Update providers/archive_provider.py

providers/archive_provider.py

@@ -42,10 +42,12 @@ def search(query: str, has_transcript: bool = False):
             })
         
         return results_list
+
     except Exception as e:
         logging.error(f"An error occurred during search in archive_provider: {e}")
         return {"error": "Failed to perform search."}
 
+
 def get_details(identifier: str):
     """
     Retrieves key details for a single item from the Internet Archive, excluding the transcript.
@@ -71,8 +73,31 @@ def get_details(identifier: str):
         
         video_url = f"https://archive.org/download/{identifier}/{video_file['name']}" if video_file else None
 
-        # --- Find Audio File ---
-        audio_file = next((f for f in item.files if f.get('format') == 'VBR MP3'), None)
+        # --- Find Audio File (الطريقة المحسّنة) ---
+        audio_file = None
+        
+        # قائمة بأولويات الـ formats من الأحسن للأسوأ
+        audio_priority = [
+            'VBR MP3',           # الأفضل في الجودة
+            'MP3',               # عادي
+            '64Kbps MP3',        # جودة أقل
+            'Ogg Vorbis',        # بديل مفتوح المصدر
+            'FLAC',              # lossless لكن حجم كبير
+            'M4A',               # Apple format
+        ]
+        
+        # دور بالترتيب
+        for fmt in audio_priority:
+            audio_file = next((f for f in item.files if fmt in f.get('format', '')), None)
+            if audio_file:
+                break
+        
+        # لو مفيش، دور على امتدادات
+        if not audio_file:
+            audio_file = next((f for f in item.files 
+                               if any(f.get('name', '').lower().endswith(ext) 
+                                      for ext in ['.mp3', '.ogg', '.m4a', '.flac'])), None)
+        
         audio_url = f"https://archive.org/download/{identifier}/{audio_file['name']}" if audio_file else None
 
         # --- Structure the final response ---
@@ -93,8 +118,34 @@ def get_details(identifier: str):
     except Exception as e:
         logging.error(f"An error occurred getting details in archive_provider for {identifier}: {e}")
         return {"error": f"Failed to retrieve details for item {identifier}."}
-        return response
 
+
+def get_transcript(identifier: str):
+    """
+    Retrieves just the transcript for a single item from the Internet Archive.
+    """
+    item = _get_item_or_error(identifier)
+    if isinstance(item, dict) and "error" in item:
+        return item
+
+    try:
+        transcript_content = "Transcript not available."
+        transcript_file_info = next((f for f in item.files if f.get('format') == 'SubRip'), None) or \
+                             next((f for f in item.files if f.get('format') == 'Page Turn'), None) or \
+                             next((f for f in item.files if f.get('name', '').endswith('_ocr.txt')), None)
+        
+        if transcript_file_info:
+            transcript_file = item.get_file(transcript_file_info['name'])
+            try:
+                transcript_content = transcript_file.read().decode('utf-8', 'ignore')
+            except Exception as e:
+                logging.error(f"Could not read transcript for {identifier}: {e}")
+                return {"error": f"Transcript found for item {identifier} but could not be read."}
+
+        return {
+            "identifier": identifier,
+            "transcript": transcript_content
+        }
     except Exception as e:
-        logging.error(f"An error occurred getting details in archive_provider for {identifier}: {e}")
-        return {"error": f"Failed to retrieve details for item {identifier}."}
+        logging.error(f"An error occurred getting transcript in archive_provider for {identifier}: {e}")
+        return {"error": f"Failed to retrieve transcript for item {identifier}."}