Merge branch 'new'

.gitignore

@@ -0,0 +1,2 @@
+__pycache__
+transcript_*.txt

youtube_transcript_downloader.py

@@ -7,9 +7,11 @@ This program downloads a YouTube video transcript and translates it to English.
 
 import sys
 import re
+import json
 from youtube_transcript_api import YouTubeTranscriptApi
 from youtube_transcript_api.formatters import TextFormatter
 from deep_translator import GoogleTranslator
+import language_codes
 
 
 def extract_video_id(url):
@@ -150,9 +152,9 @@ def main():
     
     if needs_translation:
         print("\nNote: The transcript appears to be in a non-English language.")
-        print("Would you like to translate it to English?")
-        response = input("Enter 'y' for yes or 'n' for no: ").strip().lower()
-        
+        #print("Would you like to translate it to English?")
+        #response = input("Enter 'y' for yes or 'n' for no: ").strip().lower()
+        response = 'y'
         if response == 'y':
             print("\nTranslating to English...")
             translated = translate_text(original_text, 'en')
@@ -243,22 +245,10 @@ def download_captions(video_id):
         Dictionary with 'transcript', 'language', and 'success' keys,
         or None if no transcript is available
     """
-    try:
-        # First, try to get English transcript (preferably en, en-US, en-GB)
-        english_languages = ['en', 'en-US', 'en-GB']
-        transcript = YouTubeTranscriptApi().fetch(video_id, languages=english_languages)
-        
-        if transcript:
-            return {
-                'transcript': transcript,
-                'language': transcript.language,
-                'success': True
-            }
-    except Exception as e:
+    for languages in language_codes.ENGLISH_LANGUAGES, language_codes.COMMON_FALLBACK_LANGUAGES, language_codes.YOUTUBE_LANGUAGE_CODES:
         try:
-            # If no English transcript is available, try any language
-            print("No English transcript found. Trying to get transcript in original language...")
-            transcript = YouTubeTranscriptApi().fetch(video_id, languages=['de','fa'])
+            # First, try to get English transcript (preferably en, en-US, en-GB)
+            transcript = YouTubeTranscriptApi().fetch(video_id, languages=languages)
             
             if transcript:
                 return {
@@ -266,20 +256,14 @@ def download_captions(video_id):
                     'language': transcript.language,
                     'success': True
                 }
-                
-            return {
-                'transcript': None,
-                'language': None,
-                'success': False
-            }
-        
         except Exception as e:
-            print(f"Error downloading captions: {e}")
-            return {
-                'transcript': None,
-                'language': None,
-                'success': False
-            }
+            print("failed to fetch transcript in the following languages: "+json.dumps(languages,indent=2))
+    print(f"Error downloading captions: {e}")
+    return {
+        'transcript': None,
+        'language': None,
+        'success': False
+    }
 
 
 if __name__ == "__main__":