From 7a816efc04fd30e8b0999e7ae2dc118edb18e71d Mon Sep 17 00:00:00 2001
From: HadiCherkaoui <github@hide.cherkaoui.ch>
Date: Fri, 28 Feb 2025 09:13:11 +0100
Subject: [PATCH] fix google pse

i tested everything, also tested if invalid api key and such and regression tested searxng which still works
---
 src/chains/imageSearchAgent.ts      | 22 +++++++---------------
 src/chains/videoSearchAgent.ts      | 24 ++++++------------------
 src/lib/searchEngines/google_pse.ts | 15 +++++++++++++--
 src/routes/discover.ts              |  7 +++----
 4 files changed, 29 insertions(+), 39 deletions(-)

diff --git a/src/chains/imageSearchAgent.ts b/src/chains/imageSearchAgent.ts
index 4c73876..920fdf6 100644
--- a/src/chains/imageSearchAgent.ts
+++ b/src/chains/imageSearchAgent.ts
@@ -45,22 +45,14 @@ async function performImageSearch(query: string) {
   switch (searchEngine) {
     case 'google': {
       const googleResult = await searchGooglePSE(query);
-      images = googleResult.originalres
-        .map((result) => {
-          // Extract image URL from multiple possible locations in Google's response
-          const imageSrc = result.pagemap?.cse_image?.[0]?.src ||
-                            result.pagemap?.cse_thumbnail?.[0]?.src ||
-                            result.image?.thumbnailLink;
-
-          if (imageSrc && result.link && result.title) {
-            images.push({
-              img_src: imageSrc,
-              url: result.link,
+      images = googleResult.results.map((result) => {
+          if (result.img_src && result.url && result.title) {
+            return {
+              img_src: result.img_src,
+              url: result.url,
               title: result.title,
-              // Add additional metadata if needed
-              source: result.displayLink,
-              fileFormat: result.fileFormat,
-            });
+              source: result.displayLink
+            };
           }
         })
         .filter(Boolean);
diff --git a/src/chains/videoSearchAgent.ts b/src/chains/videoSearchAgent.ts
index df352fd..b16fb44 100644
--- a/src/chains/videoSearchAgent.ts
+++ b/src/chains/videoSearchAgent.ts
@@ -40,12 +40,6 @@ type VideoSearchChainInput = {
 
 const strParser = new StringOutputParser();
 
-function extractYouTubeVideoId(url: string): string | null {
-  const regex = /(?:v=|\/embed\/|\.be\/)([a-zA-Z0-9_-]{11})/;
-  const match = url.match(regex);
-  return match ? match[1] : null;
-}
-
 async function performVideoSearch(query: string) {
   const searchEngine = getSearchEngineBackend();
   const youtubeQuery = `${query} site:youtube.com`;
@@ -54,20 +48,14 @@ async function performVideoSearch(query: string) {
   switch (searchEngine) {
     case 'google': {
       const googleResult = await searchGooglePSE(youtubeQuery);
-      googleResult.originalres.results.forEach((result) => {
-        // Extract video metadata from Google PSE results
-        const thumbnail = result.pagemap?.cse_thumbnail?.[0]?.src 
-                         || result.pagemap?.videoobject?.[0]?.thumbnailurl;
-
-        if (thumbnail && result.link && result.title) {
+      googleResult.results.forEach((result) => { // Use .results instead of .originalres
+        if (result.img_src && result.url && result.title) {
+          const videoId = new URL(result.url).searchParams.get('v');
           videos.push({
-            img_src: thumbnail,
-            url: result.link,
+            img_src: result.img_src,
+            url: result.url,
             title: result.title,
-            // Construct iframe URL from YouTube video ID
-            iframe_src: result.link.includes('youtube.com/watch?v=')
-              ? `https://www.youtube.com/embed/${result.link.split('v=')[1].split('&')[0]}`
-              : null,
+            iframe_src: videoId ? `https://www.youtube.com/embed/${videoId}` : null
           });
         }
       });
diff --git a/src/lib/searchEngines/google_pse.ts b/src/lib/searchEngines/google_pse.ts
index 5232b0c..f09531d 100644
--- a/src/lib/searchEngines/google_pse.ts
+++ b/src/lib/searchEngines/google_pse.ts
@@ -63,11 +63,22 @@ export const searchGooglePSE = async (query: string) => {
       title: item.title,
       url: item.link,
       content: item.snippet,
-      img_src: item.pagemap?.cse_image?.[0]?.src,
+      img_src: item.pagemap?.cse_image?.[0]?.src
+             || item.pagemap?.cse_thumbnail?.[0]?.src
+             || item.image?.thumbnailLink,
+      ...(item.pagemap?.videoobject?.[0] && {
+        videoData: {
+          duration: item.pagemap.videoobject[0].duration,
+          embedUrl: item.pagemap.videoobject[0].embedurl
+        }
+      })
     }));
 
     return { results, originalres };
   } catch (error) {
-    throw new Error('Google PSE Error:', error.response?.data || error.message);
+    const errorMessage = error.response?.data
+      ? JSON.stringify(error.response.data, null, 2)
+      : error.message || 'Unknown error';
+    throw new Error(`Google PSE Error: ${errorMessage}`);
   }
 };
diff --git a/src/routes/discover.ts b/src/routes/discover.ts
index 80022fc..0f47b97 100644
--- a/src/routes/discover.ts
+++ b/src/routes/discover.ts
@@ -6,9 +6,8 @@ import logger from '../utils/logger';
 
 const router = express.Router();
 
-const searchEngine = getSearchEngineBackend();
-
-async function performSearch(query: string, site: string, searchEngine: string) {
+async function performSearch(query: string, site: string) {
+  const searchEngine = getSearchEngineBackend();
   switch (searchEngine) {
     case 'google': {
       const googleResult = await searchGooglePSE(query);
@@ -65,7 +64,7 @@ router.get('/', async (req, res) => {
         queries.map(async ({ site, topic }) => {
           try {
             const query = `site:${site} ${topic}`;
-            return await performSearch(query, site, searchEngine);
+            return await performSearch(query, site);
           } catch (error) {
             logger.error(`Error searching ${site}: ${error.message}`);
             return [];