(chore): bumped up to 1.1.6

README.md

@@ -62,6 +62,8 @@
 
 > Use `pip3` command instead of `pip` if you are on Linux or MacOS.
 
+> Use `--break-system-packages` flag to install 'PytubePP' in global environment if you get `error: externally-managed-environment` while installing in Linux or MacOS (Don't worry it will not break your system packages, it's just a security mesure)
+
 ```terminal
 pip install pytubepp
 ```
@@ -72,21 +74,29 @@ pip install pytubepp
 pip install pytubefix pytubepp --upgrade
 ```
 
+**UNINSTALL: If you want to uninstall PytubePP (Use the command below to uninstall) NOTE: it will only remove the 'PytubePP' python package**
+```
+pip uninstall pytubepp -y
+```
+
 ### **📌 Commands and Flags**
 Using PytubePP is as simple as just supplying it only the YouTube video url as argument!
-** Before Starting Please NOTE: PytubePP follows a simple rule - "Use the Default Download Configuration if No Flags are Passed"
+> Before starting please NOTE: PytubePP follows a simple principle -> `Use Default Configuration if No Flags are Passed`
 * To download a video in default configuration (maximum resolution and without any caption by default) the command will look like:
 ```terminal
 pytubepp "https://youtube.com/watch?v=2lAe1cqCOXo"
 ```
+> NOTE: This command will behave differently if you have changed default configurations
 * To download the video in a specific resolution (suppose 480p) the command will be:
 ```terminal
 pytubepp "https://youtube.com/watch?v=2lAe1cqCOXo" -s 480p
 ```
+> NOTE: PytubePP always uses default configuration of flags if they are not passed for example if you only pass `-s` flag then it will use the default caption along with it, if you only pass `-c` then it will use default stream and vice versa
 * To download the video with embeded caption (suppose en - English) the command will be:
 ```terminal
 pytubepp "https://youtube.com/watch?v=2lAe1cqCOXo" -c en
 ```
+> NOTE: You can override and disable default caption for the current video if you pass `-c none`
 * To download the video in audio-only MP3 format the command will be:
 ```terminal
 pytubepp "https://youtube.com/watch?v=2lAe1cqCOXo" -s mp3
@@ -101,12 +111,13 @@ pytubepp "https://youtube.com/watch?v=2lAe1cqCOXo" -i
 | Flag | Usage | Requires Parameter | Requires URL | Parameters | Default |
 | :--- | :---  | :---               | :---         | :---       | :---    |
 | -s | Choose preferred download stream | YES | YES | `144` `144p` `240` `240p` `360` `360p` `480` `480p` `720` `720p` `hd` `1080` `1080p` `fhd` `1440` `1440p` `2k` `2160` `2160p` `4k` `4320` `4320p` `8k` `mp3` (Pass any one of them) | Your chosen Default Stream via `-ds` flag |
-| -c | Choose preferred caption | YES | YES | All [ISO 639-1 Language Codes](https://www.w3schools.com/tags/ref_language_codes.asp) + some others (Pass any one of them) eg: `en` for English | Your chosen Default Caption via `-dc` flag |
+| -c | Choose preferred caption | YES | YES | All [ISO 639-1 Language Codes](https://www.w3schools.com/tags/ref_language_codes.asp) + auto generated ones + `none` for No Caption (Pass any one of them) eg: `en` for English | Your chosen Default Caption via `-dc` flag |
 | -i | Shows the video information like: Title, Author, Views, Publication Date, Duration, Available Download Streams | NO | YES | No parameters | No default |
+| -ls | Lists all available streams (video, audio, caption) (only for debuging purposes) | NO | YES | No parameters | No default |
 | -ri | Shows the video information in raw json format | NO | YES | No parameters | No default |
 | -jp | Shows raw json output in prettified view (with indentation: 4) (primarily used with -ri flag)| NO | YES | No parameters | No default |
 | -ds | Set default download stream | YES | NO | `144p` `240p` `360p` `480p` `720p` `1080p` `1440p` `2160p` `4320p` `mp3` `max` (Pass any one of them) | `max` |
-| -dc | Set default caption | YES | NO | All [ISO 639-1 Language Codes](https://www.w3schools.com/tags/ref_language_codes.asp) + some others + `none` for No Caption (Pass any one of them) eg: `en` for English | `none` |
+| -dc | Set default caption | YES | NO | All [ISO 639-1 Language Codes](https://www.w3schools.com/tags/ref_language_codes.asp) + auto generated ones + `none` for No Caption (Pass any one of them) eg: `en` for English | `none` |
 | -df | Set custom download folder path | YES | NO | Use the full path excluding the last trailing slash within double quotes eg(in Linux): `"/path/to/folder"` (Make sure the folder path you enterted is already created and accessable) | Within `PytubePP Downloads` folder in your System's `Downloads` folder |
 | -r | Reset to default configuration (Download Folder, Default Stream) | NO | NO | No parameters | No default |
 | -sc | Show all current user configurations | NO | NO | No parameters | No default |

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pytubepp"
-version = "1.1.3"
+version = "1.1.6"
 authors = [
   { name="Subhamoy Biswas", email="hey@neosubhamoy.com" },
 ]

pytubepp/download.py

@@ -1,6 +1,6 @@
 from tqdm import tqdm
 from .config import get_temporary_directory, load_config
-from .utils import get_unique_filename, postprocess_cleanup
+from .utils import get_unique_filename, postprocess_cleanup, unpack_caption
 import os, re, requests, shutil, sys, random, ffmpy
 
 userConfig = load_config()
@@ -21,6 +21,7 @@ def download_progressive(stream, itag, title, resolution, file_extention, captio
     if caption_code:
         print(f'Downloading Caption ({caption_code})...')
         caption = captions[caption_code]
+        _, caption_lang = unpack_caption(caption)
         caption_file = os.path.join(tempDIR, random_filename + '_cap.srt')
         caption.save_captions(caption_file)
         print('Processing...')
@@ -28,7 +29,7 @@ def download_progressive(stream, itag, title, resolution, file_extention, captio
         output_temp_file_with_subs = os.path.join(tempDIR, random_filename + '_merged.' + file_extention)
         ff = ffmpy.FFmpeg(
             inputs={output_temp_file: None},
-            outputs={output_temp_file_with_subs: ['-i', caption_file, '-c', 'copy', '-c:s', 'mov_text', '-metadata:s:s:0', f'language={caption_code}', '-metadata:s:s:0', f'title={caption_code}', '-metadata:s:s:0', f'handler_name={caption_code}']}
+            outputs={output_temp_file_with_subs: ['-i', caption_file, '-c', 'copy', '-c:s', 'mov_text', '-metadata:s:s:0', f'language={caption_code}', '-metadata:s:s:0', f'title={caption_lang}', '-metadata:s:s:0', f'handler_name={caption_lang}']}
         )
         ff.run(stdout=devnull, stderr=devnull)
         devnull.close()

pytubepp/main.py

@@ -3,7 +3,7 @@ from tabulate import tabulate
 from .config import get_temporary_directory, load_config, update_config, reset_config
 from .download import download_progressive, download_nonprogressive, download_audio, progress
 from .postprocess import merge_audio_video, convert_to_mp3
-from .utils import get_version, clear_temp_files, is_valid_url, network_available
+from .utils import get_version, clear_temp_files, is_valid_url, network_available, ffmpeg_installed, nodejs_installed, unpack_caption
 import appdirs, os, re, sys, argparse, json
 
 class YouTubeDownloader:
@@ -43,9 +43,14 @@ class YouTubeDownloader:
             print('\nRequest timeout! Please check your network and try again...!!')
             sys.exit()
 
+        if not nodejs_installed():
+            print("\nWarning: Node.js is not installed or not found in PATH!")
+            print("BotGuard poToken generation will not work properly without Node.js environment")
+            print("Please install Node.js, read https://github.com/neosubhamoy/pytubepp#%EF%B8%8F-installation for instructions\n")
+        
         if is_valid_url(link):
             link = is_valid_url(link).group(1)
-            self.video = YouTube(link, 'ANDROID', on_progress_callback=progress)
+            self.video = YouTube(link, 'WEB', on_progress_callback=progress)
             self.author = self.video.author
             self.title = re.sub(r'[\\/*?:"<>|]', '_', self.author + ' - ' + self.video.title)
             self.thumbnail = self.video.thumbnail_url
@@ -90,7 +95,7 @@ class YouTubeDownloader:
                 'ado_bitrate': matching_stream.abr
             }
         else:
-            _select_suitable_audio_stream = lambda stream: 139 if stream.itag in [160, 133] else (251 if stream.mime_type == 'video/webm' else 140)
+            _select_suitable_audio_stream = lambda stream: 251 if stream.mime_type == 'video/webm' else 140
             # Check for HDR variants first
             hdr_stream = None
             if res in ['4320p', '2160p', '1440p', '1080p', '720p']:
@@ -146,9 +151,37 @@ class YouTubeDownloader:
                 print('Sorry, No video streams found....!!!')
                 sys.exit()
 
-            print(f'\nTitle: {self.video.title}\nAuthor: {self.author}\nPublished On: {self.video.publish_date.strftime("%d/%m/%Y")}\nDuration: {f"{self.video.length//3600:02}:{(self.video.length%3600)//60:02}:{self.video.length%60:02}" if self.video.length >= 3600 else f"{(self.video.length%3600)//60:02}:{self.video.length%60:02}"}\nViews: {self.views}\nCaptions: {[caption.code for caption in self.captions.keys()] or "Unavailable"}\n')
+            print(f'\nTitle: {self.video.title}\nAuthor: {self.author}\nPublished On: {self.video.publish_date.strftime("%d/%m/%Y")}\nDuration: {f"{self.video.length//3600:02}:{(self.video.length%3600)//60:02}:{self.video.length%60:02}" if self.video.length >= 3600 else f"{(self.video.length%3600)//60:02}:{self.video.length%60:02}"}\nViews: {self.views}\nCaptions: {"Available" if self.captions else "Unavailable"}')
+                
+            print('\n')
             print(tabulate(table, headers=['Stream', 'Alias (for -s flag)', 'Format', 'Size', 'FrameRate', 'V-Codec', 'A-Codec', 'V-BitRate', 'A-BitRate']))
             print('\n')
+
+            if self.captions:
+                caption_table = []
+                for caption in self.captions:
+                    cap_code, cap_lang = unpack_caption(caption)
+                    caption_table.append([cap_lang, cap_code])
+                print(tabulate(caption_table, headers=['Caption', 'CaptionCode (for -c flag)']))
+                print('\n')
+        else:
+            print('\nInvalid video link! Please enter a valid video url...!!')
+
+    def show_all_streams(self, link):
+        if self.set_video_info(link):
+            print(f"Available Streams({len(self.stream)}):")
+            if self.stream:
+                for stream in self.stream:
+                    print(stream)
+            else:
+                print('No stream available!')
+
+            print(f"\nAvailable Captions({len(self.captions)}):")
+            if self.captions:
+                for caption in self.captions:
+                    print(caption)
+            else:
+                print('No caption available!')
         else:
             print('\nInvalid video link! Please enter a valid video url...!!')
 
@@ -181,6 +214,15 @@ class YouTubeDownloader:
                 print('Sorry, No video streams found....!!!')
                 sys.exit()
 
+            captions_list = []
+            if self.captions:
+                for caption in self.captions:
+                    cap_code, cap_lang = unpack_caption(caption)
+                    captions_list.append({
+                        'code': cap_code,
+                        'lang': cap_lang
+                    })
+
             output = {
                 'id': self.video.video_id,
                 'title': self.video.title,
@@ -190,7 +232,7 @@ class YouTubeDownloader:
                 'published_on': self.video.publish_date.strftime('%d/%m/%Y'),
                 'duration': self.video.length,
                 'streams': streams_list,
-                'captions': [caption.code for caption in self.captions.keys()] or None
+                'captions': captions_list or None
             }
             
             print(json.dumps(output, indent=4 if prettify else None))
@@ -217,22 +259,38 @@ class YouTubeDownloader:
             print('\nInvalid video link! Please enter a valid video url...!!')
             return []
 
-    def print_short_info(self, chosen_stream):
-        resolution_map = {
-            '4320': '4320p (8K)', '4320p': '4320p (8K)', '8k': '4320p (8K)',
-            '2160': '2160p (4K)', '2160p': '2160p (4K)', '4k': '2160p (4K)',
-            '1440': '1440p (2K)', '1440p': '1440p (2K)', '2k': '1440p (2K)',
-            '1080': '1080p (FHD)', '1080p': '1080p (FHD)', 'fhd': '1080p (FHD)',
-            '720': '720p (HD)', '720p': '720p (HD)', 'hd': '720p (HD)',
-            '480': '480p (SD)', '480p': '480p (SD)',
-            '360': '360p (SD)', '360p': '360p (SD)',
-            '240': '240p (LD)', '240p': '240p (LD)',
-            '144': '144p (LD)', '144p': '144p (LD)',
-            'mp3': 'mp3 (Audio)'
-        }
-        print(f'\nTitle: {self.title}\nSelected Stream: {resolution_map.get(chosen_stream, "Unknown")}\n')
+    def print_short_info(self, chosen_stream, chosen_caption=None):
+        print(f'\nTitle: {self.title}')
+        
+        if chosen_stream == 'mp3':
+            print(f'Selected: Audio [128kbps (140)]')
+            return
+            
+        if chosen_stream in ['360', '360p']:
+            print(f"Selected: Video [360p (18)] + Audio [96kbps (18)]{f' + Caption [{chosen_caption}]' if chosen_caption else ''}")
+            return
+            
+        _select_suitable_audio_stream = lambda stream: 251 if stream.mime_type == 'video/webm' else 140
+        res = next((k for k, v in self.stream_resolutions.items() if chosen_stream in v['allowed_streams']), None)
+        
+        if res:
+            hdr_stream = None
+            if res in ['4320p', '2160p', '1440p', '1080p', '720p']:
+                hdr_itags = {'4320p': 702, '2160p': 701, '1440p': 700, '1080p': 699, '720p': 698}
+                hdr_stream = self.stream.get_by_itag(hdr_itags.get(res))
+            
+            matching_stream = hdr_stream if hdr_stream else self.stream.filter(res=res).first()
+            audio_stream = self.stream.get_by_itag(_select_suitable_audio_stream(matching_stream))
+            
+            print(f"Selected: Video [{res} ({matching_stream.itag})] + Audio [{audio_stream.abr} ({audio_stream.itag})]{f' + Caption [{chosen_caption}]' if chosen_caption else ''}")
 
     def download_stream(self, link, chosen_stream, chosen_caption=None):
+        if not ffmpeg_installed():
+            print("\nWarning: FFmpeg is not installed or not found in PATH!")
+            print("Some core functionalities like video processing will not work properly without FFmpeg")
+            print("Please install FFmpeg, read https://github.com/neosubhamoy/pytubepp#%EF%B8%8F-installation for instructions\n")
+            sys.exit()
+        
         if self.set_video_info(link):
             allowed_streams = self.get_allowed_streams(link)
             allowed_captions = self.get_allowed_captions(link)
@@ -242,7 +300,7 @@ class YouTubeDownloader:
                 sys.exit()
             
             if chosen_stream in allowed_streams:
-                self.print_short_info(chosen_stream)
+                self.print_short_info(chosen_stream, chosen_caption)
                 if chosen_stream in ['360', '360p']:
                     download_progressive(self.stream, 18, self.title, '360p', 'mp4', self.captions, chosen_caption)
                 elif chosen_stream in ['1080', '1080p', 'fhd']:
@@ -252,9 +310,9 @@ class YouTubeDownloader:
                 elif chosen_stream in ['480', '480p']:
                     merge_audio_video(self.title, '480p', 'mp4', download_nonprogressive(self.stream, 135, 140, 'mp4', self.temp_dir), self.captions, chosen_caption)
                 elif chosen_stream in ['240', '240p']:
-                    merge_audio_video(self.title, '240p', 'mp4', download_nonprogressive(self.stream, 133, 139, 'mp4', self.temp_dir), self.captions, chosen_caption)
+                    merge_audio_video(self.title, '240p', 'mp4', download_nonprogressive(self.stream, 133, 140, 'mp4', self.temp_dir), self.captions, chosen_caption)
                 elif chosen_stream in ['144', '144p']:
-                    merge_audio_video(self.title, '144p', 'mp4', download_nonprogressive(self.stream, 160, 139, 'mp4', self.temp_dir), self.captions, chosen_caption)
+                    merge_audio_video(self.title, '144p', 'mp4', download_nonprogressive(self.stream, 160, 140, 'mp4', self.temp_dir), self.captions, chosen_caption)
                 elif chosen_stream in ['4320', '4320p', '8k']:
                     self._handle_4320p_download(chosen_caption)
                 elif chosen_stream in ['2160', '2160p', '4k']:
@@ -315,8 +373,9 @@ def main():
     parser.add_argument('-ds', '--default-stream', default=argparse.SUPPRESS, help='set default download stream (default: max) [available arguments: 144p, 240p, 360p, 480p, 720p, 1080p, 1440p, 2160p, 4320p, mp3, max]')
     parser.add_argument('-dc', '--default-caption', default=argparse.SUPPRESS, help='set default caption (default: none) [available arguments: all language codes, none]')
     parser.add_argument('-s', '--stream', default=argparse.SUPPRESS, help='choose download stream for the current video (default: your chosen --default-stream) [available arguments: 144p, 240p, 360p, 480p, 720p, 1080p, 1440p, 2160p, 4320p, 144, 240, 360, 480, 720, 1080, 1440, 2160, 4320, mp3, hd, fhd, 2k, 4k, 8k]')
-    parser.add_argument('-c', '--caption', default=argparse.SUPPRESS, help='choose caption to embed for the current video (default: none)')
+    parser.add_argument('-c', '--caption', default=argparse.SUPPRESS, help='choose caption to embed for the current video (default: your chosen --default-caption) [available arguments: all language codes, none]')
     parser.add_argument('-i', '--show-info', action='store_true', help='show video info (title, author, views and available_streams)')
+    parser.add_argument('-ls', '--list-stream', action='store_true', help='list all available streams (video, audio, caption) (only for debuging purposes)')
     parser.add_argument('-ri', '--raw-info', action='store_true', help='show video info in raw json format')
     parser.add_argument('-jp', '--json-prettify', action='store_true', help='show json in prettified indented view')
     parser.add_argument('-sc', '--show-config', action='store_true', help='show all current user config settings')
@@ -351,7 +410,11 @@ def main():
 
         # Handle info display flags
         if args.show_info:
+            print('Loading...')
             downloader.show_video_info(args.url)
+        if args.list_stream:
+            print('Loading...')
+            downloader.show_all_streams(args.url)
         if args.raw_info:
             downloader.show_raw_info(args.url, args.json_prettify)
         if args.json_prettify and not args.raw_info:
@@ -359,10 +422,13 @@ def main():
         
         # Handle download cases
         if hasattr(args, 'stream') and hasattr(args, 'caption'):
+            print('Loading...')
             if downloader.set_video_info(args.url):
-                if args.caption not in downloader.captions.keys():
+                if (args.caption not in downloader.captions.keys()) and (args.caption != 'none'):
                     print('\nInvalid caption code or caption not available! Please choose a different caption...!! (use -i to see available captions)')
                     sys.exit()
+                elif args.caption == 'none':
+                    downloader.download_stream(args.url, args.stream)
                 elif args.stream == 'mp3' and downloader.stream.get_by_itag(140):
                     print(f'\nYou have chosen to download mp3 stream! ( Captioning audio files is not supported )')
                     answer = input('Do you still want to continue downloading ? [yes/no]\n')
@@ -376,6 +442,7 @@ def main():
                 else:
                     downloader.download_stream(args.url, args.stream, args.caption)
         elif hasattr(args, 'stream'):
+            print('Loading...')
             if downloader.set_video_info(args.url):
                 if downloader.default_caption == 'none':
                     downloader.download_stream(args.url, args.stream)
@@ -402,10 +469,31 @@ def main():
                     else:
                         print('Download cancelled! exiting...!!')
         elif hasattr(args, 'caption'):
+            print('Loading...')
             if downloader.set_video_info(args.url):
-                if args.caption not in downloader.captions.keys():
+                if (args.caption not in downloader.captions.keys()) and (args.caption != 'none'):
                     print('\nInvalid caption code or caption not available! Please choose a different caption...!! (use -i to see available captions)')
                     sys.exit()
+                elif args.caption == 'none':
+                    if downloader.default_stream == 'max' and downloader.maxres:
+                        downloader.download_stream(args.url, downloader.maxres)
+                    elif downloader.default_stream == 'mp3' and downloader.stream.get_by_itag(140):
+                        downloader.download_stream(args.url, downloader.default_stream)
+                    elif downloader.default_stream != 'max' and downloader.stream.filter(res=downloader.default_stream):
+                        downloader.download_stream(args.url, downloader.default_stream)
+                    else:
+                        if downloader.maxres:
+                            print(f'\nDefault stream not available! ( Default: {downloader.default_stream} | Available: {downloader.maxres} )')
+                            answer = input('Do you want to download the maximum available stream ? [yes/no]\n')
+                            while answer not in ['yes', 'y', 'no', 'n']:
+                                print('Invalid answer! try again...!! answer with: [yes/y/no/n]')
+                                answer = input('Do you want to download the maximum available stream ? [yes/no]\n')
+                            if answer in ['yes', 'y']:
+                                downloader.download_stream(args.url, downloader.maxres)
+                            else:
+                                print('Download cancelled! exiting...!!')
+                        else:
+                            print('Sorry, No downloadable video stream found....!!!')
                 elif downloader.default_stream == 'max' and downloader.maxres:
                     downloader.download_stream(args.url, downloader.maxres, args.caption)
                 elif downloader.default_stream == 'mp3' and downloader.stream.get_by_itag(140):
@@ -433,7 +521,8 @@ def main():
                             print('Download cancelled! exiting...!!')
                     else:
                         print('Sorry, No downloadable video stream found....!!!')
-        elif not any([args.show_info, args.raw_info, args.json_prettify]):  # If no info flags are set
+        elif not any([args.show_info, args.raw_info, args.json_prettify, args.list_stream]):  # If no info flags are set
+            print('Loading...')
             if downloader.set_video_info(args.url):
                 if downloader.default_stream == 'max' and downloader.maxres:
                     if downloader.default_caption == 'none':
@@ -523,8 +612,13 @@ def main():
         
         if hasattr(args, 'default_caption'):
             if args.default_caption != downloader.default_caption:
-                if not all(c.isalpha() or c in '.-' for c in args.default_caption) or len(args.default_caption) > 10:
-                    print('\nInvalid caption code! Only a-z, A-Z, dash (-) and dot (.) are allowed with maximum 10 characters...!!')
+                if not (re.match(r'^[a-z]{2}(-[A-Za-z]+)?$', args.default_caption) or
+                        re.match(r'^a\.[a-z]{2}(-[A-Za-z]+)?$', args.default_caption) or
+                        re.match(r'^none$', args.default_caption)):
+                    print('\nInvalid caption code! Allowed formats are:\n'
+                        '- ISO 639-1 language codes (e.g: en, zh-Hans)\n'
+                        '- Auto-generated variants: a.ISO639-1LanguageCode (e.g: a.en, a.zh-Hans)\n'
+                        '- none\n')
                 else:
                     update_config('defaultCaption', args.default_caption)
                     print(f'\nDefault caption updated to: {args.default_caption}')
@@ -546,6 +640,9 @@ def main():
         if args.show_info:
             print('\nNo video url supplied! exiting...!!')
 
+        if args.list_stream:
+            print('\nNo video url supplied! exiting...!!')
+
         if args.raw_info:
             print('\nNo video url supplied! exiting...!!')
 

pytubepp/postprocess.py

@@ -1,6 +1,6 @@
 from mutagen.id3 import ID3, APIC, TIT2, TPE1, TALB
 from .config import get_temporary_directory, load_config
-from .utils import get_unique_filename, postprocess_cleanup
+from .utils import get_unique_filename, postprocess_cleanup, unpack_caption
 from .download import download_thumbnail
 import os, shutil, ffmpy
 
@@ -17,6 +17,7 @@ def merge_audio_video(title, resolution, file_extention, random_filename, captio
     if caption_code:
         print(f'Downloading Caption ({caption_code})...')
         caption = captions[caption_code]
+        _, caption_lang = unpack_caption(caption)
         srt_file = os.path.join(tempDIR, random_filename + '_cap.srt')
         caption.save_captions(srt_file)
         vtt_file = os.path.join(tempDIR, random_filename + '_cap.vtt')
@@ -38,7 +39,7 @@ def merge_audio_video(title, resolution, file_extention, random_filename, captio
         input_params = {video_file: None, audio_file: None}
         output_params = {output_temp_file: ['-i', subtitle_file, '-c:v', 'copy', '-c:a', 'copy', 
                         '-c:s', subtitle_codec, '-metadata:s:s:0', f'language={caption_code}',
-                        '-metadata:s:s:0', f'title={caption_code}', '-metadata:s:s:0', f'handler_name={caption_code}']}
+                        '-metadata:s:s:0', f'title={caption_lang}', '-metadata:s:s:0', f'handler_name={caption_lang}']}
         
         devnull = open(os.devnull, 'w')
         ff = ffmpy.FFmpeg(inputs=input_params, outputs=output_params)

pytubepp/utils.py

@@ -15,6 +15,20 @@ def network_available():
     except subprocess.CalledProcessError:
         return False
     
+def nodejs_installed():
+    try:
+        subprocess.run(['node', '--version'], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=True)
+        return True
+    except (subprocess.CalledProcessError, FileNotFoundError):
+        return False
+    
+def ffmpeg_installed():
+    try:
+        subprocess.run(['ffmpeg', '-version'], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=True)
+        return True
+    except (subprocess.CalledProcessError, FileNotFoundError):
+        return False
+
 def get_version():
     try:
         return version('pytubepp')
@@ -22,7 +36,7 @@ def get_version():
         return "Unknown"
     
 def is_valid_url(url):
-    match = re.search(r"(https?://(?:www\.|music\.)?youtube\.com/watch\?v=[^&]{11}|https?://youtu\.be/[^?&]*(\?si=[^&]*)?)", url)
+    match = re.search(r"(https?://(?:www\.|music\.)?youtube\.com/(?:watch\?v=[^&]{11}|shorts/[^?&]+)|https?://youtu\.be/[^?&]*(\?si=[^&]*)?)", url)
     return match
     
 def get_unique_filename(filename, directory=downloadDIR):
@@ -33,6 +47,17 @@ def get_unique_filename(filename, directory=downloadDIR):
         counter += 1
     return filename
 
+def unpack_caption(caption):
+    caption_str = str(caption)
+    code_start = caption_str.find('code="') + 6
+    code_end = caption_str.find('"', code_start)
+    lang_start = caption_str.find('lang="') + 6
+    lang_end = caption_str.find('"', lang_start)
+    
+    code = caption_str[code_start:code_end]
+    lang = caption_str[lang_start:lang_end]
+    return code, lang
+
 def postprocess_cleanup(dir, files, random_filename):
     for file in files:
         file_path = os.path.join(dir, random_filename + file)