From 227fd7c412c8ace1dd0ca8895001e9168c3b9d97 Mon Sep 17 00:00:00 2001
From: Hamza-Ayed <hamzaayedflutter@gmail.com>
Date: Fri, 5 Jun 2026 17:03:37 +0300
Subject: [PATCH] Deploy on 2026-06-05 17:03:37

---
 app/Services/Crawler/AiAnalyzer.php | 23 +++++++++++--
 app/Services/Crawler/RssParser.php  | 53 +++++++++++++++++++++--------
 config/ai.php                       |  4 +--
 3 files changed, 62 insertions(+), 18 deletions(-)

diff --git a/app/Services/Crawler/AiAnalyzer.php b/app/Services/Crawler/AiAnalyzer.php
index 13aeacf..acc4492 100644
--- a/app/Services/Crawler/AiAnalyzer.php
+++ b/app/Services/Crawler/AiAnalyzer.php
@@ -158,6 +158,25 @@ PROMPT;
         $score = 30;
         $tags = [];
         $isOpportunity = true; // Treat all entries as opportunities by default
+        $orgName = null;
+        $country = null;
+
+        // Smart Regex rules for extracting organization names from title
+        if (preg_match('/^([A-Z0-9][A-Za-z0-9\s\-\.\&]{2,40})\s+(raises|launches|secures|gets|partners|funded|acquires|announces|closes|receives|seeks)\b/i', $title, $matches)) {
+            $orgName = trim($matches[1]);
+        } elseif (preg_match('/(backs|invests in|funds|acquires)\s+([A-Z0-9][A-Za-z0-9\s\-\.\&]{2,40})/i', $title, $matches)) {
+            $orgName = trim($matches[2]);
+        } elseif (preg_match('/(investment in|funding for|launch of)\s+([A-Z0-9][A-Za-z0-9\s\-\.\&]{2,40})/i', $title, $matches)) {
+            $orgName = trim($matches[2]);
+        }
+
+        if ($orgName) {
+            $orgName = preg_replace('/\b(series|seed|funding|round|raised|million|billion|capital|partners|ventures|inc|ltd|corp|co|llc)\b.*$/i', '', $orgName);
+            $orgName = trim($orgName, " \t\n\r\0\x0B,.-");
+            if (strlen($orgName) < 2 || in_array(strtolower($orgName), ['startup', 'founder', 'investor', 'program', 'new', 'why', 'how', 'what', 'who', 'the'])) {
+                $orgName = null;
+            }
+        }
 
         // Keyword patterns
         if (preg_match('/\b(grant|funding|award|prize)\b/i', $text)) {
@@ -238,8 +257,8 @@ PROMPT;
             'tags' => $tags,
             'is_opportunity' => $isOpportunity,
             'summary' => substr($description, 0, 200),
-            'organization_name' => null,
-            'country' => null,
+            'organization_name' => $orgName,
+            'country' => $country,
         ];
     }
 }
\ No newline at end of file
diff --git a/app/Services/Crawler/RssParser.php b/app/Services/Crawler/RssParser.php
index 060c86d..b2fe9d1 100644
--- a/app/Services/Crawler/RssParser.php
+++ b/app/Services/Crawler/RssParser.php
@@ -20,25 +20,50 @@ class RssParser
      */
     public function fetchEntries(string $url): array
     {
-        $context = stream_context_create([
-            'http' => [
-                'timeout' => 15,
-                'user_agent' => 'ScoutIQ/1.0 (Crawler)',
-            ],
-            'ssl' => [
-                'verify_peer' => false,
-                'verify_peer_name' => false,
-            ],
-        ]);
+        $xml = false;
+        if (function_exists('curl_init')) {
+            $ch = curl_init();
+            curl_setopt($ch, CURLOPT_URL, $url);
+            curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
+            curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
+            curl_setopt($ch, CURLOPT_USERAGENT, 'ScoutIQ/1.0 (Crawler)');
+            curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
+            curl_setopt($ch, CURLOPT_TIMEOUT, 15);
+            
+            $xml = curl_exec($ch);
+            $httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);
+            curl_close($ch);
 
-        $xml = @file_get_contents($url, false, $context);
-        if (!$xml) {
-            return [];
+            if ($httpCode !== 200) {
+                throw new \Exception("HTTP Error {$httpCode}");
+            }
+            if ($xml === false) {
+                throw new \Exception("Connection failed via cURL");
+            }
+        } else {
+            $context = stream_context_create([
+                'http' => [
+                    'timeout' => 15,
+                    'user_agent' => 'ScoutIQ/1.0 (Crawler)',
+                ],
+                'ssl' => [
+                    'verify_peer' => false,
+                    'verify_peer_name' => false,
+                ],
+            ]);
+            $xml = @file_get_contents($url, false, $context);
+            if ($xml === false) {
+                $status = "Connection failed";
+                if (isset($http_response_header) && isset($http_response_header[0])) {
+                    $status = $http_response_header[0];
+                }
+                throw new \Exception($status);
+            }
         }
 
         $feed = @simplexml_load_string($xml);
         if (!$feed) {
-            return [];
+            throw new \Exception("Invalid XML structure");
         }
 
         $entries = [];
diff --git a/config/ai.php b/config/ai.php
index 6660c24..29094fe 100644
--- a/config/ai.php
+++ b/config/ai.php
@@ -2,11 +2,11 @@
 
 return [
     'gemini' => [
-        'api_key' => ($_ENV['GEMINI_API_KEY'] === 'null' || !$_ENV['GEMINI_API_KEY']) ? null : $_ENV['GEMINI_API_KEY'],
+        'api_key' => (getenv('GEMINI_API_KEY') ?: ($_SERVER['GEMINI_API_KEY'] ?? ($_ENV['GEMINI_API_KEY'] ?? null))),
         'model' => 'gemini-flash-lite-latest',
     ],
     'jwt' => [
-        'secret' => $_ENV['JWT_SECRET'] ?? 'base64:3uFzGf9o8+D+U0mC4/3K1y4m81Qj7G6qTzS=',
+        'secret' => getenv('JWT_SECRET') ?: ($_SERVER['JWT_SECRET'] ?? ($_ENV['JWT_SECRET'] ?? 'base64:3uFzGf9o8+D+U0mC4/3K1y4m81Qj7G6qTzS=')),
         'algorithm' => 'HS256',
         'expires_in' => 86400 * 30, // 30 days
     ],