uncomment the mark_as_downloaded

.gitignore

@@ -6,6 +6,3 @@ save
 __pycache__
 twitch_secrets.json
 .vscode/settings.json
-download
-output.log
-*.mp4

build_videos.py

@@ -1,127 +0,0 @@
-#!/usr/bin/env python3
-import database
-import youtube_short
-import transcribe_video
-import twitch_chat_vod
-
-DB = None
-
-def build_chat_video():
-    chats = DB.get_unuploaded_chats()
-    
-    for chat in chats:
-        (
-            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,
-        ) = chat
-        
-        print("====================================================")
-        print(f"🚀 Chat Video: {title}")
-        print("====================================================")
-
-        twitch_chat_vod.combine_twitch_vod_and_chat(f"download/videos/{id}/{id}.mp4", "side-by-side")
-
-    print("====================================================")
-    print(f"✅ Processing: Chat Video Done.")
-    print("====================================================")
-
-
-def build_transcribe():
-    unuploadeds = DB.get_unuploaded()
-
-    for unuploaded in unuploadeds:
-        (
-            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,
-        ) = unuploaded
-
-        if clip_is:
-            target_dir = f"download/clips"
-        else:
-            target_dir = f"download/videos"
-
-        print("====================================================")
-        print(f"🚀 Transcribe: {title}")
-        print("====================================================")
-        
-        transcribe_video.transcribe_to_srt(f"{target_dir}/{id}/{id}.mp4")
-
-    print("====================================================")
-    print(f"✅ Processing: Transcribing Done.")
-    print("====================================================")
-
-
-def build_shorts():
-    shorts = DB.get_unuploaded_shorts()
-
-    top_txt = "TeamPGP Live on Twitch...\n Every Friday and Sunday @7:30 ET.\n twitch.tv/teampgp"
-
-    for short in shorts:
-        (
-            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,
-        ) = short
-
-        target_dir = f"download/clips/{id}/{id}.mp4"
-
-        print("====================================================")
-        print(f"🚀 Processing: Clip to Youtube Short {title}")
-        print("====================================================")
-
-        youtube_short.fit_to_9_16_letterbox(target_dir, top_txt, f"Clipped By: {creator_name}.")
-
-    print("====================================================")
-    print(f"✅ Processing: Clip to Youtube Short Done.")
-    print("====================================================")
-
-def main():
-    global DB
-    DB = database.Database()
-    build_shorts()
-    build_transcribe()
-    build_chat_video()
-
-if __name__ == "__main__":
-    main()

database.py

@@ -5,18 +5,19 @@ from pathlib import Path
 from typing import Any
 
 class Database:
-    def __init__(self, db_path: str = "database.db"):
+    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"
 
-        file_exists = Path(db_path).is_file()
+        # IMPORTANT Must check if database.db exists before connecting to it.
+        file_exists = Path("database.db").is_file()
 
-        self.conn = sqlite3.connect(db_path)
+        self.conn = sqlite3.connect("database.db")
         self.cursor = self.conn.cursor()
 
         if not file_exists:
             self.create_database()
 
-    def __exit__(self):
+    def __del__(self):
         # Destructors are unpredictable in Python; explicitly close when done instead
         try:
             self.close_database()
@@ -34,7 +35,7 @@ class Database:
             duration TEXT NOT NULL,
             url TEXT NOT NULL,
             thumbnail_url TEXT NOT NULL,
-            game_id TEXT NOT NULL,
+            game_id INTEGER NOT NULL,
             game_name TEXT NOT NULL,
             stream_id TEXT NOT NULL,
             creator_name TEXT NOT NULL,
@@ -54,10 +55,10 @@ class Database:
             self.conn.commit()
             self.conn.close()
 
-    def __mark_as(self, record_id: str, set_row: str, mark: str = "1" ):
+    def __mark_as(self, record_id: str, set_sql: str):
         self.cursor.execute(
-            f"UPDATE twitch_videos SET {set_row} = ? WHERE id = ?", 
+            f"UPDATE twitch_videos SET {set_sql} = 1 WHERE id = ?", 
-            (mark, record_id))
+            (record_id,))
         self.conn.commit()
 
     def mark_as_uploaded_shorts(self, record_id: str):
@@ -76,22 +77,18 @@ class Database:
         """Flags a specific row record to downloaded (1)."""
         self.__mark_as(record_id, "downloaded")
 
-    def unmark_as_download(self, record_id: str):
+    def __get_unuploaded(self, set_sql: str) -> list[Any]:
-        """Flags a specific row record to downloaded (0)."""
-        self.__mark_as(record_id, "downloaded", "0")
-
-    def __get_unuploaded(self, set_row: str, also: 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_row} = 0 {also}")
+        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", "AND clip_is = 1")
+        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", "AND clip_is = 0")
+        return self.__get_unuploaded("uploaded_yt_chats")
                 
     def get_unuploaded(self) -> list[Any]:
         """Retrieve all rows that were download but not uploaded_yt"""
@@ -102,20 +99,6 @@ class Database:
         self.cursor.execute(f"SELECT {self.columns} FROM twitch_videos WHERE downloaded = 0")
         return self.cursor.fetchall()
 
-    def get_download(self) -> list[Any]:
-        """Retrieves all rows that were downloaded"""
-        self.cursor.execute(f"SELECT {self.columns} FROM twitch_videos WHERE downloaded = 1")
-        return self.cursor.fetchall()
-
-    def get_clips(self) -> list[Any]:
-        """Retrieves all rows that are clip_is"""
-        self.cursor.execute(f"SELECT {self.columns} FROM twitch_videos WHERE clip_is = 1")
-        return self.cursor.fetchall()
-
-    def get_vods(self) -> list[Any]:
-        self.cursor.execute(f"SELECT {self.columns} FROM twitch_videos WHERE clip_is = 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, 
@@ -129,23 +112,10 @@ class Database:
 
         # Explicitly defining columns removes the security risk and column-count bug
         query = """
-            INSERT INTO twitch_videos (
+            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 (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
-            ON CONFLICT(id) DO UPDATE SET
-                title = excluded.title,
-                created_at = excluded.created_at,
-                view_count = excluded.view_count,
-                duration = excluded.duration,
-                url = excluded.url,
-                thumbnail_url = excluded.thumbnail_url,
-                game_id = excluded.game_id,
-                game_name = excluded.game_name,
-                stream_id = excluded.stream_id,
-                creator_name = excluded.creator_name,
-                clip_is = excluded.clip_is
-            WHERE excluded.duration != twitch_videos.duration
         """
 
         values = (
@@ -158,5 +128,5 @@ class Database:
             self.conn.commit()
         except Exception as e:
             # Prevent silent failures if the database connection drops
-            print(f"❌ Database insertion failed: {e}")
+            print(f"Database insertion failed: {e}")
             self.conn.rollback()

find_youtube_tags.py

@@ -38,8 +38,8 @@ def get_my_uploads_playlist_id(youtube):
         request = youtube.channels().list(part="contentDetails", mine=True)
         response = request.execute()
         
-        if "items" in response and len(response['items']) > 0:
+        if "items" in response and len(response["items"]) > 0:
-            return response['items'][0]['contentDetails']['relatedPlaylists']['uploads']
+            return response["items"][0]["contentDetails"]["relatedPlaylists"]["uploads"]
         else:
             print("No channel found for these credentials.")
             return None
@@ -70,7 +70,7 @@ def scan_channel_videos_for_tag(youtube, uploads_playlist_id: str, target_tag: s
             playlist_response = playlist_request.execute()
             
             video_ids_batch = [
-                item['snippet']['resourceId']['videoId'] 
+                item["snippet"]["resourceId"]["videoId"] 
                 for item in playlist_response.get("items", [])
             ]
             
@@ -87,10 +87,10 @@ def scan_channel_videos_for_tag(youtube, uploads_playlist_id: str, target_tag: s
             video_response = video_request.execute()
 
             for video in video_response.get("items", []):
-                title = video['snippet']['title']
+                title = video["snippet"]["title"]
-                video_id = video['id']
+                video_id = video["id"]
                 # Tags are optional fields on YouTube; default to an empty list if absent
-                tags = video['snippet'].get("tags", [])
+                tags = video["snippet"].get("tags", [])
                 
                 # Normalize tags to lowercase for clean matching evaluation
                 tags_lower = [tag.lower() for tag in tags]

linux.py

@@ -1,56 +1,17 @@
 #!/usr/bin/env python3
-import sys
-import shlex
 import subprocess
 
-def run_command(cmd_str: str, progress_prefix: str = "Progress", look_for: list = ["frame=", "time=", "fps=", "Rendering frame"]) -> bool:
+def run_command(command: str):
-   """Runs a system command, streams its output live, and reports errors on failure."""
+    """Executes a Linux command, waits for completion, and returns output."""
-   args = shlex.split(cmd_str)
+    try:
-
+        # shell=True allows running full command strings with pipes/wildcards
-   # Redirect stderr to stdout to catch all logging/progress in one stream
+        # text=True returns strings instead of bytes
-   process = subprocess.Popen(
+        result = subprocess.run(
-        args,
+            command, shell=True, check=True, capture_output=True, text=True
-        stdout=subprocess.PIPE,
-        stderr=subprocess.STDOUT,
-        text=True,
-        bufsize=1
         )
-   print(f"Executing: {cmd_str[:90]}...")
 
-   # Maintain a small buffer history to display context if a crash occurs
+        return {"success": True, "stdout": result.stdout, "stderr": result.stderr}
-   output_history = []
 
-   # Stream the output live to the terminal
+    except subprocess.CalledProcessError as e:
-   while True:
+        # Handles errors if the Linux command returns a non-zero exit code
-        line = process.stdout.readline()
+        return {"success": False, "stdout": e.stdout, "stderr": e.stderr}
-        if not line and process.poll() is not None:
-            break
-        if line:
-            clean_line = line.strip()
-            output_history.append(clean_line) # Keep history for error reporting
-            
-            # Keep history slim by only keeping the last 20 lines
-            if len(output_history) > 20:
-                output_history.pop(0)
-
-            # Only print updates that show progress metrics to keep terminal clean
-            if any(metric in clean_line for metric in look_for):
-                sys.stdout.write(f"\r[{progress_prefix}] {clean_line}")
-                sys.stdout.flush()
-            elif "Error" in clean_line or "failed" in clean_line:
-                print(f"\n[Alert] {clean_line}")
-            
-   print("\n") # New line after process finishes
-   
-   # Evaluate success status
-   success = (process.returncode == 0)
-   
-   if not success:
-       print(f"❌ Command failed with exit code: {process.returncode}")
-       print("--- Technical Error Details (Last 5 lines of output) ---")
-       # Print the last 5 captured lines to show the exact point of failure
-       for error_line in output_history[-5:]:
-           print(f"  > {error_line}")
-       print("---------------------------------------------------------")
-
-   return success

main.py

@@ -1,20 +0,0 @@
-#!/usr/bin/env python3
-import asyncio
-
-import twitch_video_info
-import twitch_download_videos
-import twitch_download_thumbnails
-
-import build_videos
-
-if __name__ == "__main__":
-    # Get Twitch Video Info
-    asyncio.run(twitch_video_info.main())
-
-    # Download Twitch Videos
-    twitch_download_videos.main()
-
-    twitch_download_thumbnails.main()
-
-    #Build
-    build_videos.main()

migrate_sql1.py

@@ -1,67 +0,0 @@
-#!/usr/bin/env python3
-import sqlite3
-
-# Connect to your database file
-db_name = "database.db"  # Change to your actual file name
-conn = sqlite3.connect(db_name)
-cursor = conn.cursor()
-
-try:
-  # 1. Create a temporary table with the new text-based game_id
-  cursor.execute(
-      """
-        CREATE TABLE IF NOT EXISTS twitch_videos_temp (
-            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 TEXT 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
-        )
-    """
-  )
-
-  # 2. Copy and convert data to the temporary table
-  cursor.execute(
-      """
-        INSERT INTO twitch_videos_temp (
-            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
-        )
-        SELECT 
-            id, title, created_at, view_count, duration, url, thumbnail_url, 
-            CAST(game_id AS TEXT), game_name, stream_id, creator_name, clip_is, downloaded, 
-            uploaded_yt, uploaded_yt_chats, uploaded_yt_shorts
-        FROM twitch_videos
-    """
-  )
-
-  # 3. Drop the old table configuration
-  cursor.execute("DROP TABLE twitch_videos")
-
-  # 4. Rename the temporary table to your exact original table name
-  cursor.execute("ALTER TABLE twitch_videos_temp RENAME TO twitch_videos")
-
-  # Commit changes if everything succeeded
-  conn.commit()
-  print("Migration successful! 'twitch_videos' table updated.")
-
-except sqlite3.Error as e:
-  # Roll back changes if an error occurs
-  conn.rollback()
-  print(f"An error occurred: {e}")
-
-finally:
-  # Close database connection
-  conn.close()

redownload_clips.py

@@ -1,35 +0,0 @@
-#!/usr/bin/env python3
-import database
-
-DB = None
-
-def redownload_clips():
-    clips = DB.get_clips()
-
-    for clip in clips:
-        # Unpack variables clearly
-        (
-            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,
-        ) = clip
-
-        DB.unmark_as_download(id)
-    
-
-if __name__ == "__main__":
-    DB = database.Database()
-    redownload_clips()

remove_uneed_files.py

@@ -1,72 +0,0 @@
-import os
-
-import database
-
-DB = None
-
-def remove_files():
-    datas = DB.get_download()
-
-    top_txt = "TeamPGP Live on Twitch...\n Every Friday and Sunday @7:30 ET.\n twitch.tv/teampgp"
-
-    for data in datas:
-        (
-            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,
-        ) = data
-
-        if clip_is == 0:
-            video_path = f"download/videos/{id}/{id}.mp4"
-        else:
-            video_path = f"download/clips/{id}/{id}.mp4"
-        
-        temp_chat = video_path.replace(".mp4", "_temp_chat.mp4")
-        temp_with_chat = video_path.replace(".mp4", "_temp_with_chat.mp4")
-        video_chat = video_path.replace(".mp4", "_with_chat.mp4")
-        video_chatSS = video_path.replace(".mp4", "_SS_with_chat.mp4")
-        video_chat_over = video_path.replace(".mp4", "_over_with_chat.mp4")
-        mask_path = video_path.replace(".mp4", "_temp_chat_mask.mp4")
-
-        shorts_gaussian_9_16 = ""#video_path.replace(".mp4", "_gaussian_9_16.mp4")
-        shorts_9_16 = ""#video_path.replace(".mp4", "_9_16.mp4")
-
-        srt_file = ""#video_path.replace(".mp4", ".srt")
-        
-
-        files = [temp_chat, temp_with_chat, video_chatSS, video_chat_over, mask_path, shorts_gaussian_9_16, shorts_9_16, srt_file, video_chat]
-
-        for file in files:
-            if os.path.exists(file):
-                if file == video_path:
-                    print("❌ Error: trying to delete import file.")
-                    return
-                else:
-                    os.remove(file)
-
-def redownload():
-    DB.unmark_as_download("2840110867")
-
-
-def main():
-    global DB
-    DB = database.Database()
-
-    remove_files()
-    redownload()
-
-if __name__ == "__main__":
-    main()

requirements.txt

@@ -1,51 +1,38 @@
-aiohappyeyeballs==2.7.1
-aiohttp==3.14.2
-aiosignal==1.4.0
-anyio==4.14.2
 attrs==26.1.0
-beautifulsoup4==4.15.0
+beautifulsoup4==4.14.3
-certifi==2026.7.22
+certifi==2026.2.25
-cffi==2.1.0
+cffi==2.0.0
-charset-normalizer==3.4.9
+chardet==5.2.0
-chat-downloader==0.2.8
+charset-normalizer==3.4.7
 click==8.4.2
-colorlog==6.12.0
+colorama==0.4.6
 cryptography==49.0.0
 cuda-bindings==13.3.1
-cuda-pathfinder==1.6.0
+cuda-pathfinder==1.5.6
 cuda-toolkit==13.0.3.0
 decorator==5.3.1
 defusedxml==0.7.1
-docstring_parser==0.18.0
+docopt==0.6.2
-enum-tools==0.13.0
+filelock==3.31.0
-filelock==3.32.0
-frozenlist==1.8.0
 fsspec==2026.6.0
-git-filter-repo==2.47.0
+google-api-core==2.31.0
-google==3.0.0
-google-api-core==2.32.0
 google-api-python-client==2.198.0
-google-auth==2.56.2
+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
-httpcore==1.0.9
 httplib2==0.32.0
-httpx==0.28.1
+idna==3.11
-idna==3.18
+ImageIO==2.37.3
-ImageIO==2.37.4
 imageio-ffmpeg==0.6.0
-isodate==0.7.2
 Jinja2==3.1.6
 joblib==1.5.3
 llvmlite==0.48.0
-lxml==6.1.1
 MarkupSafe==3.0.3
 more-itertools==11.1.0
 moviepy==2.2.1
 mpmath==1.3.0
-multidict==6.7.1
 networkx==3.6.1
 nltk==3.10.0
 numba==0.66.0
@@ -68,42 +55,42 @@ nvidia-nvtx==13.0.85
 oauthlib==3.3.1
 openai-whisper==20250625
 outcome==1.3.0.post0
+packaging==26.2
 pillow==11.3.0
-pip_system_certs==5.3
+pipreqs==0.4.13
 proglog==0.1.12
-propcache==0.5.2
 proto-plus==1.28.1
 protobuf==7.35.1
 pyasn1==0.6.4
 pyasn1_modules==0.4.2
-pycountry==26.2.16
 pycparser==3.0
-pycryptodome==3.23.0
-Pygments==2.20.0
 pyparsing==3.3.2
 PySocks==1.7.1
-python-dateutil==2.9.0.post0
+python-apt==3.0.0
+python-debian==1.0.1
+python-debianbts==4.1.1
 python-dotenv==1.2.2
 regex==2026.7.19
-requests==2.34.2
+reportbug==13.2.0
+requests==2.33.1
 requests-oauthlib==2.0.0
+selenium==4.43.0
 setuptools==83.0.0
-six==1.17.0
 sniffio==1.3.1
 sortedcontainers==2.4.0
-soupsieve==2.9.1
+soupsieve==2.8.3
-streamlink==8.4.0
 sympy==1.14.0
 tiktoken==0.13.0
 torch==2.13.0
-tqdm==4.69.0
+tqdm==4.67.3
 trio==0.33.0
 trio-websocket==0.12.2
 triton==3.7.1
-twitchAPI==4.5.0
+typing_extensions==4.15.0
-typing_extensions==4.16.0
 uritemplate==4.2.0
-urllib3==2.7.0
+urllib3==2.6.3
+webdriver-manager==4.0.2
 websocket-client==1.9.0
+wheel==0.46.1
 wsproto==1.3.2
-yarl==1.24.5
+yarg==0.1.10

transcribe_video.py

@@ -1,119 +1,61 @@
 #!/usr/bin/env python3
 import os
-import sys
-import shutil
 import subprocess
-from pathlib import Path
+import whisper
-from faster_whisper import WhisperModel
+import linux
-from faster_whisper.utils import format_timestamp
+from moviepy import VideoFileClip
+from whisper.utils import get_writer
 
-# Prevent OpenMP thread conflicts from crashing the script
+model = whisper.load_model("base")
-os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
 
-# 5 minutes per chunk (300 seconds) keeps RAM usage low and stable
+def extract_audio(video_path: str, audio_temp_path: str):
-CHUNK_DURATION_SEC = 300 
+    # Create a temporary path for a sanitized copy of the video
+    sanitized_video_path = video_path.replace(".mp4", "_clean.mp4")
     
-print("🔧 Initializing C++ Engine...")
+    print("Sanitizing video metadata for MoviePy parser...")
-model = WhisperModel(
+    # -map_chapters -1 removes chapter layouts that break the parser.
-    "base", 
+    # -sn strips text/subtitle streams that crash MoviePy.
-    device="cpu", 
+    # -c copy copies video and audio instantly without quality loss.
-    compute_type="int8", 
+    linux.run_command(f"ffmpeg -y -i {video_path} -map_chapters -1 -sn -c copy {sanitized_video_path}")
-    cpu_threads=0, # Let CTranslate2 auto-detect safe core counts
-    num_workers=1         
-)
-print("✅ C++ Model loaded successfully.")
-
-
-def extract_audio_and_chunk(video_path: str, output_dir: Path) -> list:
-    """Extracts and splits audio into 5-minute chunks using a single FFmpeg pass."""
-    print("🚀 Extracting and chunking audio with FFmpeg...")
-    output_dir.mkdir(parents=True, exist_ok=True)
-    
-    # Segment format output: chunk_000.wav, chunk_001.wav, etc.
-    chunk_pattern = str(output_dir / "chunk_%03d.wav")
-    
-    command = [
-        "ffmpeg", "-y", "-i", video_path,
-        "-vn", "-ac", "1", "-ar", "16000",
-        "-acodec", "pcm_s16le", "-sn", "-map_chapters", "-1",
-        "-f", "segment", "-segment_time", str(CHUNK_DURATION_SEC),
-        chunk_pattern
-    ]
-    
-    result = subprocess.run(command, stdout=subprocess.DEVNULL, stderr=subprocess.PIPE, text=True)
-    if result.returncode != 0:
-        print(f"❌ FFmpeg Error Output:\n{result.stderr}")
-        raise RuntimeError("FFmpeg extraction and chunking failed.")
-        
-    # Return sorted list of generated chunk files
-    return sorted(list(output_dir.glob("chunk_*.wav")))
-
-
-def transcribe_to_srt(video_path: str, force: bool = False):
-    video_path_obj = Path(video_path)
-    srt_path = video_path_obj.with_suffix(".srt")
-    temp_dir = video_path_obj.parent / f"temp_chunks_{video_path_obj.stem}"
-
-    if srt_path.exists():
-        if not force:
-            print(f"❌ Error: Transcription file already exists: {srt_path}")
-            return
-        else:
-            srt_path.unlink()
     
+    print("Extracting uncompressed WAV audio...")
     try:
-        # Step 1: Split audio into bite-sized pieces
+        # Load the sanitized file instead of the raw Twitch clip
-        audio_chunks = extract_audio_and_chunk(str(video_path_obj), temp_dir)
+        with VideoFileClip(sanitized_video_path) as video:
-        if not audio_chunks:
+            video.audio.write_audiofile(
-            print("❌ Error: No audio chunks were generated.")
+                audio_temp_path, 
-            return
+                fps=16000,
-
+                codec="pcm_s16le", 
-        print(f"📦 Successfully split audio into {len(audio_chunks)} chunks.")
+                ffmpeg_params=["-ac", "1"]
-        print("🎙️ Starting safe chunk-by-chunk transcription...")
-
-        global_segment_index = 1
-        
-        with open(srt_path, "w", encoding="utf-8") as srt_file:
-            for chunk_idx, chunk_path in enumerate(audio_chunks):
-                # Calculate the time offset for the current chunk
-                time_offset = chunk_idx * CHUNK_DURATION_SEC
-                print(f"\n⏳ Processing chunk {chunk_idx + 1}/{len(audio_chunks)} ({chunk_path.name})...")
-                
-                segments_generator, info = model.transcribe(
-                    str(chunk_path), 
-                    beam_size=1,
-                    vad_filter=True,
-                    temperature=0.0
             )
-                
-                # Consume chunk generator and shift timestamps instantly
-                for segment in segments_generator:
-                    # Shift timestamps relative to the original video timeline
-                    actual_start = segment.start + time_offset
-                    actual_end = segment.end + time_offset
-                    
-                    start_str = format_timestamp(actual_start, always_include_hours=True)
-                    end_str = format_timestamp(actual_end, always_include_hours=True)
-                    
-                    srt_file.write(f"{global_segment_index}\n{start_str} --> {end_str}\n{segment.text.strip()}\n\n")
-                    global_segment_index += 1
-                    
-                # Free up space as we go by deleting the processed chunk
-                chunk_path.unlink()
-
-        print(f"\n✅ All chunks combined! SRT subtitle file saved in: {srt_path}")
-
-    except Exception as e:
-        print(f"\n❌ Execution Error: {e}")
     finally:
-        # Clean up the temporary folder entirely
+        # Always clean up the temporary sanitized video on Windows 11
-        if temp_dir.exists():
+        if os.path.exists(sanitized_video_path):
-            shutil.rmtree(temp_dir)
+            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__":
-    target_video = "download/videos/2813112936/2813112936.mp4"
+    video_path = "my_video.mp4" 
-    if not os.path.exists(target_video):
+    audio_temp_path = "temp_audio.wav"  # Changed extension to .wav
-        print(f"❌ System Error: Target video file does not exist at path: {target_video}")
+    
-    else:
+    output_dir = os.getcwd()  
-        transcribe_to_srt(target_video, force=True)
+    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_chat_vod.py

@@ -1,150 +0,0 @@
-#!/usr/bin/env python3
-import  os
-import cv2
-import linux
-
-def get_video_height(video_path: str) -> int:
-    # Open the video file
-    video = cv2.VideoCapture(video_path)
-    
-    # Get the height property
-    height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
-    
-    # Always release the video object
-    video.release()
-    
-    return height
-
-def combine_twitch_vod_and_chat(vod_path: str, layout: str = "side-by-side", force: bool = False) -> bool:
-    """
-    Renders Twitch chat JSON to video and combines it with the source VOD.
-    Provides real-time terminal feedback for all processing steps.
-    """
-    threads = 8
-
-    video_height = 1080
-
-    video_path = vod_path
-    video_chat = ""
-    chat_path = video_path.replace(".mp4", "_chat.json")
-    temp_with_chat = video_path.replace(".mp4", "_temp_with_chat.mp4")
-    temp_chat = video_path.replace(".mp4", "_temp_chat.mp4")
-    video_chat_SS = video_path.replace(".mp4", "_SS_with_chat.mp4")
-    video_chat_over = video_path.replace(".mp4", "_over_with_chat.mp4")
-    mask_path = video_path.replace(".mp4", "_temp_chat_mask.mp4")
-
-    # Step 1: Pre-flight checks
-    if not os.path.exists(video_path):
-        print(f"❌ Error: Source video not found: {video_path}")
-        return False
-    
-    if not os.path.exists(chat_path):
-        print(f"❌ Error: Chat file not found: {chat_path}")
-        return False
-
-    if os.path.exists(temp_with_chat):
-        os.remove(temp_with_chat)
-
-    if layout == "side-by-side":
-        video_chat = video_chat_SS
-    elif layout == "overlay":
-        video_chat = video_chat_over
-    else:
-        return False
-
-    if os.path.exists(video_chat):
-        if not force:
-            print(f"❌ Error: Chat video already exists: {video_chat}")
-            return False
-        else:
-            os.remove(video_chat)
-
-    if os.path.exists(temp_chat):
-        os.remove(temp_chat)
-    if os.path.exists(mask_path):
-        os.remove(mask_path)
-    
-    # Step 2: Render Chat to Video
-    print("====================================================")
-    print("🚀 STEP 1: Rendering Chat JSON to Video Layer")
-    print("====================================================")
-
-    video_height = get_video_height(vod_path)
-    
-    chat_cmd = (
-        f"TwitchDownloaderCLI chatrender "
-        f"-i {chat_path} "
-        f"-w 400 -h {video_height} "
-        f"--collision Overwrite "
-        f"--temp-path download/temp "
-        f"--font-size 20 "           
-        f"--background-color #00000000 "
-        f"-o {temp_chat}"
-    )
-
-    if layout == "overlay":
-        chat_cmd = (f"{chat_cmd} --generate-mask ")
-
-    if not os.path.exists(temp_chat):
-        chat_success = linux.run_command(chat_cmd, look_for=["[STATUS]"])
-        if chat_success:
-            print("✅ Success: TwitchDownloaderCLI render chat video.")
-        else:
-            print("❌ Error: TwitchDownloaderCLI failed to render chat video.")
-            os.remove(temp_chat)
-            os.remove(mask_path)
-            return False
-
-    # Step 3: Combine Video and Chat using FFmpeg
-    print("====================================================")
-    print(f"🚀 STEP 2: Merging VOD and Chat Layout ({layout})")
-    print("====================================================")
-    
-    # -preset superfast speeds up the 3+ hour encoding process significantly
-    # -map 0:a? safely includes audio if it exists, without breaking on silent VODs
-    if layout == "side-by-side":
-        ffmpeg_cmd = (
-            f"ffmpeg -y -i {video_path} -i {temp_chat} "
-            f"-filter_complex '[1:v]scale=-1:ih[scaled_chat];[0:v][scaled_chat]hstack=inputs=2[v]' "
-            f"-map '[v]' -map 0:a? -c:v libx264 -crf 18 -preset slow -c:a copy "
-            f"-threads {threads} {temp_with_chat}"
-        )
-    elif layout == "overlay":
-        ffmpeg_cmd = (
-            f"ffmpeg -y -i {video_path} -i {temp_chat} -i {mask_path} "
-            f"-filter_complex '[1:v][2:v]alphamerge[masked_chat];[0:v][masked_chat]overlay=x=0:y=10[v]' "
-            f"-map '[v]' -map 0:a? -c:v libx264 -crf 18 -preset slow -c:a copy "
-            f"-threads {threads} {temp_with_chat}"
-        )
-    else:
-        raise ValueError("Invalid layout choice. Choose 'side-by-side' or 'overlay'.")
-
-    ffmpeg_success = linux.run_command(ffmpeg_cmd, progress_prefix="FFmpeg Merge")
-
-    # Step 4: Final verification and cleanup
-    if ffmpeg_success and os.path.exists(temp_with_chat):
-        os.rename(temp_with_chat, video_chat)
-        print("====================================================")
-        print(f"🎉 SUCCESS: Video processing complete!")
-        print(f"📁 Output Saved: {video_chat}")
-        print("====================================================")
-        
-        # Clean up the massive temporary chat video to save storage space
-        if os.path.exists(temp_chat):
-            print("🧹 Cleaning up temporary chat render video...")
-            os.remove(temp_chat)
-        if os.path.exists(mask_path):
-            os.remove(mask_path)
-        if os.path.exists(temp_with_chat):
-            os.remove(temp_with_chat)
-        return True
-    else:
-        print("❌ Error: FFmpeg failed to merge the video streams.")
-        if os.path.exists(video_chat):
-            os.remove(video_chat)
-        if os.path.exists(temp_with_chat):
-            os.remove(temp_with_chat)
-        return False
-
-if __name__ == "__main__":
-    combine_twitch_vod_and_chat("download/videos/2813112936/2813112936.mp4", "overlay", True)

twitch_down_uploader.py

@@ -58,11 +58,11 @@ def download():
             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:
+            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']}")
+                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:
@@ -72,11 +72,11 @@ def download():
             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:
+            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"Slug: {slug} | Download Process failed. {output["stdout"]}. Error: {output["stderr"]}")
 
 
     print(f"Finished Downloading {DB.table}...")

twitch_download_clips.py

@@ -66,11 +66,11 @@ def download_clips():
         # Uses standard clipdownload directive
         output = run_linux_command(f"TwitchDownloaderCLI clipdownload --id {slug} -o save/clips/{slug}/{slug}.mp4")
         
-        if output['success'] is True:
+        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"Slug: {slug} | Download Process failed. {output["stdout"]}. Error: {output["stderr"]}")
             
     print("Finished Downloading Clips...")
 
@@ -94,7 +94,7 @@ def upload_clips():
 
         tags.extend(top_hashtags({slug}))
 
-        output = uploader.upload_video(file_path, title, categoryId, description, privatcyStatus, tags)
+        #output = uploader.upload_video(file_path, title, categoryId, description, privatcyStatus, tags)
 
         if output is True:
             print(f"Slug: {slug} | Was successfully uploaded.")

twitch_download_thumbnails.py

@@ -1,162 +0,0 @@
-import os
-import json
-import asyncio
-import requests
-from twitchAPI.twitch import Twitch
-from twitchAPI.helper import first
-
-import database
-
-# 1. Fill in your credentials from the Twitch Developer Console
-SECRETS = None
-TWITCH = None
-USER = None
-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 download_live_thumbnail(twitch_client, streamer_username: str, w: int = 1920, h: int = 1080):
-    """Fetches and saves the live stream thumbnail for an active broadcast."""
-    print(f"🔎 Checking live status for: {streamer_username}...")
-    
-    # Query the live streams endpoint
-    stream_generator = twitch_client.get_streams(user_logins=[streamer_username])
-    stream_data = await first(stream_generator)
-    
-    if not stream_data:
-        print(f"❌ User '{streamer_username}' is offline. Live thumbnails require an active stream.")
-        return
-
-    # Twitch API live streams use the {width} and {height} format
-    raw_url = stream_data.thumbnail_url
-    clean_url = raw_url.replace('{width}', str(w)).replace('{height}', str(h))
-    
-    filename = f"live_{streamer_username}_{w}x{h}.jpg"
-    save_image(clean_url, filename)
-
-async def download_vod_thumbnail(twitch_client, vod_id: str, w: int = 1920, h: int = 1080):
-    """Fetches and saves a thumbnail from a past broadcast VOD ID."""
-    print(f"🔎 Searching for VOD ID: {vod_id}...")
-    
-    # Query the videos endpoint
-    video_generator = twitch_client.get_videos(vod_id)
-    video_data = await first(video_generator)
-
-    filename = f"download/videos/{vod_id}/{vod_id}_{w}x{h}.jpg"
-    if os.path.exists(filename):
-        return
-    
-    if not video_data:
-        print(f"❌ VOD ID {vod_id} could not be found.")
-        return
-
-    # Twitch VOD endpoints typically format string tokens as %{width} and %{height}
-    raw_url = video_data.thumbnail_url
-    if not raw_url:
-        print("❌ This VOD does not have an available thumbnail.")
-        return
-        
-    clean_url = raw_url.replace('%{width}', str(w)).replace('%{height}', str(h))
-    
-    #filename = f"vod_{vod_id}_{w}x{h}.jpg"
-    save_image(clean_url, filename)
-
-async def download_clip_thumbnail(clip_id: str, url: str):
-    print(f"🔎 Searching for Clip ID: {clip_id}...")
-           
-    filename = f"download/clips/{clip_id}/{clip_id}.jpg"
-    if os.path.exists(filename):
-        return
-           
-    save_image(url, filename, False)
-
-def save_image(url: str, filename: str, stream: bool = True):
-    """Helper function to stream image bytes directly to a file."""
-    try:
-        response = requests.get(url, stream)
-        if response.status_code == 200:
-            with open(filename, 'wb') as file:
-                if stream is True:
-                    for chunk in response.iter_content(1024):
-                        file.write(chunk)
-                else:
-                    file.write(response.content)
-            print(f"✅ Success! Saved as: {filename}")
-        else:
-            print(f"❌ Download failed. HTTP Status: {response.status_code}")
-    except Exception as e:
-        print(f"❌ An error occurred during file writing: {e}")
-
-async def main():
-    # Initialize connection & automatically authorize the App token
-    await get_twitch()
-    twitch = TWITCH # Twitch(APP_ID, APP_SECRET)
-    
-    # --- OPTION A: Download Live Thumbnail ---
-    # Target user must be streaming live right now
-    target_streamer = CHANNEL_NAME
-    #await download_live_thumbnail(twitch, target_streamer, 1920, 1080)
-    
-    # --- OPTION B: Download Past Broadcast VOD Thumbnail ---
-    # Extract the ID sequence from your target video link
-    # target_vod = "2145678901"
-    db = database.Database()
-    vods = db.get_vods()
-    for vod in vods:
-        (
-            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,
-        ) = vod
-
-        await download_vod_thumbnail(twitch, id, 1920, 1080)
-
-    clips = db.get_clips()
-    for clip in clips:
-        (
-            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,
-        ) = clip
-    
-        await download_clip_thumbnail(id, thumbnail_url)
-
-if __name__ == '__main__':
-    asyncio.run(main())

twitch_download_videos.py

@@ -1,7 +1,8 @@
 #!/usr/bin/env python3
+import requests
+import os
+import time
 import csv
-import subprocess
-from datetime import datetime, timedelta, timezone
 
 import linux
 from database import Database
@@ -18,91 +19,31 @@ def write_csv(data, file_name):
         writer.writerows(data)
 
 def download():
-    """Find all undownloaded videos and clips, and download them safely."""
+    """Find all undownload videos and download them."""
     undownloaded = DB.get_undownloaded()
 
-    print("Starting downloads...")
+    print(f"Download...")
-    for row in undownloaded:
+    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:
-        # Unpack variables clearly
+        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}")
-            id,
+        if not clip_is:
-            title,
+            output = linux.run_command(f"TwitchDownloaderCLI videodownload --id {id} -o download/videos/{id}/{id}.mp4 --collision Overwrite")
-            created_at,
+            output2 = linux.run_command(f"TwitchDownloaderCLI chatdownload --id {id} -o download/videos/{id}/{id}_chat.json -E --collision Overwrite")
-            view_count,
+            write_csv(data, f"download/videos/{id}/{id}.csv")
-            duration,
+        elif clip_is:
-            url,
+            output = linux.run_command(f"TwitchDownloaderCLI clipdownload --id {id} -o download/clips/{id}/{id}.mp4 --collision Overwrite")
-            thumbnail_url,
+            write_csv(data, f"download/clips/{id}/{id}.csv")
-            game_id,
-            game_name,
-            stream_id,
-            creator_name,
-            clip_is,
-            downloaded,
-            uploaded_yt,
-            uploaded_yt_chats,
-            uploaded_yt_shorts,
-        ) = row
 
-        # 1. Define your data's timestamp (Example: April 10, 2026, at 10:00 AM)
+        time.sleep(1)
-        #datetime.strptime(created_at, "%Y-%m-%dT%H:%M:%SZ")
-        data_timestamp = datetime.fromisoformat(created_at)
 
-        # 2. Get the exact current date and time
+        if output["success"] is True:
-        current_time = datetime.now(timezone.utc)
+            print(f"ID: {id} | Date: {created_at} | Game: {game_name} | Title: {title} | was successful")
-
-        # 3. Calculate the difference between the two times
-        time_difference = current_time - data_timestamp
-
-        # 4. Check if the difference is greater than 24 hours
-        if time_difference > timedelta(hours=24):
-            print("The data is more than 24 hours old.")
-        else:
-            #lets wait 24 hours befor downloading
-            print("The data is less than 24 hours old.")
-            continue
-
-        data = [list(row)]
-        print(
-            f"ID: {id} | Date: {created_at} | Game: {game_name} | Title: {title}"
-        )
-
-        # 1. Define paths and isolate base directory
-        if clip_is:
-            target_dir = f"download/clips/{id}"
-            cmd = f"TwitchDownloaderCLI clipdownload --id {id} -o {target_dir}/{id}.mp4 --collision Overwrite --temp-path download/temp"
-        else:
-            target_dir = f"download/videos/{id}"
-            # FIXED: Removed the duplicated command string combined with '&&'
-            cmd = f"TwitchDownloaderCLI videodownload --id {id} -o {target_dir}/{id}.mp4 --collision Overwrite --threads 2 --temp-path download/temp"
-
-        csv_file = f"{target_dir}/{id}.csv"
-
-        # 3. FIXED: Use the live streaming function to prevent Out-Of-Memory crashes
-        output = linux.run_command(cmd, look_for=["[STATUS]"])
-        output2 = linux.run_command(f"TwitchDownloaderCLI chatdownload --id {id} -o {target_dir}/{id}_chat.json -E --collision Overwrite --temp-path download/temp", look_for=["[STATUS]"])
-
-        if output:
-            # Only write CSV and update database if download actually completed
-            write_csv(data, csv_file)
-            print(f"✅ Success: TwitchDownloaderCLI video. {target_dir}")
             DB.mark_as_downloaded(id)
         else:
-            print(f"ID: {id} | Download Process failed.")
+            print(f"ID: {id} | Download Process failed. {output["stdout"]}. Error: {output["stderr"]}")
-            #print(f"❌ Reason/Error: {output.get('error', 'Unknown Error')}")
-            #if output.get("stderr"):
-            #    print(f"Details: {output['stderr']}")
 
-            # Clear temporary chunk clutter immediately if a VOD crashes out
+    print(f"Finished Downloading...")
-            if not clip_is:
-                print("Flushing temporary crash chunks...")
-                subprocess.run("rm -rf download/temp/*", shell=True)
-
-    print("Finished Downloading Pipeline.")
-
-def main():
-    global DB
-    DB = Database()
-    download()
 
 if __name__ == "__main__":
-    main()
+    DB = Database()
+    download()

twitch_secrets copy.json

@@ -0,0 +1,5 @@
+{
+    "client_id": "yr610ucde5vlae3zqniv23eps4ky7j",
+    "client_secret": "1m8bopo5hwtnv0mox9wql8i33fqrgr",
+    "manual_token": "dkmhv4f6k0mr1yyzof54xqll5pf7l3"
+}

twitch_video_info.py

@@ -99,7 +99,7 @@ async def get_streamer_vods():
         
         # Safely convert game_id to integer if possible, otherwise default to 0
         try:
-            clean_game_id = game_id
+            clean_game_id = int(game_id)
         except ValueError:
             clean_game_id = 0
 
@@ -133,6 +133,11 @@ async def get_streamer_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,
@@ -141,7 +146,7 @@ async def get_streamer_clips():
             "duration": c.duration,
             "url": c.url,
             "thumbnail_url": c.thumbnail_url,
-            "game_id": c.game_id,
+            "game_id": clean_game_id,
             "game_name": game_name,
             "stream_id": "0",
             "creator_name": c.creator_name,

uploader.py

@@ -78,7 +78,7 @@ def upload_video(file_path: str, title: str, category: CategoryId, description:
     try:
         # Check if file exists
         if not os.path.exists(file_path):
-            print(f"❌ Error: File not found: {file_path}")
+            print(f"Error: File not found: {file_path}")
             return False
 
         # Load credentials

vod_clip.py

@@ -183,7 +183,7 @@ def get_clip_slugs(channel_name):
         return clip_slugs
 
     except Exception as e:
-        print(f"❌ An unexpected error occurred: {e}")
+        print(f"An unexpected error occurred: {e}")
         return []
 
 if __name__ == "__main__":

youtube_hashtags.py

@@ -1,18 +1,15 @@
 #!/usr/bin/env python3
 import re
-import json
-import nltk
 import string
 from collections import Counter
 from nltk.corpus import stopwords
 from nltk.tokenize import word_tokenize
+import nltk
 
-# Download necessary NLTK data modules
+# Download necessary NLTK data
 nltk.download('punkt', quiet=True)
 nltk.download('stopwords', quiet=True)
 nltk.download('punkt_tab', quiet=True)
-nltk.download('averaged_perceptron_tagger', quiet=True) # Required for POS tagging
-nltk.download('averaged_perceptron_tagger_eng', quiet=True)
 
 def extract_text_from_srt(file_path: str):
     with open(file_path, 'r', encoding='utf-8') as file:
@@ -22,55 +19,32 @@ def extract_text_from_srt(file_path: str):
     clean_text = re.sub(r'\d+', '', clean_text)
     return clean_text
 
-def extract_text_from_json(file_path: str):
+def get_top_hashtags(srt_file_path: str, top_n: int = 10):
-    with open(file_path, "r", encoding="utf-8") as file:
+    raw_text = extract_text_from_srt(srt_file_path)
-        data = json.load(file)
     
-    messages = []
+    # Lowercase and remove punctuation
-    for comment in data.get("comments", []):
+    raw_text = raw_text.lower()
-        message_text = comment.get("message", {}).get("body", "")
+    raw_text = raw_text.translate(str.maketrans('', '', string.punctuation))
-        messages.append(message_text)
     
-    # Return a single merged string of all chat text
+    # Tokenize and remove stopwords
-    return " ".join(messages)
+    words = word_tokenize(raw_text)
-
-def get_top_nouns(file_path: str, top_n: int = 10):
-    # 1. Extract raw text
-    if file_path.endswith(".srt"):
-        raw_text = extract_text_from_srt(file_path)
-    else:
-        raw_text = extract_text_from_json(file_path)
-        
-    # 2. Basic cleanup (Keep original case for proper noun accuracy)
-    # Strip basic punctuation but leave words intact
-    clean_text = raw_text.translate(str.maketrans('', '', string.punctuation))
-    
-    # 3. Tokenize words
-    words = word_tokenize(clean_text)
-    
-    # 4. Part-of-Speech Tagging
-    tagged_words = nltk.pos_tag(words)
-    
-    # 5. Filter for Nouns (NN = Singular Noun, NNP = Proper Noun, NNS = Plural Noun)
     stop_words = set(stopwords.words('english'))
-    nouns = []
     
-    for word, tag in tagged_words:
+    # Filter for alphabetical words longer than 3 characters that aren't stop words
-        word_lower = word.lower()
+    filtered_words = [
-        # Filter out short fragments and standard stopwords
+        word for word in words 
-        if tag in ['NN', 'NNP', 'NNS'] and len(word_lower) > 2 and word_lower not in stop_words:
+        if word.isalpha() and word not in stop_words and len(word) > 3
-            nouns.append(word_lower)
+    ]
     
-    # 6. Count frequencies
+    # Get frequency and create hashtags
-    noun_counts = Counter(nouns)
+    word_counts = Counter(filtered_words)
-    return [noun for noun, count in noun_counts.most_common(top_n)]
+    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_nouns('download/videos/2813112936/2813112936.srt', top_n=10)
+    results = get_top_hashtags('your_video.srt', top_n=10)
-    print("Trending Hashtags SRT:", results)
+    print("Trending Hashtags:", results)
-
-    results = get_top_nouns("download/videos/2813112936/2813112936_chat.json", top_n=10)
-    print("Trending Hashtags JSON:", results)

youtube_short.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
-import os
+import argparse
-import json
+import sys
 import linux
 import tempfile
 from pathlib import Path
@@ -11,133 +11,142 @@ from pathlib import Path
 import numpy as np
 from PIL import Image, ImageFilter
 
-def get_video_info(input_path: Path) -> tuple:
+def apply_gaussian_blur(frame, radius: int = 30):
-    """Uses ffprobe to instantly read input video dimensions and frame rate."""
+    """
-    cmd = f"ffprobe -v error -select_streams v:0 -show_entries stream=width,height,r_frame_rate -of json {input_path}"
+    Transforms a single NumPy array frame using PIL's true GaussianBlur filter.
-    # Run command and capture output (assumes linux.run_command prints or you use subprocess)
+    """
-    import subprocess
+    # Convert numpy array to PIL Image
-    result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
+    image = Image.fromarray(frame)
-    #linux.run_command(cmd)
+    # Apply high-quality true Gaussian Blur
-    try:
+    blurred_image = image.filter(ImageFilter.GaussianBlur(radius=radius))
-        data = json.loads(result.stdout)
+    # Return back as a numpy array for MoviePy
-        stream = data['streams'][0]
+    return np.array(blurred_image)
-        w = int(stream['width'])
-        h = int(stream['height'])
-        # Convert fractional FPS string (e.g. "60/1" or "30000/1001") to float
-        fps_parts = stream['r_frame_rate'].split('/')
-        fps = float(fps_parts[0]) / float(fps_parts[1]) if len(fps_parts) > 1 else float(fps_parts[0])
-        return w, h, fps
-    except Exception:
-        return 1920, 1080, 60.0  # Safe defaults if probe fails
 
-def fit_to_9_16_letterbox(input_path: str, top_text: str = "TOP TEXT", bottom_text: str = "BOTTOM TEXT", use_blur: bool = True, force: bool = False):
+def fit_to_9_16_letterbox(input_path: str, top_text: str = "TOP TEXT", bottom_text: str = "BOTTOM TEXT", use_blur: bool = True):
-    threads = "8"
     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}"
 
-    if os.path.exists(output_path):
+    print("🧼 Sanitizing video metadata streams inside an automated safe context...")
-        if not force:
+    with tempfile.NamedTemporaryFile(suffix=input_file.suffix, delete=False) as temp_file:
-            print(f"❌ Error: Short video already exists: {output_path}")
+        temp_path = temp_file.name
-            return
-        else:
-            os.remove(output_path)
 
-    # 1. Probe input metadata instantly
+    bg_scaled = None
-    orig_w, orig_h, fps = get_video_info(input_file)
+    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
 
-    print("✍️ Generating text overlay graphics via MoviePy...")
+        # Background logic
-    # Render static images for text instead of running a video context
+        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, color="white", font="DejaVuSans-Bold",
+            text=top_text,
-        text_align="center", size=(canvas_w - 100, 300), method="caption"
+            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=bottom_text,
-        text_align="center", size=(canvas_w - 100, 300), method="caption"
+            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
         )
 
-    # Save text layers to temporary PNGs
+        # Clean up file locks safely
-    top_png = tempfile.NamedTemporaryFile(suffix=".png", delete=False).name
+        clip.close()
-    bottom_png = tempfile.NamedTemporaryFile(suffix=".png", delete=False).name
+        if bg_scaled: bg_scaled.close()
-    title_clip.save_frame(top_png)
+        if bg_cropped: bg_cropped.close()
-    bottom_clip.save_frame(bottom_png)
+        background_layer.close()
-    
+        foreground_clip.close()
         title_clip.close()
         bottom_clip.close()
+        final_clip.close()
 
-    print("🎬 Dispatching compilation workload to FFmpeg filtergraph...")
-    
-    # 2. Build the complex FFmpeg filtergraph
-    # [0:v] is the raw input video stream
-    filter_complex = []
-
-    if use_blur:
-        # Scale height to 1920, crop center 1080x1920, apply fast boxblur (power of 3 approximates Gaussian)
-        filter_complex.append(
-            f"[0:v]scale=-1:{canvas_h},crop={canvas_w}:{canvas_h}:(iw-{canvas_w})/2:0,boxblur=luma_radius=35:luma_power=3[bg];"
-        )
-    else:
-        # Generate a pure black background canvas matching video frame specs
-        filter_complex.append(
-            f"color=c=black:s={canvas_w}x{canvas_h}:r={fps}[bg];"
-        )
-
-    # Scale the foreground video to a clean 1080 width, keeping aspect ratio
-    filter_complex.append(
-        f"[0:v]scale={canvas_w}:-1[fg];"
-    )
-
-    # Layer composition chain:
-    # Overlay 1: Put scaled foreground onto background (centered vertically)
-    filter_complex.append(
-        f"[bg][fg]overlay=0:(H-h)/2[tmp1];"
-    )
-    # Overlay 2: Drop top text asset onto position Y=180
-    filter_complex.append(
-        f"[tmp1][1:v]overlay=(W-w)/2:180[tmp2];"
-    )
-    # Overlay 3: Drop bottom text asset onto position Y=1430
-    filter_complex.append(
-        f"[tmp2][2:v]overlay=(W-w)/2:1430[finalv]"
-    )
-
-    filter_graph = "".join(filter_complex)
-
-    # 3. Execute the native assembly command
-    # -map_chapters -1 -sn: Strips unnecessary metadata chunks instantly
-    # -c:a copy: Safely pulls original digital audio directly without decompression cycles
-    # -threads 0: Forces FFmpeg to auto-consume all available processing cores
-    ffmpeg_cmd = (
-        f'ffmpeg -y -v error -i "{input_file}" -i "{top_png}" -i "{bottom_png}" '
-        f'-filter_complex "{filter_graph}" '
-        f'-map "[finalv]" -map 0:a? -c:v libx264 -crf 18 -preset slow -pix_fmt yuv420p '
-        f'-c:a copy -map_chapters -1 -sn -threads {threads} "{output_path}"'
-    )
-
-    try:
-        linux.run_command(ffmpeg_cmd)
-        print(f"🎉 High-speed processing complete! Video saved to: {output_path}")
     finally:
-        # Clean up temporary PNG picture files safely
+        temp_file_path = Path(temp_path)
-        for path in (top_png, bottom_png):
+        if temp_file_path.exists():
-            if os.path.exists(path):
+            temp_file_path.unlink()
-                os.unlink(path)
         
+    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__":
-    import time
+    main()
-
-    start_time = time.perf_counter()
-
-    creator_name = "greenskiesbluegrass"
-    top_txt = "TeamPGP Live on Twitch...\n Every Friday and Sunday @7:30 ET.\n twitch.tv/teampgp"
-    bottom_txt = f"Clipped By: {creator_name}."
-    fit_to_9_16_letterbox("download/clips/AbnegateAgitatedGrassPJSalt/AbnegateAgitatedGrassPJSalt.mp4", top_txt, bottom_txt, True, True)
-
-    end_time = time.perf_counter()
-    execution_time = end_time - start_time
-
-    print(f"The function took {execution_time:.6f} seconds to complete.")