From 4cb989db866e645f7f1927339d08ac90630f27ea Mon Sep 17 00:00:00 2001
From: localhorst <localhorst@mosad.xyz>
Date: Fri, 15 Aug 2025 12:03:31 +0200
Subject: [PATCH] next

---
 check_Names_and_Paths.sh |   4 +-
 check_metadata.py        | 147 +++++++++++++++++++++++++++++++++++++++
 find_duplicates.py       |   0
 3 files changed, 149 insertions(+), 2 deletions(-)
 mode change 100644 => 100755 check_Names_and_Paths.sh
 create mode 100755 check_metadata.py
 mode change 100644 => 100755 find_duplicates.py

diff --git a/check_Names_and_Paths.sh b/check_Names_and_Paths.sh
old mode 100644
new mode 100755
index e973428..db03364
--- a/check_Names_and_Paths.sh
+++ b/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
diff --git a/check_metadata.py b/check_metadata.py
new file mode 100755
index 0000000..d704a4c
--- /dev/null
+++ b/check_metadata.py
@@ -0,0 +1,147 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+""" Author:                     Hendrik Schutter, localhorst@mosad.xyz
+    Date of creation:           2022/02/13
+    Date of last modification:  2022/01/26
+"""
+
+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
+    codec: str
+    size: int #bytes
+    resolution: (int , int)
+    duration: int #in sec
+
+def supported_file_extension(filename):
+    if filename.endswith('.mp4') or filename.endswith('.mkv') or filename.endswith('.m4v'):
+        return True
+    return False
+
+def get_length(filename):
+    result = subprocess.run(["ffprobe", "-v", "error", "-show_entries",
+                             "format=duration", "-of",
+                             "default=noprint_wrappers=1:nokey=1", filename],
+        stdout=subprocess.PIPE,
+        stderr=subprocess.DEVNULL)
+    try:
+        length = float(result.stdout)
+    except ValueError:
+        length = 0.0
+    return length
+
+def get_codec(filename):
+    result = subprocess.run(["ffprobe", "-v", "error", "-select_streams", "v:0",
+                             "-show_entries", "stream=codec_name",
+                             "-of", "default=noprint_wrappers=1:nokey=1", filename],
+        stdout=subprocess.PIPE,
+        stderr=subprocess.DEVNULL)
+    return str(result.stdout.decode("utf-8")).rstrip("\n")
+
+def get_resolution(filename):
+    result = subprocess.run(["ffprobe", "-v", "error", "-select_streams", "v:0",
+                             "-show_entries", "stream=width,height",
+                             "-of", "default=noprint_wrappers=1:nokey=1", filename],
+        stdout=subprocess.PIPE,
+        stderr=subprocess.DEVNULL)
+    try:
+        resolution = ((result.stdout.decode("utf-8").rstrip("\n").partition('\n')[0]), (result.stdout.decode("utf-8").rstrip("\n").partition('\n')[2]))
+    except ValueError:
+        resolution = (0, 0)
+    return resolution
+
+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 human_readable_size(size, decimal_places=2):
+    for unit in ['B', 'KiB', 'MiB', 'GiB', 'TiB', 'PiB']:
+        if size < 1024.0 or unit == 'PiB':
+            break
+        size /= 1024.0
+    return f"{size:.{decimal_places}f} {unit}"
+
+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.basename(name), extension=os.path.splitext(name)[1], full_path=full_path, codec=get_codec(full_path), size=os.path.getsize(full_path), resolution=get_resolution(full_path),  duration=get_length(full_path)))
+            pbar.update(1)
+    pbar.close()   
+    return media_files
+
+def print_all(media_files):
+    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 int(media_file.resolution[0]) >= 1800 and media_file.codec != "av1" and media_file.codec != "vp9" and media_file.codec != "h265":
+        	print ('"'+media_file.name+'" ', end='')
+
+def print_codecs(media_files):
+    codecs = list()
+
+    for media_file in media_files:
+        if next((codec_type for codec_type in codecs if codec_type["name"] == media_file.codec), False):
+                #this codec type is already in list --> add occurrence
+                for codec_type in codecs:
+                    if (codec_type["name"] == media_file.codec):
+                        codec_type["occurrence"] +=1
+        else:
+            #this const is NOT in list --> create occurrence dict and add to list
+            thisdict = { }
+            thisdict["name"] = media_file.codec
+            thisdict["occurrence"] = 1
+            codecs.append(thisdict)
+
+    #sort bases on occurrence
+    codecs.sort(key=lambda x: x["occurrence"], reverse=True)
+
+    for codec_type in codecs:
+        print ("{:<8} | {:<16} | {:<8}".format(codec_type["name"], str(codec_type["occurrence"])+" files", str(round(float(float(100 / len(media_files)) * codec_type["occurrence"]),1))+"%"))
+    print("\ntotal "+ str(len(media_files)) + str(" files"))
+
+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)
+
+    print("")
+    print_codecs(media_files)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/find_duplicates.py b/find_duplicates.py
old mode 100644
new mode 100755