uncomment the mark_as_downloaded

.gitignore

@@ -1,3 +1,8 @@
 /secrets.json
 /client_secrets.json
 /clips_database.db
+database.db
+save
+__pycache__
+twitch_secrets.json
+.vscode/settings.json

.vscode/launch.json

@@ -0,0 +1,15 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python Debugger: Python File",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "${file}",
+            "args": []
+        }
+    ]
+}

auth_twitch.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python3
+import asyncio
+import json
+import os
+import webbrowser
+from twitchAPI.twitch import Twitch
+from twitchAPI.oauth import UserAuthenticator
+from twitchAPI.type import AuthScope
+
+SECRETS_FILE = "twitch_secrets.json"
+
+def load_credentials():
+    """Loads existing Client ID and Secret from your JSON file."""
+    if not os.path.exists(SECRETS_FILE):
+        raise FileNotFoundError(f"Could not find {SECRETS_FILE} in this directory.")
+    with open(SECRETS_FILE, "r") as f:
+        data = json.load(f)
+    return data.get("client_id"), data.get("client_secret")
+
+def save_token_to_json(token):
+    """Saves the generated token into twitch_secrets.json under 'manual_token'."""
+    with open(SECRETS_FILE, "r") as f:
+        data = json.load(f)
+    
+    # Inject the new token
+    data["manual_token"] = token
+    
+    with open(SECRETS_FILE, "w") as f:
+        json.dump(data, f, indent=4)
+    print(f"\n[SUCCESS] Token saved inside '{SECRETS_FILE}' under 'manual_token'!")
+
+async def main():
+    try:
+        client_id, client_secret = load_credentials()
+        if not client_id or not client_secret:
+            print("[ERROR] Please add your client_id and client_secret to the JSON file first.")
+            return
+
+        print("Initializing local connection loop...")
+        # Initialize official Twitch connection interface
+        twitch = await Twitch(client_id, client_secret)
+        
+        # Scopes: We leave this empty [] since VOD collection only requires basic public clearance
+        scopes = [] 
+        
+        # Create an authenticator that automatically sets up http://localhost:17563
+        auth = UserAuthenticator(twitch, scopes, url="http://localhost:17563")
+        
+        # Request authentication URL
+        auth_url = auth.return_auth_url()
+        print(f"\nIf your browser does not open automatically, copy and paste this URL into your browser:\n{auth_url}\n")
+        
+        # Open your system default browser to let you manually click "Authorize"
+        webbrowser.open(auth_url)
+        
+        print("Waiting for you to click 'Authorize' in your web browser...")
+        # The script halts here, running a local background server until you click authorize
+        token, refresh_token = await auth.authenticate()
+        
+        print(f"\nSuccessfully generated Token: {token}")
+        
+        # Save it right back into your configuration file
+        save_token_to_json(token)
+        
+        # Gracefully shut down the library connection
+        await twitch.close()
+
+    except Exception as e:
+        print(f"\n[ERROR] An error occurred: {e}")
+        print("Double-check that http://localhost:17563 is added to your Twitch Dev Console.")
+
+if __name__ == "__main__":
+    # Run the asynchronous loop
+    asyncio.run(main())

database.py

@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+import sqlite3
+from datetime import datetime
+from pathlib import Path
+from typing import Any
+
+class Database:
+    def __init__(self):
+        self.columns = "id, title, created_at, view_count, duration, url, thumbnail_url, game_id, game_name, stream_id, creator_name, clip_is, downloaded, uploaded_yt, uploaded_yt_chats, uploaded_yt_shorts"
+
+        # IMPORTANT Must check if database.db exists before connecting to it.
+        file_exists = Path("database.db").is_file()
+
+        self.conn = sqlite3.connect("database.db")
+        self.cursor = self.conn.cursor()
+
+        if not file_exists:
+            self.create_database()
+
+    def __del__(self):
+        # Destructors are unpredictable in Python; explicitly close when done instead
+        try:
+            self.close_database()
+        except:
+            pass
+
+    def create_database(self):
+        """Creates a table structured explicitly for Twitch videos properties."""
+        self.cursor.execute("""
+        CREATE TABLE IF NOT EXISTS twitch_videos (
+            id TEXT PRIMARY KEY,
+            title TEXT NOT NULL,
+            created_at TEXT NOT NULL,
+            view_count INTEGER NOT NULL,
+            duration TEXT NOT NULL,
+            url TEXT NOT NULL,
+            thumbnail_url TEXT NOT NULL,
+            game_id INTEGER NOT NULL,
+            game_name TEXT NOT NULL,
+            stream_id TEXT NOT NULL,
+            creator_name TEXT NOT NULL,
+            clip_is BOOLEAN NOT NULL DEFAULT 0,
+            downloaded BOOLEAN NOT NULL DEFAULT 0,
+            uploaded_yt BOOLEAN NOT NULL DEFAULT 0,
+            uploaded_yt_chats BOOLEAN NOT NULL DEFAULT 0,
+            uploaded_yt_shorts BOOLEAN NOT NULL DEFAULT 0
+        )
+        """)
+        
+        self.conn.commit()
+
+    def close_database(self):
+        """Commit before we close."""
+        if self.conn:
+            self.conn.commit()
+            self.conn.close()
+
+    def __mark_as(self, record_id: str, set_sql: str):
+        self.cursor.execute(
+            f"UPDATE twitch_videos SET {set_sql} = 1 WHERE id = ?", 
+            (record_id,))
+        self.conn.commit()
+
+    def mark_as_uploaded_shorts(self, record_id: str):
+        """Flags a specific row record to uploaded_yt_shorts (1)."""
+        self.__mark_as(record_id, "uploaded_yt_shorts")
+
+    def mark_as_uploaded_chats(self, record_id: str):
+        """Flags a specific row record to uploaded_yt_chats (1)."""
+        self.__mark_as(record_id, "uploaded_yt_chats")
+
+    def mark_as_uploaded_yt(self, record_id: str):
+        """Flags a specific row record to uploaded_yt (1)."""
+        self.__mark_as(record_id, "uploaded_yt")
+
+    def mark_as_downloaded(self, record_id: str):
+        """Flags a specific row record to downloaded (1)."""
+        self.__mark_as(record_id, "downloaded")
+
+    def __get_unuploaded(self, set_sql: str) -> list[Any]:
+        """Retrieve all rows that were download but not uploaded"""
+        self.cursor.execute(f"SELECT {self.columns} FROM twitch_videos WHERE downloaded = 1 AND {set_sql} = 0")
+        return self.cursor.fetchall()
+
+    def get_unuploaded_shorts(self) -> list[Any]:
+        """Retrieve all rows that were download but not uploaded_yt_shorts"""
+        return self.__get_unuploaded("uploaded_yt_shorts")
+
+    def get_unuploaded_chats(self) -> list[Any]:
+        """Retrieve all rows that were download but not uploaded_yt_chats"""
+        return self.__get_unuploaded("uploaded_yt_chats")
+                
+    def get_unuploaded(self) -> list[Any]:
+        """Retrieve all rows that were download but not uploaded_yt"""
+        return self.__get_unuploaded("uploaded_yt")
+
+    def get_undownloaded(self) -> list[Any]:
+        """Retrieves all rows that were not downloaded"""
+        self.cursor.execute(f"SELECT {self.columns} FROM twitch_videos WHERE downloaded = 0")
+        return self.cursor.fetchall()
+
+    def insert_video_record(
+        self, id: str, title: str, created_at: str, view_count: int, duration: str, 
+        url: str, thumbnail_url: str, game_id: int, game_name: str, stream_id: str, 
+        creator_name: str, clip_is: bool
+    ):
+        try:
+            dt_obj = datetime.strptime(created_at, "%Y-%m-%dT%H:%M:%SZ")
+            clean_datetime = dt_obj.strftime("%Y-%m-%d %H:%M:%S")
+        except (ValueError, TypeError):
+            clean_datetime = created_at
+
+        # Explicitly defining columns removes the security risk and column-count bug
+        query = """
+            INSERT OR IGNORE INTO twitch_videos (
+                id, title, created_at, view_count, duration, url, thumbnail_url, 
+                game_id, game_name, stream_id, creator_name, clip_is
+            ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+        """
+
+        values = (
+            id, title, clean_datetime, view_count, duration, url, thumbnail_url, 
+            game_id, game_name, stream_id, creator_name, clip_is
+        )
+
+        try:
+            self.cursor.execute(query, values)
+            self.conn.commit()
+        except Exception as e:
+            # Prevent silent failures if the database connection drops
+            print(f"Database insertion failed: {e}")
+            self.conn.rollback()

find_youtube_tags.py

@@ -0,0 +1,147 @@
+#!/usr/bin/env python3
+import json
+from google.oauth2.credentials import Credentials
+from google.auth.transport.requests import Request
+from googleapiclient.discovery import build
+from googleapiclient.errors import HttpError
+
+def load_credentials():
+    """Load credentials from secrets.json (Reused from your previous flow)"""
+    try:
+        with open('secrets.json', 'r') as f:
+            creds_data = json.load(f)
+            
+        credentials = Credentials(
+            token=creds_data['token'],
+            refresh_token=creds_data['refresh_token'],
+            token_uri=creds_data['token_uri'],
+            client_id=creds_data['client_id'],
+            client_secret=creds_data['client_secret'],
+            scopes=creds_data['scopes']
+        )
+        
+        if credentials.expired:
+            credentials.refresh(Request())
+            
+        return credentials
+    except FileNotFoundError:
+        print("Error: secrets.json not found!")
+        return None
+    except Exception as e:
+        print(f"Error loading credentials: {str(e)}")
+        return None
+
+def get_my_uploads_playlist_id(youtube):
+    """Retrieves the system upload playlist ID for the authenticated user's channel."""
+    try:
+        # mine=True automatically references the authorized account
+        request = youtube.channels().list(part="contentDetails", mine=True)
+        response = request.execute()
+        
+        if "items" in response and len(response["items"]) > 0:
+            return response["items"][0]["contentDetails"]["relatedPlaylists"]["uploads"]
+        else:
+            print("No channel found for these credentials.")
+            return None
+    except HttpError as e:
+        print(f"API Error retrieving channel details: {str(e)}")
+        return None
+
+def scan_channel_videos_for_tag(youtube, uploads_playlist_id: str, target_tag: str):
+    """
+    Loops through all channel video uploads and filters those possessing the target tag.
+    """
+    target_tag_lower = target_tag.lower()
+    all_videos_count = 0
+    matched_videos = []
+    next_page_token = None
+
+    print("Beginning channel scan...")
+    
+    while True:
+        try:
+            # Step A: Retrieve a batch of video IDs from the uploads playlist container
+            playlist_request = youtube.playlistItems().list(
+                part="snippet",
+                playlistId=uploads_playlist_id,
+                maxResults=50,
+                pageToken=next_page_token
+            )
+            playlist_response = playlist_request.execute()
+            
+            video_ids_batch = [
+                item["snippet"]["resourceId"]["videoId"] 
+                for item in playlist_response.get("items", [])
+            ]
+            
+            if not video_ids_batch:
+                break
+                
+            all_videos_count += len(video_ids_batch)
+
+            # Step B: Pass batch to videos().list to extract metadata details (including tags)
+            video_request = youtube.videos().list(
+                part="snippet",
+                id=",".join(video_ids_batch)
+            )
+            video_response = video_request.execute()
+
+            for video in video_response.get("items", []):
+                title = video["snippet"]["title"]
+                video_id = video["id"]
+                # Tags are optional fields on YouTube; default to an empty list if absent
+                tags = video["snippet"].get("tags", [])
+                
+                # Normalize tags to lowercase for clean matching evaluation
+                tags_lower = [tag.lower() for tag in tags]
+                
+                if target_tag_lower in tags_lower:
+                    matched_videos.append({
+                        "id": video_id,
+                        "title": title,
+                        "tags": tags
+                    })
+                    print(f"🔍 Found Match: '{title}' (ID: {video_id})")
+
+            # Check if another page token exists, if not break the pagination loop
+            next_page_token = playlist_response.get("nextPageToken")
+            if not next_page_token:
+                break
+
+        except HttpError as e:
+            print(f"An error occurred while fetching video batches: {str(e)}")
+            break
+
+    # Summary reporting
+    print("\n" + "="*40)
+    print(f"Scan complete. Analyzed {all_videos_count} total videos.")
+    print(f"Found {len(matched_videos)} videos containing the '{target_tag}' tag.")
+    print("="*40)
+    
+    return matched_videos
+
+def main():
+    credentials = load_credentials()
+    if not credentials:
+        return
+        
+    youtube = build('youtube', 'v3', credentials=credentials)
+    
+    # 1. Fetch your dynamic uploads playlist pointer
+    uploads_id = get_my_uploads_playlist_id(youtube)
+    
+    if uploads_id:
+        print(f"Target Uploads Playlist ID: {uploads_id}")
+        
+        # 2. Run the iterative match parser targeting the 'clips' keyword tag
+        target_keyword = "clips"
+        results = scan_channel_videos_for_tag(youtube, uploads_id, target_keyword)
+        
+        # 3. Print out a neat clean list of matches
+        if results:
+            print(f"\n--- List of matching videos for tag '{target_keyword}': ---")
+            for index, item in enumerate(results, start=1):
+                print(f"{index}. {item['title']} -> https://youtu.be{item['id']}")
+
+if __name__ == "__main__":
+    main()

linux.py

@@ -0,0 +1,17 @@
+#!/usr/bin/env python3
+import subprocess
+
+def run_command(command: str):
+    """Executes a Linux command, waits for completion, and returns output."""
+    try:
+        # shell=True allows running full command strings with pipes/wildcards
+        # text=True returns strings instead of bytes
+        result = subprocess.run(
+            command, shell=True, check=True, capture_output=True, text=True
+        )
+
+        return {"success": True, "stdout": result.stdout, "stderr": result.stderr}
+
+    except subprocess.CalledProcessError as e:
+        # Handles errors if the Linux command returns a non-zero exit code
+        return {"success": False, "stdout": e.stdout, "stderr": e.stderr}

requirements.txt

@@ -0,0 +1,96 @@
+attrs==26.1.0
+beautifulsoup4==4.14.3
+certifi==2026.2.25
+cffi==2.0.0
+chardet==5.2.0
+charset-normalizer==3.4.7
+click==8.4.2
+colorama==0.4.6
+cryptography==49.0.0
+cuda-bindings==13.3.1
+cuda-pathfinder==1.5.6
+cuda-toolkit==13.0.3.0
+decorator==5.3.1
+defusedxml==0.7.1
+docopt==0.6.2
+filelock==3.31.0
+fsspec==2026.6.0
+google-api-core==2.31.0
+google-api-python-client==2.198.0
+google-auth==2.56.0
+google-auth-httplib2==0.4.0
+google-auth-oauthlib==1.4.0
+googleapis-common-protos==1.75.0
+h11==0.16.0
+httplib2==0.32.0
+idna==3.11
+ImageIO==2.37.3
+imageio-ffmpeg==0.6.0
+Jinja2==3.1.6
+joblib==1.5.3
+llvmlite==0.48.0
+MarkupSafe==3.0.3
+more-itertools==11.1.0
+moviepy==2.2.1
+mpmath==1.3.0
+networkx==3.6.1
+nltk==3.10.0
+numba==0.66.0
+numpy==2.4.6
+nvidia-cublas==13.1.1.3
+nvidia-cuda-cupti==13.0.85
+nvidia-cuda-nvrtc==13.0.88
+nvidia-cuda-runtime==13.0.96
+nvidia-cudnn-cu13==9.20.0.48
+nvidia-cufft==12.0.0.61
+nvidia-cufile==1.15.1.6
+nvidia-curand==10.4.0.35
+nvidia-cusolver==12.0.4.66
+nvidia-cusparse==12.6.3.3
+nvidia-cusparselt-cu13==0.8.1
+nvidia-nccl-cu13==2.29.7
+nvidia-nvjitlink==13.3.33
+nvidia-nvshmem-cu13==3.4.5
+nvidia-nvtx==13.0.85
+oauthlib==3.3.1
+openai-whisper==20250625
+outcome==1.3.0.post0
+packaging==26.2
+pillow==11.3.0
+pipreqs==0.4.13
+proglog==0.1.12
+proto-plus==1.28.1
+protobuf==7.35.1
+pyasn1==0.6.4
+pyasn1_modules==0.4.2
+pycparser==3.0
+pyparsing==3.3.2
+PySocks==1.7.1
+python-apt==3.0.0
+python-debian==1.0.1
+python-debianbts==4.1.1
+python-dotenv==1.2.2
+regex==2026.7.19
+reportbug==13.2.0
+requests==2.33.1
+requests-oauthlib==2.0.0
+selenium==4.43.0
+setuptools==83.0.0
+sniffio==1.3.1
+sortedcontainers==2.4.0
+soupsieve==2.8.3
+sympy==1.14.0
+tiktoken==0.13.0
+torch==2.13.0
+tqdm==4.67.3
+trio==0.33.0
+trio-websocket==0.12.2
+triton==3.7.1
+typing_extensions==4.15.0
+uritemplate==4.2.0
+urllib3==2.6.3
+webdriver-manager==4.0.2
+websocket-client==1.9.0
+wheel==0.46.1
+wsproto==1.3.2
+yarg==0.1.10

transcribe_video.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python3
+import os
+import subprocess
+import whisper
+import linux
+from moviepy import VideoFileClip
+from whisper.utils import get_writer
+
+model = whisper.load_model("base")
+
+def extract_audio(video_path: str, audio_temp_path: str):
+    # Create a temporary path for a sanitized copy of the video
+    sanitized_video_path = video_path.replace(".mp4", "_clean.mp4")
+    
+    print("Sanitizing video metadata for MoviePy parser...")
+    # -map_chapters -1 removes chapter layouts that break the parser.
+    # -sn strips text/subtitle streams that crash MoviePy.
+    # -c copy copies video and audio instantly without quality loss.
+    linux.run_command(f"ffmpeg -y -i {video_path} -map_chapters -1 -sn -c copy {sanitized_video_path}")
+    
+    print("Extracting uncompressed WAV audio...")
+    try:
+        # Load the sanitized file instead of the raw Twitch clip
+        with VideoFileClip(sanitized_video_path) as video:
+            video.audio.write_audiofile(
+                audio_temp_path, 
+                fps=16000,
+                codec="pcm_s16le", 
+                ffmpeg_params=["-ac", "1"]
+            )
+    finally:
+        # Always clean up the temporary sanitized video on Windows 11
+        if os.path.exists(sanitized_video_path):
+            os.remove(sanitized_video_path)
+
+
+def transcribe_to_srt(audio_path: str, output_directory: str, output_filename: str):    
+    print("Transcribing audio...")
+    result = model.transcribe(audio_path)
+    
+    print("Creating SRT file...")
+    srt_writer = get_writer("srt", output_directory)
+    srt_writer(result, output_filename, {})
+    
+    print(f"SRT subtitle file saved in: {output_directory}")
+    if os.path.exists(audio_path):
+        os.remove(audio_path)
+
+
+if __name__ == "__main__":
+    video_path = "my_video.mp4" 
+    audio_temp_path = "temp_audio.wav"  # Changed extension to .wav
+    
+    output_dir = os.getcwd()  
+    output_prefix = "my_video_subtitles"  
+    
+    extract_audio(video_path, audio_temp_path)
+    transcribe_to_srt(audio_temp_path, output_dir, output_prefix)
+    
+    if os.path.exists(audio_temp_path):
+        os.remove(audio_temp_path)

twitch_down_uploader.py

@@ -0,0 +1,327 @@
+#!/usr/bin/env python3
+import requests
+import os
+import linux
+import time
+
+from database import Database
+
+import uploader
+from uploader import CategoryId
+
+import youtube_hashtags
+import transcribe_video
+
+CHANNEL_NAME = 'teampgp' # Replace with the streamer's username
+DB = None
+
+def transcribe(id: str):
+    """Transcribes the Video File."""
+    video_file = f"save/{DB.table}/{id}/{id}.mp4"
+
+    # Check if the video file exists
+    if not os.path.exists(video_file):
+        print(f"Error: File not found: {video_file}")
+        return False
+
+    # no need to continue if srt transcribe file already exists
+    if os.path.exists(f"save/{DB.table}/{id}/transcribe_{id}.srt"):
+        print(f"video already transcribed:")
+        return True
+
+    transcribe_video.extract_audio(video_file, f"save/{DB.table}/{id}/temp_{id}_audio.wav")
+    transcribe_video.transcribe_to_srt(f"save/{DB.table}/{id}/temp_{id}_audio.wav", f"save/{DB.table}/{id}/", f"transcribe_{id}")
+
+    return True
+
+def top_hashtags(id: str):
+    """"Hashtags from transcribed SRT file."""
+    file_srt = f"save/{DB.table}/{id}/transcribe_{id}.srt"
+
+    # if srt transcribe file not exists
+    if not os.path.exists(file_srt):
+        print(f"Transcribe file not found {file_srt}")
+        return []
+
+    tags = youtube_hashtags.get_top_hashtags(file_srt)
+    return tags
+
+def download():
+    """Find all undownload videos and download them."""
+    undownloaded = DB.get_undownloaded()
+
+    print(f"Download {DB.table}...")
+
+    if DB.table == "videos":
+        for record_id, record_date, title, game_name, downloaded, uploaded_yt, chat_upload_yt in undownloaded:
+            print(f"ID: {record_id} | Date: {record_date} | Game: {game_name} | Title: {title}")
+            output = linux.run_command(f"TwitchDownloaderCLI videodownload --id {record_id} -o save/videos/{record_id}/{record_id}.mp4 --collision Overwrite")
+            output2 = linux.run_command(f"TwitchDownloaderCLI chatdownload --id {record_id} -o save/videos/{record_id}/{record_id}_chat.json -E --collision Overwrite")
+            time.sleep(1)
+            if output["success"] is True:
+                print(f"ID: {record_id} | Date: {record_date} | Game: {game_name} | Title: {title} | was successful")
+                DB.mark_as_downloaded(record_id)
+            else:
+                print(f"ID: {record_id} | Download Process failed. {output["stdout"]}. Error: {output["stderr"]}")
+
+    elif DB.table == "clips":
+        for slug, record_date, title, game_name, clip_by, views, downloaded, uploaded_yt, uploaded_shorts_yt in undownloaded:
+            print(f"Slug: {slug} | Date: {record_date} | Game: {game_name} | By: {clip_by} | Views: {views} | Title: {title}")
+            
+            # Uses standard clipdownload directive
+            output = linux.run_command(f"TwitchDownloaderCLI clipdownload --id {slug} -o save/clips/{slug}/{slug}.mp4 --collision Overwrite")
+            time.sleep(1)
+            
+            if output["success"] is True:
+                print(f"Slug: {slug} | Was successfully downloaded.")
+                DB.mark_as_downloaded(slug)
+            else:
+                print(f"Slug: {slug} | Download Process failed. {output["stdout"]}. Error: {output["stderr"]}")
+
+
+    print(f"Finished Downloading {DB.table}...")
+
+def upload():
+    """Loops over the downloaded videos entries and uploaded them to youtube."""
+    print(f"Uploading {DB.table}...")
+
+    unuploaded = DB.get_unuploaded()
+
+    twitch_datetime = " Live on Twitch Every Friday and Sunday @7:30 ET https://twitch.tv/teampgp"
+    file_path = ""
+    title = ""
+    description = ""
+    categoryId = CategoryId.GAMING
+    privatcyStatus = 'private'
+    base_tags = ['gaming', 'TeamPGP', 'twitch', 'Level1Techs']
+
+    upload_queue = []
+
+    if DB.table == "videos":
+        for record_id, record_date, title, game_name, downloaded, uploaded_yt, chats_upload_yt in unuploaded:
+            print(f"ID: {record_id} | Date: {record_date} | Game: {game_name} | Title: {title}")
+
+            file_path = f"save/videos/{record_id}/{record_id}.mp4"
+            description = f"Game: {game_name}, on {record_date}, #VODS {twitch_datetime}"
+            tags = list(base_tags)
+            tags.extend([f'{game_name}', 'twitch_vods', 'vods'])
+            tags.extend(top_hashtags(record_id))
+
+            upload_queue.append([record_id, file_path, title, categoryId, description, privatcyStatus, tags])
+
+    elif DB.table == "clips":
+        for slug, record_date, title, game_name, clip_by, views, downloaded, uploaded_yt, shorts_uploaded_yt in unuploaded:
+            print(f"Slug: {slug} | Date: {record_date} | Game: {game_name} | By: {clip_by} | Views: {views} | Title: {title}")
+
+            transcribe(slug)
+
+            file_path = f"save/clips/{slug}/{slug}.mp4"
+            description = f"Game: {game_name}, Cliped By: {clip_by}, on {record_date}, #Shorts #Clips {twitch_datetime}"
+            tags = list(base_tags)
+            tags.extend([f'{game_name}', 'twitch_clips', 'clips', f'{clip_by}', 'shorts'])
+            tags.extend(top_hashtags(slug))
+
+            upload_queue.append([slug, file_path, title, categoryId, description, privatcyStatus, tags])
+
+    for db_id, file_path, title, categoryId, description, privatcyStatus, tags in upload_queue:
+        output = uploader.upload_video(file_path, title, categoryId, description, privatcyStatus, tags)
+        if output is True:
+            print(f"Title: {title} | Was successfully uploaded.")
+            DB.mark_as_uploaded(db_id)
+        else:
+            print(f"Title: {title} | Download Process failed.")
+
+def create_chats():
+    pass
+
+def create_shorts():
+    pass
+
+def get_vod_ids_simplified(channel_name: str):
+    """Queries Twitch's public endpoint directly for trending clips."""
+    session = requests.Session()
+    url = "https://gql.twitch.tv/gql"
+    
+    # Case-preserved headers to prevent 400 Bad Request errors
+    session.headers = {
+        "Client-ID": "kimne78kx3ncx6brgo4mv6wki5h1ko",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+        "Content-Type": "text/plain"
+    }
+
+    videos_query_string = """
+    query GetChannelVideos($login: String!, $limit: Int!, $after: Cursor) {
+        user(login: $login) {
+            videos(first: $limit, types: [ARCHIVE], after: $after) {
+                pageInfo {
+                    hasNextPage
+                    endCursor
+                }
+                edges {
+                    node {
+                        id
+                        title
+                        publishedAt
+                        game {
+                            displayName
+                        }
+                    }
+                }
+            }
+        }
+    }
+    """
+
+    clips_query_string = """
+    query GetChannelClips($login: String!, $limit: Int!, $after: Cursor) {
+        user(login: $login) {
+            clips(first: $limit, criteria: { period: ALL_TIME }, after: $after) {
+                pageInfo {
+                    hasNextPage
+                    endCursor
+                }
+                edges {
+                    cursor
+                    node {
+                        slug
+                        title
+                        createdAt
+                        viewCount
+                        game {
+                            displayName
+                        }
+                        curator {
+                            login
+                        }
+                    }
+                }
+            }
+        }
+    }
+    """
+
+    video_ids = []
+    has_next_page = True
+    cursor = None
+    
+    limit = 50
+    query_string = ""
+    operation_name = ""
+    if DB.table == "videos":
+        query_string = videos_query_string
+        limit = 100
+        operation_name = "GetChannelVideos"
+    elif DB.table == "clips":
+        query_string = clips_query_string
+        limit = 40
+        operation_name = "GetChannelClips"
+
+    while has_next_page:
+        time.sleep(1)
+        # A simplified query string that hardcodes the ARCHIVE type filter into the request structure
+        payload = [{
+            "operationName": operation_name,
+            "query": query_string,
+            "variables": {
+                "login": channel_name.lower(),
+                "limit": limit,
+                "after": cursor
+            }
+        }]
+        
+        try:
+            # Prepping ensures Python does not rewrite the Client-ID header case
+            req = requests.Request('POST', url, json=payload)
+            #req = requests.Request('POST', url, data=json.dumps(payload))
+            prepped = session.prepare_request(req)
+            
+            response = session.send(prepped)
+            response.raise_for_status()
+            
+            data = response.json()
+            
+            # Pull out the target index array dictionary object
+            result = data[0] if isinstance(data, list) else data
+            
+            if "errors" in result:
+                print(f"Twitch GraphQL Error: {result['errors']}")
+                return []
+                
+            user_data = result.get('data', {}).get('user', {})
+            if not user_data:
+                print(f"Channel '{channel_name}' not found.")
+                return []
+
+            edges = user_data.get(DB.table, {}).get('edges', [])
+
+            # --- BREAK CONDITION 1: Stop if Twitch returns no more data items ---
+            if not edges or len(edges) == 0:
+                print("No more items returned by the server. Ending pagination loop.")
+                break
+
+            last_edge_cursor = None
+            print(f"--- Processing {DB.table} for {channel_name} ---")
+            for edge in edges:
+                last_edge_cursor = edge.get("cursor")
+                node = edge.get('node', {})
+                if not node:
+                    continue
+                
+                game_info = node.get('game')
+                game_name = game_info.get('displayName') if game_info else "Unknown/No Category"
+                
+                # FIXED: Switched fields to use safe .get() metrics to completely prevent KeyErrors
+                node_id = node.get('id')
+                node_title = node.get('title', 'No Title')
+                
+                if DB.table == "videos":
+                    published_at = node.get('publishedAt')
+                    print(f"ID: {node_id} | Date: {published_at} | Game: {game_name} | Title: {node_title}")
+                
+                    DB.insert_videos_record(node_id, published_at, node_title, game_name)
+                    if node_id:
+                        video_ids.append(node_id)
+                        
+                elif DB.table == "clips":
+                    slug = node.get('slug')
+                    created_at = node.get('createdAt')
+                    view_count = node.get('viewCount', 0)
+                    
+                    curator_info = node.get('curator')
+                    clip_by = curator_info.get('login') if curator_info else "Unknown Creator"
+                    
+                    print(f"Slug: {slug} | Date: {created_at} | Game: {game_name} | By: {clip_by} | Views: {view_count} | Title: {node_title}")
+                    
+                    DB.insert_clips_record(slug, created_at, node_title, game_name, clip_by, int(view_count))
+                    if slug:
+                        video_ids.append(slug)
+
+            # --- CORRECTED PAGINATION ENGINE FOR BOTH TABLES ---
+            page_info = user_data.get(DB.table, {}).get('pageInfo', {})
+            has_next_page = page_info.get("hasNextPage", False)
+            
+            next_cursor = page_info.get("endCursor") or last_edge_cursor
+            
+            if not next_cursor or next_cursor == cursor:
+                print("Cursor did not advance or is null. Safely terminating loop.")
+                break
+                
+            cursor = next_cursor
+
+        except Exception as e:
+            print(f"An unexpected error occurred: {e}")
+            if 'response' in locals():
+                print(f"Server Response Text: {response.text}")
+            return []
+            
+    return video_ids
+
+if __name__ == "__main__":
+    tables = ["clips"]
+    for table in tables:
+        DB = Database(table)
+
+        get_vod_ids_simplified(CHANNEL_NAME)
+        #download()
+        #upload()
+        #DB.close_database()

twitch_download_clips.py

@@ -1,60 +1,15 @@
 #!/usr/bin/env python3
 import requests
-import sqlite3
 import subprocess
 from datetime import datetime
 
+from database import Database
+
+import uploader
+from uploader import CategoryId
+
 CHANNEL_NAME = 'teampgp'  # Replace with the streamer's username
-
+DB = Database("clips")
-# Stores data locally
-CONN = sqlite3.connect("clips_database.db")
-CURSOR = CONN.cursor()
-
-def create_database():
-    """Creates a table structured explicitly for Twitch clip properties."""
-    CURSOR.execute(
-        """
-        CREATE TABLE IF NOT EXISTS clips (
-            slug TEXT PRIMARY KEY,
-            date TEXT NOT NULL,
-            title TEXT NOT NULL,
-            gamename TEXT NOT NULL,
-            clip_by TEXT NOT NULL,
-            view_count INTEGER NOT NULL,
-            downloaded INTEGER NOT NULL,
-            uploaded_yt INTEGER NOT NULL
-        )
-        """
-    )
-    CONN.commit()
-
-def close_database():
-    """Commits queries before ending connection context."""
-    CONN.commit()
-    CONN.close()
-
-def download_clips():
-    """Loops over undownloaded metadata entries to write files down locally."""
-    undownloaded_clips = get_undownloaded_clips()
-
-    print("Downloading Clips...")
-
-    for slug, record_date, title, game_name, clip_by, views, downloaded in undownloaded_clips:
-        print(f"Slug: {slug} | Date: {record_date} | Game: {game_name} | By: {clip_by} | Views: {views} | Title: {title}")
-        
-        # Ensures destination folder structures exist before executing CLI tool
-        run_linux_command(f"mkdir -p save/clips/{slug}")
-        
-        # Uses standard clipdownload directive
-        output = run_linux_command(f"TwitchDownloaderCLI clipdownload --id {slug} -o save/clips/{slug}/{slug}.mp4")
-        
-        if output["success"] is True:
-            print(f"Slug: {slug} | Was successfully downloaded.")
-            mark_as_downloaded(slug)
-        else:
-            print(f"Slug: {slug} | Process failed.")
-
-    print("Finished Downloading Clips...")
 
 def run_linux_command(command: str):
     """Executes a Linux command, waits for completion, and returns output."""
@@ -66,34 +21,87 @@ def run_linux_command(command: str):
     except subprocess.CalledProcessError as e:
         return {"success": False, "stdout": e.stdout, "stderr": e.stderr}
 
-def mark_as_downloaded(slug: str):
+def transcribe(slug: str):
-    """Flags a specific clip row record to downloaded (1)."""
+    """Transcribes the Video File."""
-    CURSOR.execute(
+    video_file = f"save/clips/{slug}/{slug}.mp4"
-        "UPDATE clips SET downloaded = 1 WHERE slug = ?",
-        (slug,)
-    )
-    CONN.commit()
 
-def get_undownloaded_clips():
+    # Check if the video file exists
-    """Retrieves all clip rows remaining to be captured."""
+    if not os.path.exists(video_file):
-    CURSOR.execute(
+        print(f"Error: File not found: {video_file}")
-        "SELECT slug, date, title, gamename, clip_by, view_count, downloaded FROM clips WHERE downloaded = 0"
+        return False
-    )
-    return CURSOR.fetchall()
 
-def insert_record(slug: str, record_date_str: str, title: str, gamename: str, clip_by: str, views: int):
+    # no need to continue if srt transcribe file already exists
-    """Cleans up ISO-8601 strings into unified date structures for the database."""
+    if os.path.exists(f"save/clips/{slug}/transcribe_{slug}.srt"):
-    try:
+        print(f"video already transcribed:")
-        clean_date = datetime.strptime(record_date_str, "%Y-%m-%dT%H:%M:%SZ").date()
+        return True
-    except ValueError:
-        clean_date = record_date_str
 
-    CURSOR.execute(
+    import transcribe_video
-        "INSERT OR IGNORE INTO clips (slug, date, title, gamename, clip_by, view_count, downloaded, uploaded_yt) VALUES (?, ?, ?, ?, ?, ?, ?, ?)",
+    transcribe_video.extract_audio(video_file, f"save/clips/{slug}/temp_{slug}_audio.wav")
-        (slug, str(clean_date), title, gamename, clip_by, views, False, False),
+    transcribe_video.transcribe_to_srt(f"save/clips/{slug}/temp_{slug}_audio.wav", f"save/clips/{slug}/", f"transcribe_{slug}")
-    )
-    CONN.commit()
 
+    return True
+
+def top_hashtags(slug: str):
+    file_srt = f"save/clips/{slug}/transcribe_{slug}.srt"
+
+    # if srt transcribe file not exists
+    if not os.path.exists(file_srt):
+        print(f"Transcribe file not found {file_srt}")
+        return []
+
+    import youtube_hashtags
+
+    return youtube_hashtags.get_top_hashtags(file_srt)
+
+
+def download_clips():
+    """Loops over undownloaded metadata entries to write files down locally."""
+    undownloaded_clips = DB.get_undownloaded()
+
+    print("Downloading Clips...")
+
+    for slug, record_date, title, game_name, clip_by, views, downloaded, uploaded_yt, uploaded_shorts_yt in undownloaded_clips:
+        print(f"Slug: {slug} | Date: {record_date} | Game: {game_name} | By: {clip_by} | Views: {views} | Title: {title}")
+          
+        # Uses standard clipdownload directive
+        output = run_linux_command(f"TwitchDownloaderCLI clipdownload --id {slug} -o save/clips/{slug}/{slug}.mp4")
+        
+        if output["success"] is True:
+            print(f"Slug: {slug} | Was successfully downloaded.")
+            DB.mark_as_downloaded(slug)
+        else:
+            print(f"Slug: {slug} | Download Process failed. {output["stdout"]}. Error: {output["stderr"]}")
+            
+    print("Finished Downloading Clips...")
+
+def upload_clips():
+    """Loops over the downloaded videos entries and uploaded them to youtube."""
+    print(f"Uploading Clips...")
+
+    unuploaded_clips = DB.get_unuploaded()
+
+    categoryId = CategoryId.GAMING
+
+    for slug, record_date, title, game_name, clip_by, views, downloaded, uploaded_yt in unuploaded_clips:
+        print(f"Slug: {slug} | Date: {record_date} | Game: {game_name} | By: {clip_by} | Views: {views} | Title: {title}")
+
+        file_path = f"save/clips/{slug}/{slug}.mp4"
+        title = title
+        description = f"Game: {game_name}, Cliped By: {clip_by}, on {record_date}, #Shorts #Clips #Twitch Every Friday and Sunday @7:30 EST https://twitch.tv/teampgp"
+        categoryId = CategoryId.GAMING
+        privatcyStatus = 'private'
+        tags = ['shorts', 'gaming', 'TeamPGP', f'{game_name}', f'{clip_by}', 'twitch_clips', 'clips', 'Level1Techs', 'twitch']
+
+        tags.extend(top_hashtags({slug}))
+
+        #output = uploader.upload_video(file_path, title, categoryId, description, privatcyStatus, tags)
+
+        if output is True:
+            print(f"Slug: {slug} | Was successfully uploaded.")
+            DB.mark_as_uploaded(slug)
+        else:
+            print(f"Slug: {slug} | Upload Process failed.")
+        
 def get_channel_clips(channel_name: str):
     """Queries Twitch's public endpoint directly for trending clips."""
     session = requests.Session()
@@ -174,7 +182,7 @@ def get_channel_clips(channel_name: str):
             
             print(f"Slug: {node['slug']} | Date: {node['createdAt']} | Game: {game_name} | By: {clip_by} | Views: {node['viewCount']} | Title: {node['title']}")
             
-            insert_record(node['slug'], node['createdAt'], node['title'], game_name, clip_by, int(node['viewCount']))
+            DB.insert_clips_record(node['slug'], node['createdAt'], node['title'], game_name, clip_by, int(node['viewCount']))
             slugs.append(slug_id)
             
         return slugs
@@ -184,7 +192,6 @@ def get_channel_clips(channel_name: str):
         return []
 
 if __name__ == "__main__":
-    create_database()
     get_channel_clips(CHANNEL_NAME)
     download_clips()
-    close_database()
+    upload_clips()

twitch_download_videos.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+import requests
+import os
+import time
+import csv
+
+import linux
+from database import Database
+
+CHANNEL_NAME = 'teampgp'
+DB = None
+
+def write_csv(data, file_name):
+    # Open file with newline='' to prevent extra blank rows across platforms
+    with open(file_name, "w", newline="", encoding="utf-8") as file:
+        writer = csv.writer(file)
+        
+        # Write all rows at once
+        writer.writerows(data)
+
+def download():
+    """Find all undownload videos and download them."""
+    undownloaded = DB.get_undownloaded()
+
+    print(f"Download...")
+    for id, title, created_at, view_count, duration, url, thumbnail_url, game_id, game_name, stream_id, creator_name, clip_is, downloaded, uploaded_yt, uploaded_yt_chats, uploaded_yt_shorts in undownloaded:
+        data = [[id, title, created_at, view_count, duration, url, thumbnail_url, game_id, game_name, stream_id, creator_name, clip_is, downloaded, uploaded_yt, uploaded_yt_chats, uploaded_yt_shorts]]
+        print(f"ID: {id} | Date: {created_at} | Game: {game_name} | Title: {title}")
+        if not clip_is:
+            output = linux.run_command(f"TwitchDownloaderCLI videodownload --id {id} -o download/videos/{id}/{id}.mp4 --collision Overwrite")
+            output2 = linux.run_command(f"TwitchDownloaderCLI chatdownload --id {id} -o download/videos/{id}/{id}_chat.json -E --collision Overwrite")
+            write_csv(data, f"download/videos/{id}/{id}.csv")
+        elif clip_is:
+            output = linux.run_command(f"TwitchDownloaderCLI clipdownload --id {id} -o download/clips/{id}/{id}.mp4 --collision Overwrite")
+            write_csv(data, f"download/clips/{id}/{id}.csv")
+
+        time.sleep(1)
+
+        if output["success"] is True:
+            print(f"ID: {id} | Date: {created_at} | Game: {game_name} | Title: {title} | was successful")
+            DB.mark_as_downloaded(id)
+        else:
+            print(f"ID: {id} | Download Process failed. {output["stdout"]}. Error: {output["stderr"]}")
+
+    print(f"Finished Downloading...")
+
+if __name__ == "__main__":
+    DB = Database()
+    download()

twitch_download_vod.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+import json
+import os
+import requests
+
+# The target Twitch streamer username
+TWITCH_USERNAME = "SumGuyV5" 
+
+def load_secrets(filepath="twitch_secrets.json"):
+    """Loads client credentials and potential manual token from JSON file."""
+    if not os.path.exists(filepath):
+        raise FileNotFoundError(f"Missing credential file: '{filepath}'")
+        
+    with open(filepath, "r") as file:
+        secrets = json.load(file)
+        
+    if "client_id" not in secrets or "client_secret" not in secrets:
+        raise KeyError("JSON file must contain 'client_id' and 'client_secret'.")
+        
+    return secrets["client_id"], secrets["client_secret"], secrets.get("manual_token")
+
+def get_app_access_token(client_id, client_secret):
+    """Generates an App Access Token using the correct Twitch ID server."""
+    auth_url = "https://twitch.tv"  # FIXED: Correct auth endpoint
+    payload = {
+        "client_id": client_id,
+        "client_secret": client_secret,
+        "grant_type": "client_credentials"
+    }
+    headers = {"Content-Type": "application/x-www-form-urlencoded"}
+    
+    response = requests.post(auth_url, data=payload, headers=headers)
+    response.raise_for_status() 
+    return response.json()["access_token"]
+
+def get_user_id(username, headers):
+    """Retrieves the unique numerical Twitch User ID from Helix."""
+    url = f"https://twitch.tv{username}"  # FIXED: Endpoint & parameter
+    response = requests.get(url, headers=headers)
+    response.raise_for_status()
+    data = response.json().get("data")
+    if data and len(data) > 0:
+        return data[0]["id"]  # FIXED: Helix data array returns user dictionaries
+    else:
+        raise ValueError(f"Twitch user '{username}' not found.")
+
+def get_channel_vods(user_id, headers, limit=10):
+    """Fetches past broadcasts (VODs) using valid Helix syntax."""
+    # FIXED: Restructured URL to use correct endpoint and standard query parameters
+    url = f"https://twitch.tv{user_id}&type=archive&first={limit}"
+    response = requests.get(url, headers=headers)
+    response.raise_for_status()
+    return response.json().get("data", [])
+
+def main():
+    try:
+        # 1. Load credentials from external JSON file
+        client_id, client_secret, manual_token = load_secrets("twitch_secrets.json")
+        
+        # 2. Assign or generate OAuth Access Token
+        if manual_token:
+            print("Using manual access token from JSON config file...")
+            access_token = manual_token
+        else:
+            print("No manual token found. Attempting to contact Twitch Auth Server...")
+            access_token = get_app_access_token(client_id, client_secret)
+        
+        # 3. Setup Headers required by Twitch Helix API
+        headers = {
+            "Client-ID": client_id,
+            "Authorization": f"Bearer {access_token}"
+        }
+        
+        # 4. Translate Username to User ID
+        user_id = get_user_id(TWITCH_USERNAME, headers)
+        print(f"Successfully retrieved ID for {TWITCH_USERNAME}: {user_id}\n")
+        
+        # 5. Fetch and Print VOD details
+        vods = get_channel_vods(user_id, headers, limit=5)
+        
+        if not vods:
+            print(f"No VODs found for {TWITCH_USERNAME}.")
+            return
+
+        print(f"--- Latest VODs for {TWITCH_USERNAME} ---")
+        for vod in vods:
+            print(f"Title: {vod['title']}")
+            print(f"URL: {vod['url']}")
+            print(f"Published At: {vod['published_at']}")
+            print(f"Duration: {vod['duration']}")
+            print(f"Views: {vod['view_count']}")
+            print("-" * 40)
+            
+    except (FileNotFoundError, KeyError) as config_err:
+        print(f"Configuration Error: {config_err}")
+    except requests.exceptions.HTTPError as err:
+        print(f"HTTP Error detail: {err.response.text if err.response else err}")
+    except Exception as e:
+        print(f"An error occurred: {e}")
+
+if __name__ == "__main__":
+    main()

twitch_video_info.py

@@ -0,0 +1,190 @@
+#!/usr/bin/env python3
+import asyncio
+import json
+import httpx  # Switched from requests to prevent async loop freezing
+import database
+from twitchAPI.twitch import Twitch
+from twitchAPI.helper import first
+from twitchAPI.type import VideoType
+
+SECRETS = None
+TWITCH = None
+USER = None
+GAME_CACHE = {} # Local cache dictionary to store game_id -> game_name mapping
+
+CHANNEL_NAME = "teampgp"
+
+async def get_twitch():
+    global SECRETS, TWITCH, USER
+    if SECRETS is None:
+        with open('twitch_secrets.json', 'r') as f:
+            SECRETS = json.load(f)
+    if TWITCH is None:
+        TWITCH = await Twitch(SECRETS['client_id'], SECRETS['client_secret'])
+    if USER is None:
+        USER = await first(TWITCH.get_users(logins=[CHANNEL_NAME]))
+        if not USER:
+            print("User not found.")
+
+async def get_game_name_by_id(game_id: str) -> str:
+    """Helper function to fetch game names and cache them locally."""
+    if not game_id:
+        return "Unknown / No Category"
+    if game_id in GAME_CACHE:
+        return GAME_CACHE[game_id]
+    try:
+        game_generator = TWITCH.get_games(game_ids=[game_id])
+        game = await first(game_generator)
+        if game:
+            GAME_CACHE[game_id] = game.name
+            return game.name
+    except Exception:
+        pass
+    return "Unknown Game"
+
+async def get_vod_game_name(vod_id: str):
+    """Asynchronously query Twitch GQL endpoint for VOD game metadata."""
+    game_id = "0"
+    game_name = "Unknown Game"
+    url = "https://gql.twitch.tv/gql"
+
+    headers = {
+        "Client-ID": "kimne78kx3ncx6brgo4mv6wki5h1ko",
+        "Content-Type": "application/json"
+    }
+
+    payload = [{
+        "operationName": "VideoMetadata",
+        "variables": {
+            "channelLogin": "",
+            "videoID": str(vod_id)
+        },
+        "extensions": {
+            "persistedQuery": {
+                "version": 1,
+                "sha256Hash": "45111672eea2e507f8ba44d101a61862f9c56b11dee09a15634cb75cb9b9084d"
+            }
+        }
+    }]
+
+    # Using httpx async client to prevent blocking the asyncio event loop
+    async with httpx.AsyncClient() as client:
+        try:
+            response = await client.post(url, headers=headers, json=payload)
+            if response.status_code == 200:
+                data = response.json()
+                video_info = data[0].get('data', {}).get('video')
+                if video_info and video_info.get('game'):
+                    game_id = str(video_info['game']['id'])
+                    game_name = video_info['game']['displayName']
+                    print(f"GQL Found: {game_name} (ID: {game_id})")
+                else:
+                    print(f"No game information found in GQL for VOD {vod_id}.")
+        except Exception as e:
+            print(f"Error fetching GQL metadata for VOD {vod_id}: {e}")
+
+    return game_id, game_name
+
+async def get_streamer_vods():
+    await get_twitch()
+    
+    print(f"Starting VOD extraction for {USER.display_name}...")
+    vod_generator = TWITCH.get_videos(user_id=USER.id, first=100, video_type=VideoType.ALL)
+ 
+    all_vods = []
+
+    async for v in vod_generator:
+        # Resolving game category safely without freezing the event loop
+        game_id, game_name = await get_vod_game_name(v.id)
+        
+        # Safely convert game_id to integer if possible, otherwise default to 0
+        try:
+            clean_game_id = int(game_id)
+        except ValueError:
+            clean_game_id = 0
+
+        vod_data = {
+            "id": v.id,
+            "title": v.title,
+            "created_at": str(v.published_at),
+            "view_count": int(v.view_count) if v.view_count else 0,
+            "duration": v.duration,
+            "url": v.url,
+            "thumbnail_url": v.thumbnail_url,
+            "game_id": clean_game_id,
+            "game_name": game_name,
+            "stream_id": str(v.stream_id) if v.stream_id else "0",
+            "creator_name": CHANNEL_NAME,
+            "clip_is": False,
+        }
+        all_vods.append(vod_data)
+        print(f"Collected VOD: {v.title} | Category: {game_name} ({v.duration})")
+
+    print(f"\nFinished extracting VODs. Total gathered: {len(all_vods)}")
+    return all_vods
+
+async def get_streamer_clips():
+    await get_twitch()
+
+    print(f"Starting clip extraction for {USER.display_name}...")
+    clip_generator = TWITCH.get_clips(broadcaster_id=USER.id, first=100)
+    all_clips = []
+
+    async for c in clip_generator:
+        game_name = await get_game_name_by_id(c.game_id)
+        
+        try:
+            clean_game_id = int(c.game_id)
+        except (ValueError, TypeError):
+            clean_game_id = 0
+
+        clip_data = {
+            "id": c.id,
+            "title": c.title,
+            "created_at": str(c.created_at),             
+            "view_count": int(c.view_count) if c.view_count else 0,
+            "duration": c.duration,
+            "url": c.url,
+            "thumbnail_url": c.thumbnail_url,
+            "game_id": clean_game_id,
+            "game_name": game_name,
+            "stream_id": "0",
+            "creator_name": c.creator_name,
+            "clip_is": True,
+        }
+        all_clips.append(clip_data)
+        print(f"Collected clip: {c.title} | Category: {game_name} ({c.view_count} views)")
+
+    print(f"\nFinished extracting clips. Total gathered: {len(all_clips)}")
+    return all_clips
+
+async def main():
+    print("--- Script Started ---")
+    
+    db = database.Database()
+    vods_list = await get_streamer_vods()
+    
+    for v in vods_list:
+        db.insert_video_record(
+            v['id'], v['title'], v['created_at'], v['view_count'], v['duration'], 
+            v['url'], v['thumbnail_url'], v['game_id'], v['game_name'], 
+            v['stream_id'], v['creator_name'], v['clip_is']
+        )
+
+    if vods_list:
+        print(f"Recent VOD: '{vods_list[0]['title']}'")
+
+    clips_list = await get_streamer_clips()
+        
+    for v in clips_list:
+        db.insert_video_record(
+            v['id'], v['title'], v['created_at'], v['view_count'], v['duration'], 
+            v['url'], v['thumbnail_url'], v['game_id'], v['game_name'], 
+            v['stream_id'], v['creator_name'], v['clip_is']
+        )
+    
+    if clips_list:
+        print(f"Recent VOD: '{clips_list[0]['title']}'")
+
+if __name__ == "__main__":
+    asyncio.run(main())

uploader.py

@@ -2,6 +2,8 @@
 import os
 import json
 import argparse
+from enum import Enum
+from datetime import datetime
 from google.oauth2.credentials import Credentials
 from google_auth_oauthlib.flow import InstalledAppFlow
 from google.auth.transport.requests import Request
@@ -9,6 +11,25 @@ from googleapiclient.discovery import build
 from googleapiclient.http import MediaFileUpload
 from googleapiclient.errors import HttpError
 
+class CategoryId(Enum):
+    """Official YouTube Category IDs for API Uploads."""
+
+    FILM_AND_ANIMATION = "1"
+    AUTOS_AND_VEHICLES = "2"
+    MUSIC = "10"
+    PETS_AND_ANIMALS = "15"
+    SPORTS = "17"
+    TRAVEL_AND_EVENTS = "19"
+    GAMING = "20"
+    PEOPLE_AND_BLOGS = "22"
+    COMEDY = "23"
+    ENTERTAINMENT = "24"
+    NEWS_AND_POLITICS = "25"
+    HOWTO_AND_STYLE = "26"
+    EDUCATION = "27"
+    SCIENCE_AND_TECHNOLOGY = "28"
+    NONPROFITS_AND_ACTIVISM = "29"
+
 def load_credentials():
     """Load credentials from secrets.json"""
     try:
@@ -36,14 +57,24 @@ def load_credentials():
         print(f"Error loading credentials: {str(e)}")
         return None
 
-def upload_video(file_path, description):
+def upload_video(file_path: str, title: str, category: CategoryId, description: str = "", privacyStatus: str = 'private', tags: list = None, release_time: datetime = None):
     """
     Upload a video to YouTube
     
     Args:
         file_path (str): Path to the video file
+        title (str): Title of the Video
+        categoryId (str): categoryId of the video
         description (str): Video description
+        privacyStatus (str): privacyStatus of the video
+        tags (str): tags to be use on the video
+        release_time (datetime): Optional timezone-aware UTC datetime object for timed release
+
+        schedule_date = datetime.now(timezone.utc) + timedelta(days=2)
     """
+    if tags is None:
+        tags = []
+
     try:
         # Check if file exists
         if not os.path.exists(file_path):
@@ -58,21 +89,33 @@ def upload_video(file_path, description):
         # Create YouTube API client
         youtube = build('youtube', 'v3', credentials=credentials)
 
-        # Get the filename without extension as default title
+        # Configure the status object dynamically
-        title = os.path.splitext(os.path.basename(file_path))[0]
+        status_body = {
+            'selfDeclaredMadeForKids': False
+        }
+
+        if release_time is not None:
+            if release_time.tzinfo is None:
+                release_time = release_time.replace(tzinfo=timezone.utc)
+
+            # If release_time is passed, YouTube forces privacyStatus to 'private'
+            status_body['privacyStatus'] = 'private'
+            status_body['publishAt'] = release_time.strftime('%Y-%m-%dT%H:%M:%S.000Z')
+            print(f"Configuring timed release for: {status_body['publishAt']}")
+        else:
+            # Standard immediate upload
+            status_body['privacyStatus'] = privacyStatus
+            print(f"Configuring immediate upload with status: {privacyStatus}")
 
         # Prepare the video upload request
         body = {
             'snippet': {
                 'title': title,
                 'description': description,
-                'tags': [],
+                'tags': tags,
-                'categoryId': '22'  # Default to 'People & Blogs' category
+                'categoryId': category.value
             },
-            'status': {
+            'status': status_body
-                'privacyStatus': 'private',  # Default to private
-                'selfDeclaredMadeForKids': False
-            }
         }
 
         # Create media file upload
@@ -89,7 +132,7 @@ def upload_video(file_path, description):
             media_body=media
         )
 
-        print("Starting upload...")
+        print(f"Starting upload for '{title}'...")
         response = None
         while response is None:
             status, response = insert_request.next_chunk()
@@ -100,6 +143,13 @@ def upload_video(file_path, description):
         print(f"Video ID: {response['id']}")
         print(f"Title: {response['snippet']['title']}")
         print(f"URL: https://youtu.be/{response['id']}")
+
+        # Output confirmation based on what was chosen
+        if 'publishAt' in response['status']:
+            print(f"Scheduled Release Time: {response['status']['publishAt']}")
+        else:
+            print(f"Current Privacy Status: {response['status']['privacyStatus']}")
+            
         return True
 
     except HttpError as e:
@@ -111,11 +161,41 @@ def upload_video(file_path, description):
 
 def main():
     parser = argparse.ArgumentParser(description='Upload a video to YouTube')
-    parser.add_argument('file', help='Path to the video file')
+    parser.add_argument('--file', required=True, help='Path to the video file')
-    parser.add_argument('description', help='Video description')
+    parser.add_argument('--title', required=True, help='Title of the video')
+    parser.add_argument('--category', default='PEOPLE_AND_BLOGS', choices=[c.name for c in CategoryId], help='Video category genre')
+    parser.add_argument('--description', default='', help='Video description text')
+    parser.add_argument('--privacy', default='private', choices=['public', 'private', 'unlisted'], help='Video privacy settings')
+    
+    # ADDED: Feature parsing to easily pass tags from the CLI split by commas
+    parser.add_argument('--tags', default='', help='Comma-separated tags list (e.g. "python,coding,api")')
+    
+    # ADDED: Option to provide a scheduled upload timestamp natively from CLI
+    parser.add_argument('--schedule', default=None, help='UTC Release date/time in ISO format: YYYY-MM-DDTHH:MM:SS (e.g. 2026-08-15T14:30:00)')
     
     args = parser.parse_args()
-    upload_video(args.file, args.description)
+    
+    chosen_category = CategoryId[args.category]
+    parsed_tags = [t.strip() for t in args.tags.split(',')] if args.tags else []
+    
+    # ADDED: Parse schedule string into datetime object dynamically
+    release_datetime = None
+    if args.schedule:
+        try:
+            # Assumes format matches CLI help instruction text
+            release_datetime = datetime.strptime(args.schedule, '%Y-%m-%dT%H:%M:%S').replace(tzinfo=timezone.utc)
+        except ValueError:
+            print("Error: Schedule date must format strictly as YYYY-MM-DDTHH:MM:SS")
+            return
 
+    upload_video(
+        file_path=args.file, 
+        title=args.title, 
+        category=chosen_category, 
+        description=args.description,
+        privacyStatus=args.privacy,
+        tags=parsed_tags,
+        release_time=release_datetime
+    )
 if __name__ == "__main__":
-    main()
+    main()

void_ID.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 import json
 import os
 import requests

void_id2.py

@@ -1,195 +0,0 @@
-#!/usr/bin/env python3
-import requests
-
-import sqlite3
-from datetime import date as datetime_date
-
-import subprocess
-
-CHANNEL_NAME = 'teampgp' # Replace with the streamer's username
-
-CONN = sqlite3.connect("database.db")
-CURSOR = CONN.cursor()
-
-def create_database():
-    # Creates table safely using multi-line string
-    CURSOR.execute(
-        """
-        CREATE TABLE IF NOT EXISTS vods (
-            id INTEGER PRIMARY KEY,
-            date TEXT NOT NULL,
-            title TEXT NOT NULL,
-            gamename TEXT NOT NULL,
-            downloaded INTEGER NOT NULL,
-            uploaded_yt INTEGER NOT NULL
-        )
-    """
-    )
-
-    CONN.commit()
-
-def close_database():
-    """Commit before we close."""
-    CONN.commit()
-    CONN.close()
-
-def download_vods():
-    """Find all undownload vods and download them."""
-    undownload_vods = get_undownloaded_vods()
-
-    print("Download VODs...")
-
-    for record_id, record_date, title, game_name, downloaded in undownload_vods:
-        print(f"ID: {record_id} | Date: {record_date} | Game: {game_name} | Title: {title}")
-        output = run_linux_command(f"TwitchDownloaderCLI videodownload --id {record_id} -o save/{record_id}/{record_id}.mp4")
-        output2 = run_linux_command(f"TwitchDownloaderCLI chatdownload --id {record_id} -o save/{record_id}/{record_id}_chat.json -E")
-        if output["success"] is True:
-            print(f"ID: {record_id} | Date: {record_date} | Game: {game_name} | Title: {title} | was successful")
-            mark_as_downloaded(record_id)
-        else:
-            print(f"ID: {record_id} | Date: {record_date} | Game: {game_name} | Title: {title} | was Failed")
-
-    print("Finished Downloading VODs...")
-
-def run_linux_command(command: str):
-    """Executes a Linux command, waits for completion, and returns output."""
-    try:
-        # shell=True allows running full command strings with pipes/wildcards
-        # text=True returns strings instead of bytes
-        result = subprocess.run(
-            command, shell=True, check=True, capture_output=True, text=True
-        )
-
-        return {"success": True, "stdout": result.stdout, "stderr": result.stderr}
-
-    except subprocess.CalledProcessError as e:
-        # Handles errors if the Linux command returns a non-zero exit code
-        return {"success": False, "stdout": e.stdout, "stderr": e.stderr}
-
-def mark_as_downloaded(record_id: int):
-    """Updates the downloaded status to True (1) for a specific record ID."""
-    
-    # Updates the row matching the specific ID
-    CURSOR.execute(
-        "UPDATE vods SET downloaded = 1 WHERE id = ?",
-        (record_id,)
-    )
-
-    CONN.commit()
-
-def get_undownloaded_vods():
-    """Retrieves all rows where downloaded status is False (0)."""
-    
-    # Query filters by 0 because SQLite stores booleans as integers
-    CURSOR.execute(
-        "SELECT id, date, title, gamename, downloaded FROM vods WHERE downloaded = 0"
-    )
-    records = CURSOR.fetchall()
-
-    return records
-
-def insert_record(record_id: int, record_date: datetime_date, title: str, gamename: str):
-    """Inserts a record with ID, date, gamename, and title into a SQLite database."""
-    # Connects to database file (creates it if missing)
-
-    # Inserts data using parameterized queries to prevent SQL injection
-    CURSOR.execute(
-        "INSERT OR IGNORE INTO vods (id, date, title, gamename, downloaded, uploaded_yt) VALUES (?, ?, ?, ?, ?, ?)",
-        (record_id, str(record_date), title, gamename, False, False),
-    )
-
-    # Saves changes and closes the connection
-    CONN.commit()
-
-def get_vod_ids_simplified(channel_name: str):
-    session = requests.Session()
-    url = "https://gql.twitch.tv/gql"
-    
-    # Case-preserved headers to prevent 400 Bad Request errors
-    session.headers = {
-        "Client-ID": "kimne78kx3ncx6brgo4mv6wki5h1ko",
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
-        "Content-Type": "text/plain"
-    }
-    
-    # A simplified query string that hardcodes the ARCHIVE type filter into the request structure
-    query_string = """
-    query GetChannelVideos($login: String!, $limit: Int!) {
-        user(login: $login) {
-            videos(first: $limit, types: [ARCHIVE]) {
-                edges {
-                    node {
-                        id
-                        title
-                        publishedAt
-                        game {
-                            displayName
-                        }
-                    }
-                }
-            }
-        }
-    }
-    """
-
-    payload = [{
-        "operationName": "GetChannelVideos",
-        "query": query_string,
-        "variables": {
-            "login": channel_name.lower(),
-            "limit": 50
-        }
-    }]
-    
-    try:
-        # Prepping ensures Python does not rewrite the Client-ID header case
-        req = requests.Request('POST', url, json=payload)
-        prepped = session.prepare_request(req)
-        
-        response = session.send(prepped)
-        response.raise_for_status()
-        
-        data = response.json()
-        
-        # Pull out the target index array dictionary object
-        result = data[0] if isinstance(data, list) else data
-        
-        if "errors" in result:
-            print(f"Twitch GraphQL Error: {result['errors']}")
-            return []
-            
-        user_data = result['data']['user']
-        if not user_data:
-            print(f"Channel '{channel_name}' not found.")
-            return []
-            
-        edges = user_data['videos']['edges']
-        vod_ids = []
-        
-        print(f"--- Latest VODs for {channel_name} ---")
-        for edge in edges:
-            node = edge['node']
-            
-            # Safe extraction in case a VOD has no category set (Just Chatting, Uncategorized, etc.)
-            game_info = node.get('game')
-            game_name = game_info.get('displayName') if game_info else "Unknown/No Category"
-            
-            print(f"ID: {node['id']} | Date: {node['publishedAt']} | Game: {game_name} | Title: {node['title']}")
-            
-            # Pass game_name to your database logic
-            insert_record(node['id'], node['publishedAt'], node['title'], game_name)
-            vod_ids.append(node['id'])
-            
-        return vod_ids
-
-    except Exception as e:
-        print(f"An unexpected error occurred: {e}")
-        if 'response' in locals():
-            print(f"Server Response Text: {response.text}")
-        return []
-
-if __name__ == "__main__":
-    create_database()
-    get_vod_ids_simplified(CHANNEL_NAME)
-    download_vods()
-    close_database()

youtube_hashtags.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+import re
+import string
+from collections import Counter
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+import nltk
+
+# Download necessary NLTK data
+nltk.download('punkt', quiet=True)
+nltk.download('stopwords', quiet=True)
+nltk.download('punkt_tab', quiet=True)
+
+def extract_text_from_srt(file_path: str):
+    with open(file_path, 'r', encoding='utf-8') as file:
+        content = file.read()
+    # Remove SRT timestamps and sequence numbers
+    clean_text = re.sub(r'\d+\n\d{2}:\d{2}:\d{2},\d{3} --> \d{2}:\d{2}:\d{2},\d{3}\n', '', content)
+    clean_text = re.sub(r'\d+', '', clean_text)
+    return clean_text
+
+def get_top_hashtags(srt_file_path: str, top_n: int = 10):
+    raw_text = extract_text_from_srt(srt_file_path)
+    
+    # Lowercase and remove punctuation
+    raw_text = raw_text.lower()
+    raw_text = raw_text.translate(str.maketrans('', '', string.punctuation))
+    
+    # Tokenize and remove stopwords
+    words = word_tokenize(raw_text)
+    stop_words = set(stopwords.words('english'))
+    
+    # Filter for alphabetical words longer than 3 characters that aren't stop words
+    filtered_words = [
+        word for word in words 
+        if word.isalpha() and word not in stop_words and len(word) > 3
+    ]
+    
+    # Get frequency and create hashtags
+    word_counts = Counter(filtered_words)
+    top_words = word_counts.most_common(top_n)
+    
+    hashtags = [f"{word[0]}" for word in top_words]
+    return hashtags
+
+if __name__ == "__main__":
+    # Example usage
+    # Replace 'your_video.srt' with the path to your file
+    results = get_top_hashtags('your_video.srt', top_n=10)
+    print("Trending Hashtags:", results)

youtube_short.py

@@ -0,0 +1,152 @@
+#!/usr/bin/env python3
+import argparse
+import sys
+import linux
+import tempfile
+from pathlib import Path
+from moviepy import VideoFileClip, ColorClip, CompositeVideoClip
+from moviepy.video.VideoClip import TextClip
+
+from pathlib import Path
+import numpy as np
+from PIL import Image, ImageFilter
+
+def apply_gaussian_blur(frame, radius: int = 30):
+    """
+    Transforms a single NumPy array frame using PIL's true GaussianBlur filter.
+    """
+    # Convert numpy array to PIL Image
+    image = Image.fromarray(frame)
+    # Apply high-quality true Gaussian Blur
+    blurred_image = image.filter(ImageFilter.GaussianBlur(radius=radius))
+    # Return back as a numpy array for MoviePy
+    return np.array(blurred_image)
+
+def fit_to_9_16_letterbox(input_path: str, top_text: str = "TOP TEXT", bottom_text: str = "BOTTOM TEXT", use_blur: bool = True):
+    input_file = Path(input_path)
+    output_suffix = "gaussian_9_16" if use_blur else "black_9_16"
+    output_path = input_file.parent / f"{input_file.stem}_{output_suffix}{input_file.suffix}"
+
+    print("🧼 Sanitizing video metadata streams inside an automated safe context...")
+    with tempfile.NamedTemporaryFile(suffix=input_file.suffix, delete=False) as temp_file:
+        temp_path = temp_file.name
+
+    bg_scaled = None
+    bg_cropped = None
+    background_layer = None
+
+    try:
+        linux.run_command(f"ffmpeg -y -i {input_file} -map_chapters -1 -sn -c copy {temp_path}")
+        
+        # Load video
+        clip = VideoFileClip(temp_path)
+
+        # Standard vertical 9:16 canvas sizes
+        canvas_w = 1080
+        canvas_h = 1920
+
+        # Background logic
+        if use_blur:
+            print("📐 Scaling, cropping, and blurring background layer...")
+            bg_scaled = clip.resized(height=canvas_h)
+            bg_cropped = bg_scaled.cropped(width=canvas_w, x_center=bg_scaled.w / 2)
+            background_layer = bg_cropped.transform(lambda gf, t: apply_gaussian_blur(gf(t), radius=35))
+        else:
+            print("⚫ Creating solid black background canvas...")
+            background_layer = ColorClip(size=(canvas_w, canvas_h), color=(0, 0, 0), duration=clip.duration)
+
+        print("📐 Shrinking foreground video width to fit the 1080 wide canvas...")
+        foreground_clip = clip.resized(width=canvas_w)
+
+        print("✍️ Creating multi-line top title text clip...")
+        # FIXED: Added 'method="caption"' and increased vertical size to 300
+        title_clip = TextClip(
+            text=top_text,
+            font_size=55,                  # Slightly smaller to accommodate paragraphs comfortably
+            color="white",
+            font="DejaVuSans-Bold",
+            text_align="center",
+            size=(canvas_w - 100, 300),    # Subtracted 100px for safety margins on left/right edges
+            method="caption",              # Forces text to wrap cleanly onto a new line
+            duration=clip.duration
+        )
+        # Position adjusted to center the taller 300px box in the upper section
+        positioned_top_text = title_clip.with_position(("center", 180))
+
+        print("✍️ Creating multi-line bottom text clip...")
+        # FIXED: Added 'method="caption"' and increased vertical size to 300
+        bottom_clip = TextClip(
+            text=bottom_text,
+            font_size=55,                  
+            color="white",
+            font="DejaVuSans-Bold",
+            text_align="center",
+            size=(canvas_w - 100, 300),    # Left/right margins included
+            method="caption",              # Forces text to wrap cleanly onto a new line
+            duration=clip.duration
+        )
+        # Position adjusted to center the taller 300px box in the lower section
+        positioned_bottom_text = bottom_clip.with_position(("center", 1430))
+
+        # Composite layers
+        final_clip = CompositeVideoClip(
+            [
+                background_layer, 
+                foreground_clip.with_position("center"),
+                positioned_top_text,
+                positioned_bottom_text
+            ]
+        ).with_audio(clip.audio)
+
+        print("🎬 Rendering final vertical composition...")
+        final_clip.write_videofile(
+            str(output_path),
+            codec="libx264",
+            audio_codec="aac",
+            fps=clip.fps
+        )
+
+        # Clean up file locks safely
+        clip.close()
+        if bg_scaled: bg_scaled.close()
+        if bg_cropped: bg_cropped.close()
+        background_layer.close()
+        foreground_clip.close()
+        title_clip.close()
+        bottom_clip.close()
+        final_clip.close()
+
+    finally:
+        temp_file_path = Path(temp_path)
+        if temp_file_path.exists():
+            temp_file_path.unlink()
+        
+    print(f"🎉 Text overlay video saved to: {output_path}")
+
+def main():
+    # Set up the command-line argument parser
+    parser = argparse.ArgumentParser(description="TeamPGP Clip Processing and Upload Pipeline")
+    
+    # Add optional arguments
+    parser.add_argument('--convert', type=str, metavar='CLIP_PATH', help='Path to a video file to convert to a 9:16 Short')
+    parser.add_argument('--upload', action='store_true', help='Process and upload pending Shorts in the database to YouTube')
+
+    args = parser.parse_args()
+
+    # If no flags are provided, show help text and exit
+    if not args.convert and not args.upload:
+        parser.print_help()
+        sys.exit("\n❌ Error: You must provide at least one action flag (--convert or --upload).")
+
+    # Execute conversion step if path is provided
+    if args.convert:
+        clip_by = "joelmckinney"
+        #convert_to_short(args.convert)
+        fit_to_9_16_letterbox(args.convert, "TeamPGP Live on Twitch...\n Every Friday and Sunday @7:30 ET.\n twitch.tv/teampgp", f"Clipped By: {clip_by}.", True)
+
+    # Execute database upload step if flag is provided
+    if args.upload:
+        upload_shorts()
+
+if __name__ == "__main__":
+    main()