#!/bin/python import sys import os import subprocess import json # cmd = "ls ../Videos/OBS/*.mkv" # result = subprocess.run(cmd, shell=True, capture_output=True, text=True) # print(result.stdout) color = True try: from termcolor import colored except ImportError: if os.name == "posix": print("For nicer output install termcolor:\nsudo \'your installer\' python-termcolor") else: print("For nicer output install termcolor:\npip install termcolor") color = False EXT=[".mp4", ".mkv", ".avi", ".mov", ".wmv", ".flv", ".webm", ".lrv", ".gif"] NORMAL_STYLE = ("white", None, []) ERROR_STYLE = ("red", None, ["bold"]) WARN_STYLE = ("yellow", None, ["bold"]) INFO_STYLE = ("cyan", None, []) SUCCESS_STYLE = ("green", None, ["bold"]) DEBUG_STYLE = ("magenta", None, ["dark"]) def np(string, style, end = "\n"): if color: print(colored(string, *style), end=end) else: print(string, end=end) def human_readable_size(size, decimal_places=2): for unit in ['B','KB','MB','GB','TB']: if size < 1024: return f"{size:.{decimal_places}f} {unit}" size /= 1024 def calculate_aspect(width: int, height: int) -> str: temp = 0 def gcd(a, b): """The GCD (greatest common divisor) is the highest number that evenly divides both width and height.""" return a if b == 0 else gcd(b, a % b) if width == height: return "1:1" if width < height: temp = width width = height height = temp divisor = gcd(width, height) x = int(width / divisor) if not temp else int(height / divisor) y = int(height / divisor) if not temp else int(width / divisor) return f"{x}:{y}" def get_interlace_label(fo): if not fo: return "Progressive" fo = str(fo).lower() # Map ffprobe codes to standard labels if fo in ["tt", "tff", "tb"]: return "Interlaced (TFF)" elif fo in ["bb", "bff", "bt"]: return "Interlaced (BFF)" elif "progressive" in fo: return "Progressive" return "Progressive" # Default assumption for modern web video class video_lines: def __init__(self, stream, duration): if stream.get("index"): self.id = stream.get("index") else: self.id = None if stream.get("name"): self.name = stream.get("name") else: self.name = "" if stream.get("name"): self.duration = seconds_to_hms(stream.get("duration")) else: self.duration = duration if stream.get("codec_name"): self.codec = stream.get("codec_name") else: self.codec = "" if stream.get("width"): self.width = stream.get("width") else: self.width = "" if stream.get("height"): self.height = stream.get("height") else: self.height = "" self.resolution = f"{self.width}x{self.height}" if stream.get("r_frame_rate"): num, den = map(int, stream.get("r_frame_rate").split("/")) self.framerate = round(num / den, 2) else: self.framerate = "" if stream.get("display_aspect_ratio"): self.aspect_ratio = stream.get("display_aspect_ratio") elif self.resolution != "x": self.aspect_ratio = calculate_aspect(self.width, self.height) else: self.aspect_ratio = "" if stream.get("pix_fmt"): self.pix_fmt = stream.get("pix_fmt") else: self.pix_fmt = "" if stream.get("color_space"): self.color_space = stream.get("color_space") else: self.color_space = "" if stream.get("field_order"): self.field_order = get_interlace_label(stream.get("field_order")) else: self.field_order = "" def __str__(self): string = "Video" if self.id != None: string += f" {self.id:02d}: " else: string += f": " string += f"{self.codec}" if self.duration: string += f" {self.duration}s" if self.resolution != "x": string += f"({self.resolution}" if self.framerate != "x": string += f"@{self.framerate})" if self.aspect_ratio: string += f" [{self.aspect_ratio}]" if self.pix_fmt and self.color_space: string += f" [{self.pix_fmt}, {self.color_space}]" if self.field_order: string += f" [{self.field_order}]" return string LANG_CODES = { "eng": "English", "en": "English", "spa": "Spanish", "es": "Spanish", "fra": "French", "fr": "French", "deu": "German", "ger": "German", "de": "German", "jpn": "Japanese", "ja": "Japanese", "ita": "Italian", "it": "Italian", "por": "Portuguese", "pt": "Portuguese", "rus": "Russian", "ru": "Russian", "chi": "Chinese", "zho": "Chinese", "zh": "Chinese", "kor": "Korean", "ko": "Korean", "dut": "Dutch", "nl": "Dutch", "swe": "Swedish", "sv": "Swedish", "fin": "Finnish", "fi": "Finnish", "pol": "Polish", "pl": "Polish", "ara": "Arabic", "ar": "Arabic", "hin": "Hindi", "hi": "Hindi", "tur": "Turkish", "tr": "Turkish", "und": "Undefined", " ": "Undefined", "ab": "Abkhazian", "abk": "Abkhazian", "aa": "Afar", "aar": "Afar", "af": "Afrikaans", "afr": "Afrikaans", "ak": "Akan", "aka": "Akan", "twi": "Twi", "fat": "Fanti", "sq": "Albanian", "sqi": "Albanian", "alb": "Albanian", "am": "Amharic", "amh": "Amharic", "arb": "Arabic", "an": "Aragonese", "arg": "Aragonese", "hy": "Armenian", "hye": "Armenian", "arm": "Armenian", "as": "Assamese", "asm": "Assamese", "av": "Avaric", "ava": "Avaric", "ae": "Avestan", "ave": "Avestan", "ay": "Aymara", "aym": "Aymara", "az": "Azerbaijani", "aze": "Azerbaijani", "bm": "Bambara", "bam": "Bambara", "ba": "Bashkir", "bak": "Bashkir", "eu": "Basque", "eus": "Basque", "baq": "Basque", "be": "Belarusian", "bel": "Belarusian", "bn": "Bengali", "ben": "Bengali", "bi": "Bislama", "bis": "Bislama", "bs": "Bosnian", "bos": "Bosnian", "br": "Breton", "bre": "Breton", "bg": "Bulgarian", "bul": "Bulgarian", "my": "Burmese", "mya": "Burmese", "ca": "Catalan", "cat": "Catalan", "ch": "Chamorro", "cha": "Chamorro", "ce": "Chechen", "che": "Chechen", "ny": "Chichewa", "nya": "Chichewa", "cu": "Church Slavonic", "chu": "Church Slavonic", "cv": "Chuvash", "chv": "Chuvash", "kw": "Cornish", "cor": "Cornish", "co": "Corsican", "cos": "Corsican", "cr": "Cree", "cre": "Cree", "hr": "Croatian", "hrv": "Croatian", "cs": "Czech", "ces": "Czech", "cze": "Czech", "da": "Danish", "dan": "Danish", "dv": "Divehi", "div": "Divehi", "dz": "Dzongkha", "dzo": "Dzongkha", "eo": "Esperanto", "epo": "Esperanto", "et": "Estonian", "est": "Estonian", "ee": "Ewe", "ewe": "Ewe", "fo": "Faroese", "fao": "Faroese", "fj": "Fijian", "fij": "Fijian", "fre": "French", "fy": "Western Frisian", "fry": "Western Frisian", "ff": "Fulah", "ful": "Fulah", "gd": "Gaelic, Scottish Gaelic", "gla": "Gaelic", "gl": "Galician", "glg": "Galician", "lg": "Ganda", "lug": "Ganda", "ka": "Georgian", "kat": "Georgian", "geo": "Georgian", "el": "Greek", "ell": "Greek", "gre": "Greek", "kl": "Kalaallisut", "kal": "Kalaallisut", "gn": "Guarani", "grn": "Guarani", "gu": "Gujarati", "guj": "Gujarati", "ht": "Haitian Creole", "hat": "Haitian Creole", "ha": "Hausa", "hau": "Hausa", "he": "Hebrew", "heb": "Hebrew", "hz": "Herero", "her": "Herero", "ho": "Hiri Motu", "hmo": "Hiri Motu", "hu": "Hungarian", "hun": "Hungarian", "is": "Icelandic", "isl": "Icelandic", "ice": "Icelandic", "io": "Ido", "ido": "Ido", "ig": "Igbo", "ibo": "Igbo", "id": "Indonesian", "ind": "Indonesian", "ia": "Interlingua", "ina": "Interlingua", "ie": "Interlingue", "ile": "Interlingue", "iu": "Inuktitut", "iku": "Inuktitut", "ik": "Inupiaq", "ipk": "Inupiaq", "ga": "Irish", "gle": "Irish", "jv": "Javanese", "jav": "Javanese", "kn": "Kannada", "kan": "Kannada", "kr": "Kanuri", "kau": "Kanuri", "ks": "Kashmiri", "kas": "Kashmiri", "kk": "Kazakh", "kaz": "Kazakh", "km": "Central Khmer", "khm": "Central Khmer", "ki": "Kikuyu", "kik": "Kikuyu", "rw": "Kinyarwanda", "kin": "Kinyarwanda", "ky": "Kyrgyz", "kir": "Kyrgyz", "kv": "Komi", "kom": "Komi", "kg": "Kongo", "kon": "Kongo", "kj": "Kuanyama", "kua": "Kuanyama", "ku": "Kurdish", "kur": "Kurdish", "lo": "Lao", "lao": "Lao", "la": "Latin", "lat": "Latin", "lv": "Latvian", "lav": "Latvian", "li": "Limburgan", "lim": "Limburgan", "ln": "Lingala", "lin": "Lingala", "lt": "Lithuanian", "lit": "Lithuanian", "lu": "Luba-Katanga", "lub": "Luba-Katanga", "lb": "Luxembourgish", "ltz": "Luxembourgish", "mk": "Macedonian", "mkd": "Macedonian", "mac": "Macedonian", "mg": "Malagasy", "mlg": "Malagasy", "ms": "Malay", "msa": "Malay", "ml": "Malayalam", "mal": "Malayalam", "mt": "Maltese", "mlt": "Maltese", "gv": "Manx", "glv": "Manx", "mi": "Maori", "mri": "Maori", "mao": "Maori", "mr": "Marathi", "mar": "Marathi", "mh": "Marshallese", "mah": "Marshallese", "mn": "Mongolian", "mon": "Mongolian", "na": "Nauru", "nau": "Nauru", "nv": "Navajo", "nav": "Navajo", "nd": "North Ndebele", "nde": "North Ndebele", "nr": "South Ndebele", "nbl": "South Ndebele", "ng": "Ndonga", "ndo": "Ndonga", "ne": "Nepali", "nep": "Nepali", "no": "Norwegian", "nor": "Norwegian", "nb": "Norwegian Bokmål", "nob": "Norwegian Bokmål", "nn": "Norwegian Nynorsk", "nno": "Norwegian Nynorsk", "oc": "Occitan", "oci": "Occitan", "oj": "Ojibwa", "oji": "Ojibwa", "or": "Oriya", "ori": "Oriya", "om": "Oromo", "orm": "Oromo", "os": "Ossetian", "oss": "Ossetian", "pi": "Pali", "pli": "Pali", "ps": "Pashto", "pus": "Pashto", "fa": "Persian", "fas": "Persian", "per": "Persian", "pa": "Punjabi", "pan": "Punjabi", "qu": "Quechua", "que": "Quechua", "ro": "Romanian", "ron": "Romanian", "rum": "Romanian", "rm": "Romansh", "roh": "Romansh", "rn": "Rundi", "run": "Rundi", "se": "Northern Sami", "sme": "Northern Sami", "sm": "Samoan", "smo": "Samoan", "sg": "Sango", "sag": "Sango", "sa": "Sanskrit", "san": "Sanskrit", "sc": "Sardinian", "srd": "Sardinian", "sr": "Serbian", "srp": "Serbian", "sn": "Shona", "sna": "Shona", "sd": "Sindhi", "snd": "Sindhi", "si": "Sinhala", "sin": "Sinhala", "sk": "Slovak", "slk": "Slovak", "slo": "Slovak", "sl": "Slovenian", "slv": "Slovenian", "so": "Somali", "som": "Somali", "st": "Southern Sotho", "sot": "Southern Sotho", "su": "Sundanese", "sun": "Sundanese", "sw": "Swahili", "swa": "Swahili", "ss": "Swati", "ssw": "Swati", "tl": "Tagalog", "tgl": "Tagalog", "ty": "Tahitian", "tah": "Tahitian", "tg": "Tajik", "tgk": "Tajik", "ta": "Tamil", "tam": "Tamil", "tt": "Tatar", "tat": "Tatar", "te": "Telugu", "tel": "Telugu", "th": "Thai", "tha": "Thai", "bo": "Tibetan", "bod": "Tibetan", "tib": "Tibetan", "ti": "Tigrinya", "tir": "Tigrinya", "to": "Tongan", "ton": "Tongan", "ts": "Tsonga", "tso": "Tsonga", "tn": "Tswana", "tsn": "Tswana", "tk": "Turkmen", "tuk": "Turkmen", "ug": "Uighur", "uig": "Uighur", "uk": "Ukrainian", "ukr": "Ukrainian", "ur": "Urdu", "urd": "Urdu", "uz": "Uzbek", "uzb": "Uzbek", "ve": "Venda", "ven": "Venda", "vi": "Vietnamese", "vie": "Vietnamese", "vo": "Volapük", "vol": "Volapük", "wa": "Walloon", "wln": "Walloon", "cy": "Welsh", "cym": "Welsh", "wel": "Welsh", "wo": "Wolof", "wol": "Wolof", "xh": "Xhosa", "xho": "Xhosa", "ii": "Sichuan Yi", "iii": "Sichuan Yi", "yi": "Yiddish", "yid": "Yiddish", "yo": "Yoruba", "yor": "Yoruba", "za": "Zhuang", "zha": "Zhuang", "zu": "Zulu", "zul": "Zulu" } class audio_lines: def __init__(self, stream, file_duration): # 1. Basic ID self.id = stream.get("index") # 2. Name (usually in tags as 'title') self.name = stream.get("tags", {}).get("title", "") # 3. Language (usually in tags) raw_lang = stream.get("tags", {}).get("language", "und").lower() self.language = LANG_CODES.get(raw_lang, raw_lang.capitalize()) # 4. Duration (fallback to file duration if stream duration is missing) stream_dur = stream.get("duration") if stream_dur: self.duration = seconds_to_hms(float(stream_dur)) else: self.duration = file_duration # 5. Codec self.codec = stream.get("codec_name", "") # 6. Sample Rate (converted to kHz for readability, e.g., 48000 -> 48.0) sr = stream.get("sample_rate") self.sample_rate = f"{int(sr) / 1000} kHz" if sr else "" # 7. Channels self.channels = stream.get("channels", "") # 8. Bit Depth # PCM uses bits_per_sample; lossy like AAC/MP3 might use bits_per_raw_sample depth = stream.get("bits_per_sample") or stream.get("bits_per_raw_sample") self.bit_depth = f"{depth}-bit" if depth else "" # 9. Bitrate (converted to kbps) br = stream.get("bit_rate") self.bitrate = f"{int(br) // 1000} kbps" if br else "" def __str__(self): string = "Audio" if self.id is not None: string += f" {self.id}: " else: string += ": " string += f"{self.codec}" if self.language: string += f" [{self.language}]" if self.duration: string += f" {self.duration}s" # Grouping audio specs: Channels, Sample Rate, and Bit Depth specs = [] if self.channels: specs.append(f"{self.channels}ch") if self.sample_rate: specs.append(self.sample_rate) if self.bit_depth: specs.append(self.bit_depth) if specs: string += f" ({', '.join(specs)})" if self.bitrate: string += f" @{self.bitrate}" if self.name: string += f" [{self.name}]" return string class subtitles: def __init__(self, stream, file_duration): self.id = stream.get("index") self.name = stream.get("tags", {}).get("title", "") # Language translation raw_lang = stream.get("tags", {}).get("language", "und") self.language = LANG_CODES.get(raw_lang, raw_lang.capitalize()) # Duration logic stream_dur = stream.get("duration") self.duration = seconds_to_hms(float(stream_dur)) if stream_dur else file_duration # Codec (e.g., srt, ass, subrip) self.codec = stream.get("codec_name", "") # Disposition (Extra helpful info for subs) dispo = stream.get("disposition", {}) self.is_forced = dispo.get("forced") == 1 self.is_default = dispo.get("default") == 1 def __str__(self): parts = [f"Subtitle {self.id:02d}:" if self.id is not None else "Subtitle:"] if self.codec: parts.append(self.codec.upper()) if self.language: parts.append(f"[{self.language}]") if self.duration: parts.append(f"{self.duration}s") # Add flags for Forced/Default flags = [] if self.is_forced: flags.append("FORCED") if self.is_default: flags.append("Default") if flags: parts.append(f"({'/'.join(flags)})") if self.name: parts.append(f"[{self.name}]") return " ".join(parts) def get_video_lines(file): cmd = ["ffprobe", "-v", "error", "-select_streams", "v", # video streams only "-show_entries", "stream=index,codec_name,width,height,r_frame_rate,bit_rate,duration,nb_frames,pix_fmt,field_order,time_base,display_aspect_ratio,color_space,color_transfer,color_primaries,bits_per_raw_sample:stream_tags=title", "-of", "json", file ] result = subprocess.run(cmd, capture_output=True, text=True) info = json.loads(result.stdout) streams = info.get("streams", []) return streams def get_audio_lines(file): cmd = [ "ffprobe", "-v", "error", "-select_streams", "a", # Select audio streams only "-show_entries", # Entries mapped to your requirements: "stream=index,codec_name,sample_rate,channels,bits_per_sample,bits_per_raw_sample,bit_rate,duration" + ":stream_tags=language,title", "-of", "json", file ] try: result = subprocess.run(cmd, capture_output=True, text=True, check=True) info = json.loads(result.stdout) return info.get("streams", []) except subprocess.CalledProcessError as e: print(f"Error running ffprobe: {e.stderr}") return [] def get_subtitle_lines(file): cmd = [ "ffprobe", "-v", "error", "-select_streams", "s", # Subtitle streams only "-show_entries", "stream=index,codec_name,duration:stream_tags=language,title:stream_disposition=forced,default", "-of", "json", file ] try: result = subprocess.run(cmd, capture_output=True, text=True, check=True) info = json.loads(result.stdout) return info.get("streams", []) except subprocess.CalledProcessError: return [] def get_video_duration(file_path): cmd = [ "ffprobe", "-v", "error", "-show_entries", "format=duration", "-of", "default=noprint_wrappers=1:nokey=1", file_path ] result = subprocess.run(cmd, capture_output=True, text=True) duration = float(result.stdout.strip()) return duration def seconds_to_hms(seconds): h = int(seconds // 3600) m = int((seconds % 3600) // 60) s = int(seconds % 60) return f"{h:02}:{m:02}:{s:02}" def get_stream_bitrate(file_path, stream=None): # Get duration in seconds duration = get_video_duration(file_path) # Get file size in bits size_bits = os.path.getsize(file_path) * 8 # Approximate average bitrate avg_bitrate = size_bits / duration if duration > 0 else 0 return avg_bitrate # bits per second class video_file: def __init__(self, path, base_tab=""): self.base_tab = base_tab # \t self.path = path # folder/25.mkv self.name = os.path.basename(path) # 25.mkv self.size = human_readable_size(os.path.getsize(path)) # 198MB self.duration = seconds_to_hms(get_video_duration(path)) self.bitrate = int((os.path.getsize(path) * 8)/get_video_duration(path))/1000000 if get_video_duration(path) > 0 else 0 # self. = get_video_lines(path) self.videos = [] self.audios = [] self.subtitles = [] for vl in get_video_lines(path): video_line = video_lines(vl, self.duration) self.videos.append(video_line) for al in get_audio_lines(path): audio_line = audio_lines(al, self.duration) self.videos.append(audio_line) for st in get_subtitle_lines(path): subtitle = subtitles(st, self.duration) self.videos.append(subtitle) def print(self): if self.base_tab == "\t": np(f"{self.base_tab}{self.name} ({self.size}, {self.duration}, {self.bitrate} MB/s):", NORMAL_STYLE) else: np(f"{os.path.dirname(self.path)}/", INFO_STYLE) np(f"\t{self.name} ({self.size}, {self.duration}, {self.bitrate} MB/s):", NORMAL_STYLE) for video in self.videos: np(f"\t\t{video}", NORMAL_STYLE) for audio in self.audios: np(f"\t\t{audio}", NORMAL_STYLE) for subtitle in self.subtitles: np(f"\t\t{subtitle}", NORMAL_STYLE) print() def get_folder_info(files): np(f"Videos in {os.path.dirname(files[0])}/", INFO_STYLE) for file in files: file = video_file(file, "\t") file.print() def get_file_info(file, file_name): file = video_file(file, "") file.print() def handle_files(files, all_files): if(files != []): files.sort() grouped = [] current_dir = None current_group = [] for f in files: dir_path = os.path.dirname(f) if dir_path != current_dir: if current_group: if len(current_group) == 1: grouped.append(current_group[0]) # singleton as string else: grouped.append(current_group) # multiple files as list current_dir = dir_path current_group = [f] else: current_group.append(f) # Add the last group if current_group: if len(current_group) == 1: grouped.append(current_group[0]) else: grouped.append(current_group) all_files.extend(grouped) def handle_folders(dirs, all_files): if(dirs != []): dirs.sort(key=lambda f: os.path.dirname(f)) for dir in dirs: dir_files = [] for file in os.scandir(dir): if file.is_file(): file = file.path if os.path.splitext(file)[1].lower() in EXT: dir_files.append(file) else: np(f"{file} is not a compatabile Video file", WARN_STYLE) if(dir_files != []): dir_files.sort() all_files.append(dir_files) if __name__ == "__main__": # print(sys.argv) file_dir_array = [] if len(sys.argv) == 0: print("Something went horribly wrong!") if len(sys.argv) == 1: # current_dir = os.path.dirname(os.path.realpath(__file__)) current_dir = os.getcwd() handle_folders([os.path.abspath(current_dir)], file_dir_array) else: files = [] dirs = [] for argv in sys.argv[1:]: if os.path.isfile(argv): files.append(os.path.abspath(argv)) elif os.path.isdir(argv): dirs.append(os.path.abspath(argv)) else: np(f"This is not a file or directory: {argv}\nNow canceling!", ERROR_STYLE) sys.exit() handle_folders(dirs, file_dir_array) handle_files(files, file_dir_array) for element in file_dir_array: if type(element) == list: get_folder_info(element) else: file = element get_file_info(file, file)