feat: init

core/media.py

@@ -0,0 +1,44 @@
+import json
+import os
+import subprocess
+import tempfile
+
+
+class MediaHandler:
+    @staticmethod
+    def get_media_duration(media_path: str) -> float:
+        cmd = ["ffprobe", "-v", "error", "-show_entries", "format=duration", "-of",
+               "default=noprint_wrappers=1:nokey=1", media_path]
+        try:
+            return float(subprocess.run(cmd, capture_output=True, text=True).stdout.strip())
+        except Exception:
+            return 3600.0
+
+    @staticmethod
+    def get_audio_stream_index(media_path: str, language: str) -> str:
+        lang_map = {'english': 'eng', 'french': 'fre', 'fra': 'fre', 'german': 'ger', 'spanish': 'spa',
+                    'italian': 'ita'}
+        target_iso = lang_map.get(language.lower(), 'eng')
+
+        cmd = ["ffprobe", "-v", "quiet", "-print_format", "json", "-show_streams", "-select_streams", "a", media_path]
+        try:
+            data = json.loads(subprocess.run(cmd, capture_output=True, text=True).stdout)
+            for i, stream in enumerate(data.get('streams', [])):
+                if stream.get('tags', {}).get('language', 'und').lower() == target_iso:
+                    return f"0:a:{i}"
+            return "0:a:0"
+        except Exception:
+            return "0:a:0"
+
+    @staticmethod
+    def extract_audio_chunk(media_path: str, start_sec: int, duration_sec: int, stream_index: str) -> str:
+        fd, tmp_name = tempfile.mkstemp(suffix=".wav")
+        os.close(fd)
+
+        cmd = [
+            "ffmpeg", "-y", "-ss", str(start_sec), "-i", media_path,
+            "-map", stream_index, "-t", str(duration_sec),
+            "-ac", "1", "-ar", "16000", "-vn", "-loglevel", "error", tmp_name
+        ]
+        subprocess.run(cmd, check=True)
+        return tmp_name