Update (parsing): skip words below 120

2023-11-29 12:24:15 +08:00
parent c70b0bccd4
commit 8c0ae63f42
3 changed files with 24 additions and 1 deletions
--- a/app/Jobs/Tasks/ParseUrlBodyTask.php
+++ b/app/Jobs/Tasks/ParseUrlBodyTask.php
@@ -31,6 +31,15 @@ public static function handle(int $url_to_crawl_id)

        if (is_empty($url_to_crawl->output)) {
            ParseUrlBodyJob::dispatch($url_to_crawl->id)->onQueue('default')->onConnection('default');
+            return ;
+        }
+
+        if (count_words($url_to_crawl->output) < 120)
+        {
+          $url_to_crawl->status = 'blocked';
+          $url_to_crawl->save();
+
+          return ;
        }

        $url_meta_response = null;