checkMetadata: support WebM containers

README.md

@@ -21,7 +21,7 @@
 
 ## Usage 
 
-`python ./check_metadata.py path`
+`python ./check_metadata.py path codec_filter`
 
 ## Features
 - find all video files in path

check_Names_and_Paths.sh

@@ -58,7 +58,7 @@ do
 
     ###### check extension ######
     ext="${filename##*.}"
-    if  [ "$ext" != "mkv" ] && [ "$ext" != "mp4" ]
+    if  [ "$ext" != "mkv" ] && [ "$ext" != "mp4" ] && [ "$ext" != "nfo" ]
     then
         echo "Incident: Incorrect extension: $file"
     fi
@@ -117,7 +117,7 @@ for show in tvshows/*; do
 
                         ###### check extension ######
                         ext="${episodename##*.}"
-                        if  [ "$ext" != "mkv" ] && [ "$ext" != "mp4" ]
+                        if  [ "$ext" != "mkv" ] && [ "$ext" != "mp4" ] && [ "$ext" != "nfo" ]
                         then
                             echo "Incident: Incorrect extension: $episode"
                         fi

check_metadata/check_metadata.py

@@ -13,6 +13,8 @@ import subprocess
 import datetime
 from dataclasses import dataclass
 from tqdm import tqdm
+import operator
+
 
 @dataclass
 class MediaFile:
@@ -25,7 +27,7 @@ class MediaFile:
     duration: int #in sec
 
 def supported_file_extension(filename):
-    if filename.endswith('.mp4') or filename.endswith('.mkv'):
+    if filename.endswith('.mp4') or filename.endswith('.mkv') or filename.endswith('.webm') or filename.endswith('.m4v'):
         return True
     return False
 
@@ -96,9 +98,19 @@ def scan_files(path):
     pbar.close()   
     return media_files
 
-def print_all(media_files):
+def print_all(media_files, filter_mode):
+    media_files_filtered = list() #stores all found files that match the given codec filter
+    media_files.sort(key=lambda x: x.size, reverse=True)
     for media_file in media_files:
         print ("{:<64} | {:<8} | {:<16} | {:<8} | {:<16}".format(cut_file_name(media_file.name, 64), str(datetime.timedelta(seconds=media_file.duration)).split(".")[0], human_readable_size(media_file.size), media_file.codec, str(media_file.resolution[0])+"x"+str(media_file.resolution[1])))
+        if((filter_mode != " ") and (media_file.codec == filter_mode) ):
+            media_files_filtered.append(media_file.name)
+
+    if(filter_mode != " "):        
+        print("\nFound files with selected filter: " + filter_mode + "\n")
+        for media_file_filtered in media_files_filtered:
+            print ('"'+media_file_filtered+'", ')
+        print("\n")
 
 def print_codecs(media_files):
     codecs = list()
@@ -124,15 +136,20 @@ def print_codecs(media_files):
     print("\ntotal "+ str(len(media_files)) + str(" files"))
 
 def main() -> None:
-    if(len(sys.argv) != 2):
-        path = '.' #use current pwd
-    else:
+    if(len(sys.argv) == 3):
         path = sys.argv[1] #use arg0 as path
+        filter_mode = sys.argv[2] #use arg2 as filter input
+    elif (len(sys.argv) == 2):
+        path = sys.argv[1] #use arg0 as path
+        filter_mode = " "
+    else:
+        path = '.' #use current pwd
+        filter_mode = " "
 
     media_files = scan_files(path) #scan all media files
     
     print("")
-    print_all(media_files)
+    print_all(media_files, filter_mode)
 
     print("")
     print_codecs(media_files)

convert/convert.py

@@ -0,0 +1,124 @@
+#!/usr/bin/env python3
+import json
+import os
+import subprocess
+import time
+import requests
+import sys
+from pathlib import Path
+
+PROM_URL = "http://127.0.0.1:9104/metrics"
+
+def load_config(path):
+    """Load JSON configuration file."""
+    with open(path, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+def wait_for_solar_power():
+    """
+    Wait until the Prometheus metric `fronius_site_autonomy_ratio` equals 1.0.
+    Check every 5 minutes if not available.
+    """
+    while True:
+        try:
+            r = requests.get(PROM_URL, timeout=5)
+            if r.status_code == 200:
+                for line in r.text.splitlines():
+                    if line.startswith("fronius_site_autonomy_ratio"):
+                        try:
+                            value = float(line.split()[-1])
+                            if value == 1.0:
+                                print("[INFO] Solar power available – starting conversion.")
+                                return
+                        except ValueError:
+                            pass
+            print("[INFO] No solar power – waiting 5 minutes...")
+        except requests.RequestException as e:
+            print(f"[WARN] Could not reach Prometheus: {e}")
+        time.sleep(300)  # Wait 5 minutes
+
+def analyze_codecs(oldfile, newfile, dst_folder):
+    """
+    Run codecVis to compare old and new files.
+    Then rename output.png to newfile.png.
+    """
+    cmd = ["codecVis", oldfile, newfile]
+    print(f"[CMD] {' '.join(cmd)}")
+    subprocess.run(cmd, cwd=dst_folder, check=True)
+
+    # Rename output.png to match the new file
+    output_png = Path(dst_folder) / "output.png"
+    new_png = Path(dst_folder) / (Path(newfile).name + ".png")
+    if output_png.exists():
+        output_png.rename(new_png)
+        print(f"[INFO] Analysis image saved as {new_png}")
+    else:
+        print("[WARN] output.png not found!")
+
+def main():
+    if len(sys.argv) != 2:
+        print("Give path to config file as argument.")
+        sys.exit(1)
+        
+    cfg = load_config(sys.argv[1])
+    dst_folder = Path(cfg["dst_folder"])
+    src_folder = Path(cfg["src_folder"])
+    dst_folder.mkdir(parents=True, exist_ok=True)
+
+    for job in cfg["jobs"]:
+        src_file = src_folder / job
+        tmp_movie_name = "tmp_" + Path(job).stem + ".mkv"
+        movie_name = Path(job).stem + ".mkv"
+
+        tmp_dst_file = dst_folder / tmp_movie_name
+        dst_file = dst_folder / movie_name
+
+        print(f"Source: {src_file}")
+        print(f"Temp name: {tmp_movie_name}")
+        print(f"Final name: {movie_name}")
+        
+        # Remove leftover temporary file
+        if tmp_dst_file.exists():
+            print(f"[INFO] File {tmp_dst_file} already exists. --> Delete!")
+            tmp_dst_file.unlink()
+            
+        # Skip if final file already exists
+        if dst_file.exists():
+            print(f"[INFO] Skip {dst_file}, already exists. --> Convert already done!")
+            continue
+
+        wait_for_solar_power()
+
+        try:
+            cmd = [
+                "taskset", "-c", "0,1,2,3",   # limit to first 4 CPU cores
+                "ffmpeg", "-i", str(src_file),
+                "-c:v", "libaom-av1",
+                "-c:a", "libopus",
+                "-mapping_family", "1",
+                "-af", "aformat=channel_layouts=5.1",
+                "-c:s", "copy",
+                "-map", "0",
+                "-crf", "24",
+                "-b:v", "0",
+                "-b:a", "128k",
+                "-cpu-used", "4",
+                "-row-mt", "1",
+                "-tiles", "2x2",
+                str(tmp_dst_file)
+            ]
+            print(f"[CMD] {' '.join(cmd)}")
+            subprocess.run(cmd, check=True)
+
+            # Rename temp file to final name
+            tmp_dst_file.rename(dst_file)
+
+            # Run codec analysis
+            analyze_codecs(str(src_file), str(dst_file), dst_folder)
+
+        except subprocess.CalledProcessError as e:
+            print(f"[ERROR] Processing failed for {job}: {e}")
+    
+
+if __name__ == "__main__":
+    main()

convert/convert_jobs.json

@@ -0,0 +1,8 @@
+{
+  "dst_folder": "/mnt/mainstorage/media/converted",
+  "src_folder": "/mnt/mainstorage/media/movies",
+
+  "jobs": [
+    "BigBuckBunny_320x180.mp4",
+  ]
+}

find_duplicates.py

@@ -0,0 +1,79 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+""" Author:                     Hendrik Schutter, localhorst@mosad.xyz
+    Date of creation:           2023/02/22
+    Date of last modification:  2023/02/22
+"""
+
+import os
+import sys
+import time
+import subprocess
+import datetime
+from dataclasses import dataclass
+from tqdm import tqdm
+import operator
+
+@dataclass
+class MediaFile:
+    name: str #without extension
+    extension: str #without dot
+    full_path: str
+
+def supported_file_extension(filename):
+    if filename.endswith('.mp4') or filename.endswith('.mkv') or filename.endswith('.m4v'):
+        return True
+    return False
+
+def get_number_of_files(path):
+    #filter(supported_file_extension, files)
+    return sum([len(list(filter(supported_file_extension, files))) for r, d, files in os.walk(path)])
+
+def cut_file_name(filename, max_lenght, ellipsis="..."):
+    if len(filename) > max_lenght:
+        return filename[:max_lenght-len(ellipsis)] + ellipsis
+    else:
+        return filename
+
+def scan_files(path):
+    total_numbers_to_scan = get_number_of_files(path)
+
+    media_files = list() #stores all found files with metadata
+
+    pbar = tqdm(total=total_numbers_to_scan) #print progress bar
+    
+    for root, dirs, files in os.walk(path, topdown=True):
+        for name in  filter(supported_file_extension, files):
+            pbar.set_description("Processing %s" % str("{:<32}".format(cut_file_name(name, 32))))
+            full_path = os.path.join(root, name)
+            media_files.append(MediaFile(name=os.path.splitext(name)[0], extension=os.path.splitext(name)[1], full_path=full_path))
+            pbar.update(1)
+    pbar.close()   
+    return media_files
+
+def print_all(media_files, path):
+    for media_file in media_files:
+        if (media_file.extension == ".mp4"):
+            #print(media_file.name)
+            file_test_path = path + media_file.name + ".mkv"
+            #print("Testing for: " + file_test_path)
+            if (os.path.isfile(file_test_path)):
+                print(media_file.full_path)
+                #os.remove(media_file.full_path)
+
+
+def main() -> None:
+    if(len(sys.argv) != 2):
+        path = '.' #use current pwd
+    else:
+        path = sys.argv[1] #use arg0 as path
+
+    media_files = scan_files(path) #scan all media files
+    
+    print("")
+    print_all(media_files, path)
+
+
+if __name__ == "__main__":
+    main()