peptide-repo/peptide-news-plugin
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: resolve actual article source instead of showing aggregator domain

Browse Source 
Google News RSS feeds report every article as coming from
"news.google.com" because the source was extracted from the feed URL
rather than the individual article. This adds a multi-strategy
resolver that extracts the real publisher name via:

1. SimplePie <source> element (Google News provides this)
2. Title suffix parsing ("Headline - Source" format)
3. HTTP HEAD redirect resolution as a fallback

Also adds a one-click "Fix Article Sources" backfill button on the
settings page to correct existing articles in the database.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Terence Ong
2026-04-06 19:11:14 +07:00
parent 9ec67591bd
commit 18158a3b81
3 changed files with 238 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
admin/class-peptide-news-admin.php
View File

@@ -61,9 +61,10 @@ class Peptide_News_Admin {
);
wp_localize_script( $this->plugin_name . '-admin', 'peptideNewsAdmin', array(
'ajax_url' => admin_url( 'admin-ajax.php' ),
'rest_url' => rest_url( 'peptide-news/v1/' ),
'nonce' => wp_create_nonce( 'wp_rest' ),
'ajax_url' => admin_url( 'admin-ajax.php' ),
'rest_url' => rest_url( 'peptide-news/v1/' ),
'nonce' => wp_create_nonce( 'wp_rest' ),
'admin_nonce' => wp_create_nonce( 'peptide_news_admin' ),
) );
}
@@ -556,11 +557,42 @@ class Peptide_News_Admin {
echo '<h1>' . esc_html( get_admin_page_title() ) . '</h1>';
// Fetch Now button.
echo '<form method="post">';
echo '<form method="post" style="display:inline-block;margin-right:12px;">';
wp_nonce_field( 'peptide_news_fetch_now_action' );
submit_button( __( 'Fetch Articles Now', 'peptide-news' ), 'secondary', 'peptide_news_fetch_now' );
submit_button( __( 'Fetch Articles Now', 'peptide-news' ), 'secondary', 'peptide_news_fetch_now', false );
echo '</form>';
// Backfill Sources button (fixes "news.google.com" source labels).
echo '<button type="button" id="peptide-backfill-sources" class="button button-secondary">';
echo esc_html__( 'Fix Article Sources', 'peptide-news' );
echo '</button>';
echo '<span id="peptide-backfill-result" style="margin-left:10px;"></span>';
?>
<script>
(function($) {
$('#peptide-backfill-sources').on('click', function() {
var $btn = $(this), $result = $('#peptide-backfill-result');
$btn.prop('disabled', true).text('<?php echo esc_js( __( 'Fixing...', 'peptide-news' ) ); ?>');
$result.text('');
$.post(peptideNewsAdmin.ajax_url, {
action: 'peptide_news_backfill_sources',
nonce: peptideNewsAdmin.admin_nonce
}, function(response) {
$btn.prop('disabled', false).text('<?php echo esc_js( __( 'Fix Article Sources', 'peptide-news' ) ); ?>');
if (response.success) {
$result.text(response.data.updated + ' article(s) updated.');
} else {
$result.text('Error: ' + (response.data || 'Unknown error'));
}
}).fail(function() {
$btn.prop('disabled', false).text('<?php echo esc_js( __( 'Fix Article Sources', 'peptide-news' ) ); ?>');
$result.text('Request failed.');
});
});
})(jQuery);
</script>
<?php
// Last fetch info.
$last_fetch = get_option( 'peptide_news_last_fetch' );
if ( $last_fetch ) {

202
includes/class-peptide-news-fetcher.php
View File

@@ -161,9 +161,12 @@ class Peptide_News_Fetcher {
$pub_date = current_time( 'mysql' );
}
$article_url = esc_url_raw( $item->get_permalink() );
$source_name = $this->resolve_article_source( $item, $feed_url, $article_url );
$articles[] = array(
'source' => $this->extract_domain( $feed_url ),
'source_url' => esc_url_raw( $item->get_permalink() ),
'source' => $source_name,
'source_url' => $article_url,
'title' => sanitize_text_field( $item->get_title() ),
'excerpt' => wp_trim_words( wp_strip_all_tags( $item->get_description() ), 40 ),
'content' => wp_kses_post( $item->get_content() ),
@@ -617,6 +620,201 @@ class Peptide_News_Fetcher {
return implode( ', ', array_filter( $names ) );
}
/**
* Resolve the real source name for an RSS feed item.
*
* Google News RSS wraps articles from other publishers behind
* news.google.com URLs, so the feed-level domain is useless.
* This method tries several strategies in priority order:
*
* 1. SimplePie <source> element (Google News RSS includes this).
* 2. Title suffix — Google News formats titles as "Headline - Source".
* 3. Resolve the redirect URL to get the actual publisher domain.
* 4. Fall back to the article permalink domain.
* 5. Last resort: feed URL domain.
*
* @param SimplePie_Item $item The RSS item.
* @param string $feed_url The feed URL.
* @param string $article_url The article permalink.
* @return string Source name or domain.
*/
private function resolve_article_source( $item, $feed_url, $article_url ) {
$feed_domain = $this->extract_domain( $feed_url );
$is_aggregator = in_array(
$feed_domain,
array( 'news.google.com', 'news.yahoo.com', 'msn.com', 'feedly.com' ),
true
);
// Strategy 1: SimplePie <source> element.
$source_obj = $item->get_source();
if ( $source_obj ) {
$source_title = $source_obj->get_title();
if ( ! empty( $source_title ) ) {
return sanitize_text_field( $source_title );
}
$source_link = $source_obj->get_link();
if ( ! empty( $source_link ) ) {
$domain = $this->extract_domain( $source_link );
if ( 'unknown' !== $domain ) {
return $domain;
}
}
}
// Strategy 2: Parse "Headline - Source" from title (common in aggregator feeds).
if ( $is_aggregator ) {
$title = $item->get_title();
if ( ! empty( $title ) && preg_match( '/\s[-\x{2013}\x{2014}]\s([^-\x{2013}\x{2014}]+)$/u', $title, $matches ) ) {
$candidate = trim( $matches[1] );
if ( mb_strlen( $candidate ) <= 60 && mb_strlen( $candidate ) >= 2 ) {
return sanitize_text_field( $candidate );
}
}
}
// Strategy 3: Resolve Google News redirect URL to actual destination.
if ( $is_aggregator ) {
$resolved = $this->resolve_redirect_url( $article_url );
if ( $resolved && $resolved !== $article_url ) {
$domain = $this->extract_domain( $resolved );
if ( 'unknown' !== $domain && $domain !== $feed_domain ) {
return $domain;
}
}
}
// Strategy 4: Use the article permalink domain.
$article_domain = $this->extract_domain( $article_url );
if ( 'unknown' !== $article_domain && $article_domain !== $feed_domain ) {
return $article_domain;
}
// Strategy 5: Fall back to the feed domain.
return $feed_domain;
}
/**
* Resolve a redirect URL to its final destination without downloading the body.
*
* @param string $url The URL to resolve.
* @return string|false The final URL or false on failure.
*/
private function resolve_redirect_url( $url ) {
if ( empty( $url ) ) {
return false;
}
$response = wp_remote_head( $url, array(
'timeout' => 8,
'redirection' => 5,
'user-agent' => 'Mozilla/5.0 (compatible; PeptideNewsBot/1.0)',
) );
if ( is_wp_error( $response ) ) {
return false;
}
$final_url = wp_remote_retrieve_header( $response, 'location' );
if ( empty( $final_url ) && isset( $response['http_response'] ) ) {
$http_response = $response['http_response'];
if ( method_exists( $http_response, 'get_response_object' ) ) {
$raw = $http_response->get_response_object();
if ( isset( $raw->url ) ) {
return $raw->url;
}
}
}
return ! empty( $final_url ) ? $final_url : false;
}
/**
* Backfill source names for existing articles that show an aggregator domain.
*
* Parses the " - Source" suffix from stored titles to update the source column.
*
* @return int Number of articles updated.
*/
public function backfill_article_sources() {
global $wpdb;
$table = $wpdb->prefix . 'peptide_news_articles';
$aggregators = array( 'news.google.com', 'news.yahoo.com', 'msn.com' );
$placeholders = implode( ', ', array_fill( 0, count( $aggregators ), '%s' ) );
// phpcs:ignore WordPress.DB.PreparedSQL.InterpolatedNotPrepared
$articles = $wpdb->get_results( $wpdb->prepare(
"SELECT id, title, source, source_url
FROM {$table}
WHERE source IN ({$placeholders})
AND is_active = 1",
...$aggregators
) );
if ( empty( $articles ) ) {
return 0;
}
$updated = 0;
foreach ( $articles as $article ) {
$new_source = '';
// Try parsing "Headline - Source" from title.
if ( preg_match( '/\s[-\x{2013}\x{2014}]\s([^-\x{2013}\x{2014}]+)$/u', $article->title, $matches ) ) {
$candidate = trim( $matches[1] );
if ( mb_strlen( $candidate ) <= 60 && mb_strlen( $candidate ) >= 2 ) {
$new_source = sanitize_text_field( $candidate );
}
}
// Fall back to resolving the redirect URL.
if ( empty( $new_source ) ) {
$resolved = $this->resolve_redirect_url( $article->source_url );
if ( $resolved && $resolved !== $article->source_url ) {
$domain = $this->extract_domain( $resolved );
if ( 'unknown' !== $domain && ! in_array( $domain, $aggregators, true ) ) {
$new_source = $domain;
}
}
usleep( 300000 ); // 0.3s throttle for HTTP requests.
}
if ( ! empty( $new_source ) && $new_source !== $article->source ) {
$wpdb->update(
$table,
array( 'source' => $new_source ),
array( 'id' => $article->id ),
array( '%s' ),
array( '%d' )
);
$updated++;
}
}
if ( $updated > 0 ) {
$this->clear_article_cache();
}
return $updated;
}
/**
* AJAX handler for the backfill action.
*/
public function ajax_backfill_sources() {
check_ajax_referer( 'peptide_news_admin', 'nonce' );
if ( ! current_user_can( 'manage_options' ) ) {
wp_send_json_error( 'Unauthorized', 403 );
}
$updated = $this->backfill_article_sources();
wp_send_json_success( array( 'updated' => $updated ) );
}
/**
* Extract domain from a URL for source identification.
*

1
includes/class-peptide-news.php
View File

@@ -80,6 +80,7 @@ class Peptide_News {
$this->loader->add_action( 'peptide_news_cron_fetch', $fetcher, 'fetch_all_sources' );
$this->loader->add_filter( 'cron_schedules', $fetcher, 'add_custom_cron_schedules' );
$this->loader->add_action( 'wp_ajax_peptide_news_backfill_sources', $fetcher, 'ajax_backfill_sources' );
}
/**