' . $this->getName() . ': ' . $item['uri'] . '</em></p>';
diff --git a/bridges/CNETFranceBridge.php b/bridges/CNETFranceBridge.php
index d6a766de..35e92daf 100644
--- a/bridges/CNETFranceBridge.php
+++ b/bridges/CNETFranceBridge.php
@@ -43,10 +43,8 @@ class CNETFranceBridge extends FeedExpander
$this->collectExpandableDatas('https://www.cnetfrance.fr/feeds/rss/news/');
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
foreach ($this->bannedTitle as $term) {
if (preg_match('/' . $term . '/mi', $item['title']) === 1) {
return null;
diff --git a/bridges/CaschyBridge.php b/bridges/CaschyBridge.php
index 7d632bf6..0e3a07bc 100644
--- a/bridges/CaschyBridge.php
+++ b/bridges/CaschyBridge.php
@@ -34,10 +34,8 @@ class CaschyBridge extends FeedExpander
);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
if (strpos($item['uri'], 'https://stadt-bremerhaven.de/') !== 0) {
return $item;
}
diff --git a/bridges/CommonDreamsBridge.php b/bridges/CommonDreamsBridge.php
index e1a185de..34532284 100644
--- a/bridges/CommonDreamsBridge.php
+++ b/bridges/CommonDreamsBridge.php
@@ -12,9 +12,8 @@ class CommonDreamsBridge extends FeedExpander
$this->collectExpandableDatas('http://www.commondreams.org/rss.xml', 10);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
$item['content'] = $this->extractContent($item['uri']);
return $item;
}
diff --git a/bridges/CourrierInternationalBridge.php b/bridges/CourrierInternationalBridge.php
index 9e30fd51..3d9889b0 100644
--- a/bridges/CourrierInternationalBridge.php
+++ b/bridges/CourrierInternationalBridge.php
@@ -13,10 +13,8 @@ class CourrierInternationalBridge extends FeedExpander
$this->collectExpandableDatas(static::URI . 'feed/all/rss.xml', 20);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$articlePage = getSimpleHTMLDOMCached($item['uri']);
$content = $articlePage->find('.article-text, depeche-text', 0);
if (!$content) {
diff --git a/bridges/DarkReadingBridge.php b/bridges/DarkReadingBridge.php
index aca30490..4f1622e3 100644
--- a/bridges/DarkReadingBridge.php
+++ b/bridges/DarkReadingBridge.php
@@ -56,10 +56,8 @@ class DarkReadingBridge extends FeedExpander
$this->collectExpandableDatas($feed_url, $limit);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$article = getSimpleHTMLDOMCached($item['uri']);
$item['content'] = $this->extractArticleContent($article);
$item['enclosures'] = []; //remove author profile picture
diff --git a/bridges/DauphineLibereBridge.php b/bridges/DauphineLibereBridge.php
index 0ab808cd..05748a5d 100644
--- a/bridges/DauphineLibereBridge.php
+++ b/bridges/DauphineLibereBridge.php
@@ -43,9 +43,8 @@ class DauphineLibereBridge extends FeedExpander
$this->collectExpandableDatas($url, 10);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
$item['content'] = $this->extractContent($item['uri']);
return $item;
}
diff --git a/bridges/DeutscheWelleBridge.php b/bridges/DeutscheWelleBridge.php
index 2e10d670..29b478b9 100644
--- a/bridges/DeutscheWelleBridge.php
+++ b/bridges/DeutscheWelleBridge.php
@@ -71,10 +71,8 @@ class DeutscheWelleBridge extends FeedExpander
$this->collectExpandableDatas($this->getInput('feed'));
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$parsedUrl = parse_url($item['uri']);
unset($parsedUrl['query']);
$url = $this->unparseUrl($parsedUrl);
diff --git a/bridges/DeveloppezDotComBridge.php b/bridges/DeveloppezDotComBridge.php
index 9dcbc31a..d9583fed 100644
--- a/bridges/DeveloppezDotComBridge.php
+++ b/bridges/DeveloppezDotComBridge.php
@@ -176,10 +176,8 @@ class DeveloppezDotComBridge extends FeedExpander
* Parse the content of every RSS item. And will try to get the full article
* pointed by the item URL intead of the default abstract.
*/
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
if (count($this->items) >= $this->getInput('limit')) {
return null;
}
diff --git a/bridges/EconomistBridge.php b/bridges/EconomistBridge.php
index 0572ab8f..aad72275 100644
--- a/bridges/EconomistBridge.php
+++ b/bridges/EconomistBridge.php
@@ -97,9 +97,8 @@ class EconomistBridge extends FeedExpander
$this->collectExpandableDatas($url, $limit);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
$dom = getSimpleHTMLDOM($item['uri']);
$article = $dom->find('#new-article-template', 0);
diff --git a/bridges/EngadgetBridge.php b/bridges/EngadgetBridge.php
index 3253cc2e..b9861b40 100644
--- a/bridges/EngadgetBridge.php
+++ b/bridges/EngadgetBridge.php
@@ -15,10 +15,8 @@ class EngadgetBridge extends FeedExpander
$this->collectExpandableDatas($url, $max);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$itemUrl = trim($item['uri']);
if (!$itemUrl) {
return $item;
diff --git a/bridges/EsquerdaNetBridge.php b/bridges/EsquerdaNetBridge.php
index 64a6949f..aa92aa38 100644
--- a/bridges/EsquerdaNetBridge.php
+++ b/bridges/EsquerdaNetBridge.php
@@ -31,10 +31,8 @@ class EsquerdaNetBridge extends FeedExpander
parent::collectExpandableDatas($this->getURI());
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$html = getSimpleHTMLDOMCached($item['uri']);
$content = $html->find('div#content div.content', 0);
## Fix author
diff --git a/bridges/FeedExpanderTestBridge.php b/bridges/FeedExpanderTestBridge.php
index 9a6e7bb7..65b3db89 100644
--- a/bridges/FeedExpanderTestBridge.php
+++ b/bridges/FeedExpanderTestBridge.php
@@ -14,9 +14,9 @@ class FeedExpanderTestBridge extends FeedExpander
public function collectData()
{
$url = 'http://static.userland.com/gems/backend/sampleRss.xml'; // rss 0.91
- //$url = 'http://feeds.nature.com/nature/rss/current?format=xml'; // rss 1.0
- //$url = 'https://dvikan.no/feed.xml'; // rss 2.0
- //$url = 'https://nedlasting.geonorge.no/geonorge/Tjenestefeed.xml'; // atom
+ $url = 'http://feeds.nature.com/nature/rss/current?format=xml'; // rss 1.0
+ $url = 'https://dvikan.no/feed.xml'; // rss 2.0
+ $url = 'https://nedlasting.geonorge.no/geonorge/Tjenestefeed.xml'; // atom
$this->collectExpandableDatas($url);
}
diff --git a/bridges/FilterBridge.php b/bridges/FilterBridge.php
index 3e3e812d..1add47f4 100644
--- a/bridges/FilterBridge.php
+++ b/bridges/FilterBridge.php
@@ -82,10 +82,8 @@ class FilterBridge extends FeedExpander
$this->collectExpandableDatas($this->getURI());
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
// Generate title from first 50 characters of content?
if ($this->getInput('title_from_content') && array_key_exists('content', $item)) {
$content = str_get_html($item['content']);
diff --git a/bridges/FolhaDeSaoPauloBridge.php b/bridges/FolhaDeSaoPauloBridge.php
index d8d93c4f..dba86c52 100644
--- a/bridges/FolhaDeSaoPauloBridge.php
+++ b/bridges/FolhaDeSaoPauloBridge.php
@@ -29,10 +29,8 @@ class FolhaDeSaoPauloBridge extends FeedExpander
]
];
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
if ($this->getInput('deep_crawl')) {
$articleHTMLContent = getSimpleHTMLDOMCached($item['uri']);
if ($articleHTMLContent) {
diff --git a/bridges/ForGifsBridge.php b/bridges/ForGifsBridge.php
index e210124a..0a054930 100644
--- a/bridges/ForGifsBridge.php
+++ b/bridges/ForGifsBridge.php
@@ -12,10 +12,8 @@ class ForGifsBridge extends FeedExpander
$this->collectExpandableDatas('https://forgifs.com/gallery/srss/7');
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$dom = str_get_html($item['content']);
$img = $dom->find('img', 0);
$poster = $img->src;
diff --git a/bridges/FreeCodeCampBridge.php b/bridges/FreeCodeCampBridge.php
index 141746d2..aaeaf7bd 100644
--- a/bridges/FreeCodeCampBridge.php
+++ b/bridges/FreeCodeCampBridge.php
@@ -14,10 +14,8 @@ class FreeCodeCampBridge extends FeedExpander
$this->collectExpandableDatas('https://www.freecodecamp.org/news/rss/', 15);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$dom = getSimpleHTMLDOM($item['uri']);
// figure contain's the main article image
diff --git a/bridges/FuturaSciencesBridge.php b/bridges/FuturaSciencesBridge.php
index cfb2d711..6420f319 100644
--- a/bridges/FuturaSciencesBridge.php
+++ b/bridges/FuturaSciencesBridge.php
@@ -85,10 +85,8 @@ class FuturaSciencesBridge extends FeedExpander
$this->collectExpandableDatas($url, 10);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$item['uri'] = str_replace('#xtor%3DRSS-8', '', $item['uri']);
$dom = getSimpleHTMLDOMCached($item['uri']);
$item['content'] = $this->extractArticleContent($dom);
diff --git a/bridges/GizmodoBridge.php b/bridges/GizmodoBridge.php
index 8ed30704..52812d33 100644
--- a/bridges/GizmodoBridge.php
+++ b/bridges/GizmodoBridge.php
@@ -8,10 +8,8 @@ class GizmodoBridge extends FeedExpander
const CACHE_TIMEOUT = 1800; // 30min
const DESCRIPTION = 'Returns the newest posts from Gizmodo.';
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$html = getSimpleHTMLDOMCached($item['uri']);
$html = defaultLinkTo($html, $this->getURI());
diff --git a/bridges/GolemBridge.php b/bridges/GolemBridge.php
index 96fa4506..6699e433 100644
--- a/bridges/GolemBridge.php
+++ b/bridges/GolemBridge.php
@@ -63,9 +63,8 @@ class GolemBridge extends FeedExpander
);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
$item['content'] ??= '';
$uri = $item['uri'];
diff --git a/bridges/HardwareInfoBridge.php b/bridges/HardwareInfoBridge.php
index 6a47df66..5970ecd0 100644
--- a/bridges/HardwareInfoBridge.php
+++ b/bridges/HardwareInfoBridge.php
@@ -12,10 +12,8 @@ class HardwareInfoBridge extends FeedExpander
$this->collectExpandableDatas('https://nl.hardware.info/updates/all.rss', 10);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$itemUrl = $item['uri'];
$articlePage = getSimpleHTMLDOMCached($itemUrl);
diff --git a/bridges/HeiseBridge.php b/bridges/HeiseBridge.php
index 434e7514..f89594ee 100644
--- a/bridges/HeiseBridge.php
+++ b/bridges/HeiseBridge.php
@@ -125,10 +125,8 @@ class HeiseBridge extends FeedExpander
);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$sessioncookie = $this->getInput('sessioncookie');
// strip rss parameter
diff --git a/bridges/IGNBridge.php b/bridges/IGNBridge.php
index c0260cbd..e063dbbb 100644
--- a/bridges/IGNBridge.php
+++ b/bridges/IGNBridge.php
@@ -15,10 +15,8 @@ class IGNBridge extends FeedExpander
// IGNs feed is both hidden and incomplete. This bridge tries to fix this.
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$articlePage = getSimpleHTMLDOM($item['uri']);
// List of BS elements
diff --git a/bridges/KoreusBridge.php b/bridges/KoreusBridge.php
index 874c2c92..5ef5e11f 100644
--- a/bridges/KoreusBridge.php
+++ b/bridges/KoreusBridge.php
@@ -7,10 +7,8 @@ class KoreusBridge extends FeedExpander
const URI = 'https://www.koreus.com/';
const DESCRIPTION = 'Returns the newest posts from Koreus (full text)';
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$html = getSimpleHTMLDOMCached($item['uri']);
$text = $html->find('p.itemText', 0)->innertext;
$item['content'] = utf8_encode($text);
diff --git a/bridges/LeMondeInformatiqueBridge.php b/bridges/LeMondeInformatiqueBridge.php
index c91a0437..860c0887 100644
--- a/bridges/LeMondeInformatiqueBridge.php
+++ b/bridges/LeMondeInformatiqueBridge.php
@@ -12,10 +12,8 @@ class LeMondeInformatiqueBridge extends FeedExpander
$this->collectExpandableDatas(self::URI . 'rss/rss.xml', 10);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$article_html = getSimpleHTMLDOMCached($item['uri']);
//Deduce thumbnail URL from article image URL
diff --git a/bridges/ListverseBridge.php b/bridges/ListverseBridge.php
index b7acbdd0..bffa4cda 100644
--- a/bridges/ListverseBridge.php
+++ b/bridges/ListverseBridge.php
@@ -13,9 +13,8 @@ class ListverseBridge extends FeedExpander
$this->collectExpandableDatas('https://listverse.com/feed/', 15);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
$dom = getSimpleHTMLDOM($item['uri']);
$article = $dom->find('#articlecontentonly', 0);
$item['content'] = $article;
diff --git a/bridges/MediapartBridge.php b/bridges/MediapartBridge.php
index c4deda61..aa10e159 100644
--- a/bridges/MediapartBridge.php
+++ b/bridges/MediapartBridge.php
@@ -29,10 +29,8 @@ class MediapartBridge extends FeedExpander
$this->collectExpandableDatas($url);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$itemUrl = $item['uri'];
// Mediapart provide multiple type of contents.
diff --git a/bridges/MsnMondeBridge.php b/bridges/MsnMondeBridge.php
index 9b308b99..a2592702 100644
--- a/bridges/MsnMondeBridge.php
+++ b/bridges/MsnMondeBridge.php
@@ -25,10 +25,8 @@ class MsnMondeBridge extends FeedExpander
$this->collectExpandableDatas(self::FEED_URL, 10);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
if (!preg_match('#fr-fr/actualite.*/ar-(?<id>[\w]*)\?#', $item['uri'], $matches)) {
return null;
}
diff --git a/bridges/NYTBridge.php b/bridges/NYTBridge.php
index 57c3e2af..a9942e2d 100644
--- a/bridges/NYTBridge.php
+++ b/bridges/NYTBridge.php
@@ -14,10 +14,8 @@ class NYTBridge extends FeedExpander
$this->collectExpandableDatas($url, 40);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$article = '';
try {
diff --git a/bridges/NextInpactBridge.php b/bridges/NextInpactBridge.php
index 0260da14..6982c104 100644
--- a/bridges/NextInpactBridge.php
+++ b/bridges/NextInpactBridge.php
@@ -88,10 +88,8 @@ class NextInpactBridge extends FeedExpander
$this->collectExpandableDatas($url, $limit);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$item['content'] = $this->extractContent($item, $item['uri']);
if (is_null($item['content'])) {
return null; //Filtered article
diff --git a/bridges/NextgovBridge.php b/bridges/NextgovBridge.php
index bc92d306..7fe7130a 100644
--- a/bridges/NextgovBridge.php
+++ b/bridges/NextgovBridge.php
@@ -31,10 +31,8 @@ class NextgovBridge extends FeedExpander
$this->collectExpandableDatas($url, $limit);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$article_thumbnail = 'https://cdn.nextgov.com/nextgov/images/logo.png';
$item['content'] = '<p><b>' . $item['content'] . '</b></p>';
diff --git a/bridges/NiceMatinBridge.php b/bridges/NiceMatinBridge.php
index bcebbbbb..dd90dbfe 100644
--- a/bridges/NiceMatinBridge.php
+++ b/bridges/NiceMatinBridge.php
@@ -12,10 +12,8 @@ class NiceMatinBridge extends FeedExpander
$this->collectExpandableDatas(self::URI . 'derniere-minute/rss', 10);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$item['content'] = $this->extractContent($item['uri']);
return $item;
}
diff --git a/bridges/OnVaSortirBridge.php b/bridges/OnVaSortirBridge.php
index 9f9a750c..f8c395c1 100644
--- a/bridges/OnVaSortirBridge.php
+++ b/bridges/OnVaSortirBridge.php
@@ -123,9 +123,8 @@ class OnVaSortirBridge extends FeedExpander
$this->collectExpandableDatas($url);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
$dom = getSimpleHTMLDOMCached($item['uri']);
$text = $dom->find('div.corpsMax', 0)->innertext;
$item['content'] = utf8_encode($text);
diff --git a/bridges/PhoronixBridge.php b/bridges/PhoronixBridge.php
index fc0d78e5..227685e0 100644
--- a/bridges/PhoronixBridge.php
+++ b/bridges/PhoronixBridge.php
@@ -29,10 +29,8 @@ but some RSS readers don\'t support this. "img" tag are supported by most browse
$this->collectExpandableDatas('https://www.phoronix.com/rss.php', $this->getInput('n'));
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$itemUrl = $item['uri'];
$articlePage = getSimpleHTMLDOM($itemUrl);
diff --git a/bridges/QwantzBridge.php b/bridges/QwantzBridge.php
index 2117c33c..b975bd43 100644
--- a/bridges/QwantzBridge.php
+++ b/bridges/QwantzBridge.php
@@ -11,14 +11,12 @@ class QwantzBridge extends FeedExpander
$this->collectExpandableDatas(self::URI . 'rssfeed.php');
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$item['author'] = 'Ryan North';
preg_match('/title="(.*?)"/', $item['content'], $matches);
- $title = $matches[1];
+ $title = $matches[1] ?? '';
$content = str_get_html(html_entity_decode($item['content']));
$comicURL = $content->find('img')[0]->{'src'};
diff --git a/bridges/RaceDepartmentBridge.php b/bridges/RaceDepartmentBridge.php
index 3783b53e..7390761f 100644
--- a/bridges/RaceDepartmentBridge.php
+++ b/bridges/RaceDepartmentBridge.php
@@ -12,10 +12,8 @@ class RaceDepartmentBridge extends FeedExpander
$this->collectExpandableDatas('https://www.racedepartment.com/ams/index.rss', 10);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$articlePage = getSimpleHTMLDOMCached($item['uri']);
$coverImage = $articlePage->find('img.js-articleCoverImage', 0);
diff --git a/bridges/ScribbleHubBridge.php b/bridges/ScribbleHubBridge.php
index 8f52d461..e7cdf337 100644
--- a/bridges/ScribbleHubBridge.php
+++ b/bridges/ScribbleHubBridge.php
@@ -42,10 +42,8 @@ class ScribbleHubBridge extends FeedExpander
$this->collectExpandableDatas($url);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
//For series, filter out other series from 'All' feed
if (
$this->queriedContext === 'Series'
diff --git a/bridges/SplCenterBridge.php b/bridges/SplCenterBridge.php
index ca764846..af25ec48 100644
--- a/bridges/SplCenterBridge.php
+++ b/bridges/SplCenterBridge.php
@@ -27,10 +27,8 @@ class SplCenterBridge extends FeedExpander
$this->collectExpandableDatas($url);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$articleHtml = getSimpleHTMLDOMCached($item['uri']);
foreach ($articleHtml->find('.file') as $index => $media) {
diff --git a/bridges/TapasBridge.php b/bridges/TapasBridge.php
index ddfbfb92..19995a23 100644
--- a/bridges/TapasBridge.php
+++ b/bridges/TapasBridge.php
@@ -43,10 +43,8 @@ class TapasBridge extends FeedExpander
$this->collectExpandableDatas($this->getURI());
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
// $namespaces = $feedItem->getNamespaces(true);
// if (isset($namespaces['content'])) {
// $description = $feedItem->children($namespaces['content']);
diff --git a/bridges/TheGuardianBridge.php b/bridges/TheGuardianBridge.php
index 98e56506..ac8a9661 100644
--- a/bridges/TheGuardianBridge.php
+++ b/bridges/TheGuardianBridge.php
@@ -56,10 +56,8 @@ class TheGuardianBridge extends FeedExpander
$this->collectExpandableDatas($url, 10);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$articlePage = getSimpleHTMLDOM($item['uri']);
// figure contain's the main article image
$article = $articlePage->find('figure', 0);
diff --git a/bridges/TwitterEngineeringBridge.php b/bridges/TwitterEngineeringBridge.php
index b98cfb87..96319c97 100644
--- a/bridges/TwitterEngineeringBridge.php
+++ b/bridges/TwitterEngineeringBridge.php
@@ -14,10 +14,8 @@ class TwitterEngineeringBridge extends FeedExpander
$this->collectExpandableDatas($url);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$dom = getSimpleHTMLDOMCached($item['uri']);
if (!$dom) {
$item['content'] .= '<p><em>Could not request ' . $this->getName() . ': ' . $item['uri'] . '</em></p>';
diff --git a/bridges/VarietyBridge.php b/bridges/VarietyBridge.php
index 6625dca2..a49ea353 100644
--- a/bridges/VarietyBridge.php
+++ b/bridges/VarietyBridge.php
@@ -13,10 +13,8 @@ class VarietyBridge extends FeedExpander
$this->collectExpandableDatas('https://feeds.feedburner.com/variety/headlines', 15);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
- // $articlePage gets the entire page's contents
$articlePage = getSimpleHTMLDOM($item['uri']);
// Remove Script tags
diff --git a/bridges/ViceBridge.php b/bridges/ViceBridge.php
index c7ecec33..dd81c559 100644
--- a/bridges/ViceBridge.php
+++ b/bridges/ViceBridge.php
@@ -32,10 +32,8 @@ class ViceBridge extends FeedExpander
$this->collectExpandableDatas($feedURL, 10);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$articlePage = getSimpleHTMLDOM($item['uri']);
// text and embedded content
$article = $articlePage->find('.article__body', 0);
diff --git a/bridges/WeLiveSecurityBridge.php b/bridges/WeLiveSecurityBridge.php
index f54f6b29..151484c4 100644
--- a/bridges/WeLiveSecurityBridge.php
+++ b/bridges/WeLiveSecurityBridge.php
@@ -12,10 +12,8 @@ class WeLiveSecurityBridge extends FeedExpander
],
];
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$html = getSimpleHTMLDOMCached($item['uri']);
if (!$html) {
$item['content'] .= '<br /><p><em>Could not request ' . $this->getName() . ': ' . $item['uri'] . '</em></p>';
diff --git a/bridges/WiredBridge.php b/bridges/WiredBridge.php
index 7f7f6051..f7da288c 100644
--- a/bridges/WiredBridge.php
+++ b/bridges/WiredBridge.php
@@ -50,10 +50,8 @@ class WiredBridge extends FeedExpander
$this->collectExpandableDatas($feed_url, $limit);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$originalContent = $item['content'];
$article = getSimpleHTMLDOMCached($item['uri']);
diff --git a/bridges/WordPressBridge.php b/bridges/WordPressBridge.php
index fb27eb31..84a6b8ab 100644
--- a/bridges/WordPressBridge.php
+++ b/bridges/WordPressBridge.php
@@ -34,10 +34,8 @@ class WordPressBridge extends FeedExpander
}
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$dom = getSimpleHTMLDOMCached($item['uri']);
// Find article body
diff --git a/bridges/WorldOfTanksBridge.php b/bridges/WorldOfTanksBridge.php
index 52691025..7bf20015 100644
--- a/bridges/WorldOfTanksBridge.php
+++ b/bridges/WorldOfTanksBridge.php
@@ -30,9 +30,8 @@ class WorldOfTanksBridge extends FeedExpander
$this->collectExpandableDatas(sprintf('https://worldoftanks.eu/%s/rss/news/', $this->getInput('lang')));
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
$item['content'] = $this->loadFullArticle($item['uri']);
return $item;
}
diff --git a/bridges/ZDNetBridge.php b/bridges/ZDNetBridge.php
index 00b272ce..e3b659a8 100644
--- a/bridges/ZDNetBridge.php
+++ b/bridges/ZDNetBridge.php
@@ -174,10 +174,8 @@ class ZDNetBridge extends FeedExpander
$this->collectExpandableDatas($url, $limit);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$article = getSimpleHTMLDOMCached($item['uri']);
if (!$article) {
$this->logger->info('Unable to parse the dom from ' . $item['uri']);
diff --git a/bridges/ZeitBridge.php b/bridges/ZeitBridge.php
index 7d7e89aa..0ed9276b 100644
--- a/bridges/ZeitBridge.php
+++ b/bridges/ZeitBridge.php
@@ -59,10 +59,8 @@ class ZeitBridge extends FeedExpander
$this->collectExpandableDatas($url, $limit);
}
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- $item = parent::parseItem($item);
-
$item['enclosures'] = [];
$headers = [
diff --git a/docs/05_Bridge_API/03_FeedExpander.md b/docs/05_Bridge_API/03_FeedExpander.md
index 910d1abb..62356fc9 100644
--- a/docs/05_Bridge_API/03_FeedExpander.md
+++ b/docs/05_Bridge_API/03_FeedExpander.md
@@ -1,85 +1,35 @@
-`FeedExpander` extends [`BridgeAbstract`](./02_BridgeAbstract.md) and adds functions to collect data from existing feeds.
-
**Usage example**: _You have discovered a site that provides feeds which are hidden and inaccessible by normal means. You want your bridge to directly read the feeds and provide them via **RSS-Bridge**_
-To create a new Bridge extending `FeedExpander` you must implement all required functions of [`BridgeAbstract`](./02_BridgeAbstract.md). `FeedExpander` additionally provides following functions:
-
-* [`parseItem`](#the-parseitem-function)
-* [`getName`](#the-getname-function)
-* [`getURI`](#the-geturi-function)
-* [`getDescription`](#the-getdescription-function)
-
Find a [template](#template) at the end of this file.
**Notice:** For a standard feed only `collectData` need to be implemented. `collectData` should call `$this->collectExpandableDatas('your URI here');` to automatically load feed items and header data (will subsequently call `parseItem` for each item in the feed). You can limit the number of items to fetch by specifying an additional parameter for: `$this->collectExpandableDatas('your URI here', 10)` (limited to 10 items).
-## The `parseItem` function
+## The `parseItem` method
-This function receives one item from the current feed and should return one **RSS-Bridge** item.
+This method receives one item from the current feed and should return one **RSS-Bridge** item.
The default function does all the work to get the item data from the feed, whether it is RSS 1.0,
-RSS 2.0 or Atom 1.0. If you have to redefine this function in your **RSS-Bridge** for whatever reason,
-you should first call the parent function to initialize the item, then apply the changes that you require.
+RSS 2.0 or Atom 1.0.
**Notice:** The following code sample is just an example. Implementation depends on your requirements!
```PHP
-protected function parseItem($feedItem){
- $item = parent::parseItem($feedItem);
- $item['content'] = str_replace('rssbridge','RSS-Bridge',$feedItem->content);
-
+protected function parseItem(array $item)
+{
+ $item['content'] = str_replace('rssbridge','RSS-Bridge',$item['content']);
return $item;
}
```
-### Helper functions
+### Feed parsing
-The `FeedExpander` already provides a set of functions to parse RSS or Atom items based on the specifications. Where possible make use of these functions:
-
-Function | Description
----------|------------
-`parseATOMItem` | Parses an Atom 1.0 feed item
-`parseRSS_0_9_1_Item` | Parses an RSS 0.91 feed item
-`parseRSS_1_0_Item` | Parses an RSS 1.0 feed item
-`parseRSS_2_0_Item` | Parses an RSS 2.0 feed item
-
-In the following list you'll find the feed tags assigned to the the **RSS-Bridge** item keys:
+How rss-bridge processes xml feeds:
Function | uri | title | timestamp | author | content
---------|-----|-------|-----------|--------|--------
-`parseATOMItem` | id | title | updated | author | content
-`parseRSS_0_9_1_Item` | link | title | | | description
-`parseRSS_1_0_Item` | link | title | dc:date | dc:creator | description
-`parseRSS_2_0_Item` | link, guid | title | pubDate, dc:date | author, dc:creator | description
-
-## The `getName` function
-
-Returns the name of the current feed.
-
-```PHP
-return $this->name;
-```
-
-**Notice:** Only implement this function if you require different behavior!
-
-## The `getURI` function
-
-Return the uri for the current feed.
-
-```PHP
-return $this->uri;
-```
-
-**Notice:** Only implement this function if you require different behavior!
-
-## The `getDescription` function
-
-Returns the description for the current bridge.
-
-```PHP
-return $this->description;
-```
-
-**Notice:** Only implement this function if you require different behavior!
+`atom` | id | title | updated | author | content
+`rss 0.91` | link | title | | | description
+`rss 1.0` | link | title | dc:date | dc:creator | description
+`rss 2.0` | link, guid | title | pubDate, dc:date | author, dc:creator | description
# Template
@@ -87,19 +37,19 @@ This is the template for a new bridge:
```PHP
<?php
-class MySiteBridge extends FeedExpander {
+class MySiteBridge extends FeedExpander
+{
- const MAINTAINER = 'No maintainer';
- const NAME = 'Unnamed bridge';
- const URI = '';
- const DESCRIPTION = 'No description provided';
- const PARAMETERS = [];
- const CACHE_TIMEOUT = 3600;
+ const MAINTAINER = 'No maintainer';
+ const NAME = 'Unnamed bridge';
+ const URI = '';
+ const DESCRIPTION = 'No description provided';
+ const PARAMETERS = [];
+ const CACHE_TIMEOUT = 3600;
public function collectData()
{
$this->collectExpandableDatas('your feed URI');
}
}
-// Imaginary empty line!
```
\ No newline at end of file
diff --git a/docs/05_Bridge_API/index.md b/docs/05_Bridge_API/index.md
index e49e47be..06445246 100644
--- a/docs/05_Bridge_API/index.md
+++ b/docs/05_Bridge_API/index.md
@@ -7,7 +7,7 @@ and extends one of the base classes of **RSS-Bridge**:
Base class | Description
-----------|------------
[`BridgeAbstract`](./02_BridgeAbstract.md) | This class is intended for standard _Bridges_ that need to filter HTML pages for content.
-[`FeedExpander`](./03_FeedExpander.md) | This class is an extension of `HttpCachingBridgeAbstract`, designed to load existing feeds into **RSS-Bridge**
+[`FeedExpander`](./03_FeedExpander.md) | Expand/modify existing feed urls
[`XPathAbstract`](./04_XPathAbstract.md) | This class is meant as an alternative base class for bridge implementations. It offers preliminary functionality for generating feeds based on _XPath expressions_.
For more information about how to create a new _Bridge_, read [How to create a new Bridge?](./01_How_to_create_a_new_bridge.md)
\ No newline at end of file
diff --git a/lib/FeedExpander.php b/lib/FeedExpander.php
index 70c4560d..f9cff900 100644
--- a/lib/FeedExpander.php
+++ b/lib/FeedExpander.php
@@ -5,111 +5,57 @@
*/
abstract class FeedExpander extends BridgeAbstract
{
- const FEED_TYPE_RSS_1_0 = 'RSS_1_0';
- const FEED_TYPE_RSS_2_0 = 'RSS_2_0';
- const FEED_TYPE_ATOM_1_0 = 'ATOM_1_0';
-
- private string $feedType;
- private FeedParser $feedParser;
- private array $parsedFeed;
-
- public function __construct(CacheInterface $cache, Logger $logger)
- {
- parent::__construct($cache, $logger);
- $this->feedParser = new FeedParser();
- }
+ private array $feed;
public function collectExpandableDatas(string $url, $maxItems = -1)
{
if (!$url) {
throw new \Exception('There is no $url for this RSS expander');
}
+ $maxItems = (int) $maxItems;
if ($maxItems === -1) {
$maxItems = 999;
}
$accept = [MrssFormat::MIME_TYPE, AtomFormat::MIME_TYPE, '*/*'];
$httpHeaders = ['Accept: ' . implode(', ', $accept)];
- // Notice we do not use cache here on purpose. We want a fresh view of the RSS stream each time
$xmlString = getContents($url, $httpHeaders);
if ($xmlString === '') {
throw new \Exception(sprintf('Unable to parse xml from `%s` because we got the empty string', $url), 10);
}
- // Maybe move this call earlier up the stack frames
- // Disable triggering of the php error-handler and handle errors manually instead
- libxml_use_internal_errors(true);
- // Consider replacing libxml with https://www.php.net/domdocument
- // Intentionally not using the silencing operator (@) because it has no effect here
- $xml = simplexml_load_string(trim($xmlString));
- if ($xml === false) {
- $xmlErrors = libxml_get_errors();
- foreach ($xmlErrors as $xmlError) {
- Debug::log(trim($xmlError->message));
- }
- if ($xmlErrors) {
- // Render only the first error into exception message
- $firstXmlErrorMessage = $xmlErrors[0]->message;
- }
- throw new \Exception(sprintf('Unable to parse xml from `%s` %s', $url, $firstXmlErrorMessage ?? ''), 11);
- }
- // Restore previous behaviour in case other code relies on it being off
- libxml_use_internal_errors(false);
-
- // Currently only feed metadata (not items) are plucked out
- $this->parsedFeed = $this->feedParser->parseFeed($xmlString);
-
- if (isset($xml->item[0])) {
- $this->feedType = self::FEED_TYPE_RSS_1_0;
- $items = $xml->item;
- } elseif (isset($xml->channel[0])) {
- $this->feedType = self::FEED_TYPE_RSS_2_0;
- $items = $xml->channel[0]->item;
- } elseif (isset($xml->entry[0])) {
- $this->feedType = self::FEED_TYPE_ATOM_1_0;
- $items = $xml->entry;
- } else {
- throw new \Exception(sprintf('Unable to detect feed format from `%s`', $url));
- }
+ $feedParser = new FeedParser();
+ $this->feed = $feedParser->parseFeed($xmlString);
+ $items = array_slice($this->feed['items'], 0, $maxItems);
foreach ($items as $item) {
- $parsedItem = $this->parseItem($item);
- if ($parsedItem) {
- $this->items[] = $parsedItem;
- }
- if (count($this->items) >= $maxItems) {
- break;
+ // Give bridges a chance to modify the item
+ $item = $this->parseItem($item);
+ if ($item) {
+ $this->items[] = $item;
}
}
- return $this;
}
/**
- * @param \SimpleXMLElement $item The feed item to be parsed
+ * This method is overidden by bridges
+ *
+ * @return array
*/
- protected function parseItem($item)
+ protected function parseItem(array $item)
{
- switch ($this->feedType) {
- case self::FEED_TYPE_RSS_1_0:
- return $this->feedParser->parseRss1Item($item);
- case self::FEED_TYPE_RSS_2_0:
- return $this->feedParser->parseRss2Item($item);
- case self::FEED_TYPE_ATOM_1_0:
- return $this->feedParser->parseAtomItem($item);
- default:
- throw new \Exception(sprintf('Unknown version %s!', $this->getInput('version')));
- }
+ return $item;
}
public function getURI()
{
- return $this->parsedFeed['uri'] ?? parent::getURI();
+ return $this->feed['uri'] ?? parent::getURI();
}
public function getName()
{
- return $this->parsedFeed['title'] ?? parent::getName();
+ return $this->feed['title'] ?? parent::getName();
}
public function getIcon()
{
- return $this->parsedFeed['icon'] ?? parent::getIcon();
+ return $this->feed['icon'] ?? parent::getIcon();
}
}
diff --git a/lib/FeedParser.php b/lib/FeedParser.php
index 04452e7d..0a5b4679 100644
--- a/lib/FeedParser.php
+++ b/lib/FeedParser.php
@@ -14,10 +14,10 @@ final class FeedParser
throw new \Exception('Unable to parse xml');
}
$feed = [
- 'title' => null,
- 'url' => null,
- 'icon' => null,
- 'items' => [],
+ 'title' => null,
+ 'uri' => null,
+ 'icon' => null,
+ 'items' => [],
];
if (isset($xml->item[0])) {
// rss 1.0