chore: make youtube_transcript_downloader.py executable

Changed the file mode from 100644 (non-executable) to 100755 (executable) to allow the script to be run directly.

.gitignore

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

language_codes.py

@@ -24,6 +24,19 @@ COMMON_FALLBACK_LANGUAGES = [
 ENGLISH_LANGUAGES = ['en', 'en-US', 'en-GB']
 # This can be used as the list of allowed fallback languages
 ALLOWED_FALLBACK_LANGUAGES = COMMON_FALLBACK_LANGUAGES
+COMMON_ENGLISH_WORDS = {
+        'the', 'be', 'to', 'of', 'and', 'a', 'in', 'that','has','acquire', 'have', 'i',
+        'it', 'for', 'not', 'on', 'with', 'he', 'as', 'you', 'do', 'at',
+        'this', 'but', 'his', 'by', 'from', 'they', 'we', 'say', 'her',
+        'she', 'or', 'an', 'will', 'my', 'one', 'all', 'would', 'there',
+        'their', 'what', 'so', 'up', 'out', 'if', 'about', 'who', 'get',
+        'which', 'go', 'me', 'when', 'make', 'can', 'like', 'time', 'no',
+        'just', 'him', 'know', 'take', 'people', 'into', 'year', 'your',
+        'good', 'some', 'could', 'them', 'see', 'other', 'than', 'then',
+        'now', 'look', 'only', 'come', 'its', 'over', 'think', 'also',
+        'back', 'after', 'use', 'two', 'how', 'our', 'work', 'first', 'well',
+        'way', 'even', 'new', 'want', 'because', 'any', 'these', 'give', 'day', 'without'
+    }
 
 if __name__ == "__main__":
     print("YouTube Language Codes:")

youtube_transcript_downloader.py

@@ -19,36 +19,17 @@ def extract_video_id(url):
     patterns = [
         r'(?:v=|\/)([0-9A-Za-z_-]{11}).*',
         r'youtu\.be\/([0-9A-Za-z_-]{11})',
+        r'([0-9A-Za-z_-]{11})'
     ]
     
     for pattern in patterns:
         match = re.search(pattern, url)
         if match:
             return match.group(1)
+    
     return None
 
 
-def get_transcript(video_id, languages=None):
-    """
-    Get transcript for a YouTube video.
-    
-    Args:
-        video_id: The YouTube video ID
-        languages: List of language codes to try (default: ['en', 'en-US'])
-    
-    Returns:
-        Transcript object or None if not found
-    """
-    if languages is None:
-        languages = ['en', 'en-US']
-    
-    try:
-        transcript = YouTubeTranscriptApi().fetch(video_id, languages=languages)
-        return transcript
-    except Exception as e:
-        print(f"Error getting transcript: {e}")
-        return None
-
 
 def get_transcript_text(transcript):
     """Extract plain text from transcript."""
@@ -212,26 +193,15 @@ def main():
 def is_english(text):
     """Simple check to determine if text is likely English."""
     # Common English words to check against
-    common_english_words = {
-        'the', 'be', 'to', 'of', 'and', 'a', 'in', 'that', 'have', 'i',
-        'it', 'for', 'not', 'on', 'with', 'he', 'as', 'you', 'do', 'at',
-        'this', 'but', 'his', 'by', 'from', 'they', 'we', 'say', 'her',
-        'she', 'or', 'an', 'will', 'my', 'one', 'all', 'would', 'there',
-        'their', 'what', 'so', 'up', 'out', 'if', 'about', 'who', 'get',
-        'which', 'go', 'me', 'when', 'make', 'can', 'like', 'time', 'no',
-        'just', 'him', 'know', 'take', 'people', 'into', 'year', 'your',
-        'good', 'some', 'could', 'them', 'see', 'other', 'than', 'then',
-        'now', 'look', 'only', 'come', 'its', 'over', 'think', 'also',
-        'back', 'after', 'use', 'two', 'how', 'our', 'work', 'first', 'well',
-        'way', 'even', 'new', 'want', 'because', 'any', 'these', 'give', 'day'
-    }
+    
     
     # Simple heuristic: count common English words
     words = set(text.lower().split())
-    matches = sum(1 for word in words if word in common_english_words)
-    
+    matches = sum(1 for word in words if word in language_codes.COMMON_ENGLISH_WORDS)
+    word_count = len(words)
+    print(f"found matches: {matches} out of {word_count} words")
     # If we find many common English words, it's likely English
-    return matches > len(words) * 0.05 if words else False
+    return matches > len(words) * 0.04 if words else False
 
 
 def download_captions(video_id):