embedded image finishing

frontend/src/app/scrape/bulk/route.ts

@@ -188,29 +188,47 @@ async function processCombinedMode(
   // Check content size to prevent response size issues
   const combinedContentString = combinedContent.join('\n');
   const contentSizeInMB = new Blob([combinedContentString]).size / (1024 * 1024);
-  
+
   console.log(`Combined content size: ${contentSizeInMB.toFixed(2)} MB`);
   console.log(`Combined content character length: ${combinedContentString.length}`);
   console.log(`Combined content parts count: ${combinedContent.length}`);
-  
+
+  // Handle content truncation if needed
+  let finalContent = contentSizeInMB > 10 ?
+    combinedContentString.substring(0, Math.floor(combinedContentString.length * (10 / contentSizeInMB))) + '\n\n<!-- Content truncated due to size limit -->' :
+    combinedContentString;
+
+  let finalSummary = contentSizeInMB > 10 ? baseSummary + ' (Content truncated due to size limit)' : baseSummary;
+
+  // Check if combined content has images and mark for processing
+  const hasImages = /<img[^>]+src=['"'][^'"']*['"][^>]*>/i.test(finalContent);
+  if (hasImages) {
+    finalSummary += ' (Contains embedded images - will be processed after story creation)';
+    console.log(`Combined story contains embedded images - will need processing after creation`);
+  }
+
   // Return the combined story data via progress update
   const combinedStory = {
     title: baseTitle,
     author: baseAuthor,
-    content: contentSizeInMB > 10 ? 
-      combinedContentString.substring(0, Math.floor(combinedContentString.length * (10 / contentSizeInMB))) + '\n\n<!-- Content truncated due to size limit -->' :
-      combinedContentString,
-    summary: contentSizeInMB > 10 ? baseSummary + ' (Content truncated due to size limit)' : baseSummary,
+    content: finalContent,
+    summary: finalSummary,
     sourceUrl: baseSourceUrl,
-    tags: Array.from(combinedTags)
+    tags: Array.from(combinedTags),
+    hasImages: hasImages
   };
   
   // Send completion notification for combine mode
+  let completionMessage = `Combined scraping completed: ${totalWordCount.toLocaleString()} words from ${importedCount} stories`;
+  if (hasImages) {
+    completionMessage += ` (embedded images will be processed when story is created)`;
+  }
+
   await sendProgressUpdate(sessionId, {
     type: 'completed',
     current: urls.length,
     total: urls.length,
-    message: `Combined scraping completed: ${totalWordCount.toLocaleString()} words from ${importedCount} stories`,
+    message: completionMessage,
     totalWordCount: totalWordCount,
     combinedStory: combinedStory
   });
@@ -346,7 +364,62 @@ async function processIndividualMode(
         }
 
         const createdStory = await createResponse.json();
-        
+
+        // Process embedded images if content contains images
+        let imageProcessingWarnings: string[] = [];
+        const hasImages = /<img[^>]+src=['"'][^'"']*['"][^>]*>/i.test(scrapedStory.content);
+
+        if (hasImages) {
+          try {
+            console.log(`Processing embedded images for story: ${createdStory.id}`);
+            const imageProcessUrl = `http://backend:8080/api/stories/${createdStory.id}/process-content-images`;
+            const imageProcessResponse = await fetch(imageProcessUrl, {
+              method: 'POST',
+              headers: {
+                'Authorization': authorization,
+                'Content-Type': 'application/json',
+              },
+              body: JSON.stringify({ htmlContent: scrapedStory.content }),
+            });
+
+            if (imageProcessResponse.ok) {
+              const imageResult = await imageProcessResponse.json();
+              if (imageResult.hasWarnings && imageResult.warnings) {
+                imageProcessingWarnings = imageResult.warnings;
+                console.log(`Image processing completed with warnings for story ${createdStory.id}:`, imageResult.warnings);
+              } else {
+                console.log(`Image processing completed successfully for story ${createdStory.id}. Downloaded ${imageResult.downloadedImages?.length || 0} images.`);
+              }
+
+              // Update story content with processed images
+              if (imageResult.processedContent && imageResult.processedContent !== scrapedStory.content) {
+                const updateUrl = `http://backend:8080/api/stories/${createdStory.id}`;
+                const updateResponse = await fetch(updateUrl, {
+                  method: 'PUT',
+                  headers: {
+                    'Authorization': authorization,
+                    'Content-Type': 'application/json',
+                  },
+                  body: JSON.stringify({
+                    contentHtml: imageResult.processedContent
+                  }),
+                });
+
+                if (!updateResponse.ok) {
+                  console.warn(`Failed to update story content after image processing for ${createdStory.id}`);
+                  imageProcessingWarnings.push('Failed to update story content with processed images');
+                }
+              }
+            } else {
+              console.warn(`Image processing failed for story ${createdStory.id}:`, imageProcessResponse.status);
+              imageProcessingWarnings.push('Image processing failed');
+            }
+          } catch (error) {
+            console.error(`Error processing images for story ${createdStory.id}:`, error);
+            imageProcessingWarnings.push(`Image processing error: ${error instanceof Error ? error.message : 'Unknown error'}`);
+          }
+        }
+
         results.push({
           url: trimmedUrl,
           status: 'imported',
@@ -356,17 +429,24 @@ async function processIndividualMode(
         });
         importedCount++;
 
-        console.log(`Successfully imported: ${scrapedStory.title} by ${scrapedStory.author} (ID: ${createdStory.id})`);
-        
+        console.log(`Successfully imported: ${scrapedStory.title} by ${scrapedStory.author} (ID: ${createdStory.id})${hasImages ? ` with ${imageProcessingWarnings.length > 0 ? 'warnings' : 'successful image processing'}` : ''}`);
+
         // Send progress update for successful import
+        let progressMessage = `Imported "${scrapedStory.title}" by ${scrapedStory.author}`;
+        if (hasImages) {
+          progressMessage += imageProcessingWarnings.length > 0 ? ' (with image warnings)' : ' (with images)';
+        }
+
         await sendProgressUpdate(sessionId, {
           type: 'progress',
           current: i + 1,
           total: urls.length,
-          message: `Imported "${scrapedStory.title}" by ${scrapedStory.author}`,
+          message: progressMessage,
           url: trimmedUrl,
           title: scrapedStory.title,
-          author: scrapedStory.author
+          author: scrapedStory.author,
+          hasImages: hasImages,
+          imageWarnings: imageProcessingWarnings
         });
 
       } catch (error) {