moved youtube scirpts into there own folder

package/youtube/__init__.py

@@ -0,0 +1,15 @@
+# package/youtube/__init__.py
+
+# Expose components from individual modules using relative imports
+from .find_tags import find_tags
+from .hashtags import get_top_nouns
+from .shorts import fit_to_9_16_letterbox
+from .uploader import upload_video, CategoryId
+
+# Explicitly define what is exposed when importing the subpackage
+__all__ = [
+    "find_tags",
+    "get_top_nouns",
+    "fit_to_9_16_letterbox",
+    "upload_video",
+]

package/youtube/config.py

@@ -0,0 +1,36 @@
+#!/usr/bin/env python3
+import json
+
+from google.oauth2.credentials import Credentials
+from google.auth.transport.requests import Request
+
+CREDENTIALS = None
+
+def load_credentials() -> Credentials:
+    """Load credentials from secrets.json"""
+    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']
+        )
+        
+        # Refresh token if expired
+        if credentials.expired:
+            credentials.refresh(Request())
+            
+        return credentials
+    except FileNotFoundError:
+        print("Error: secrets.json not found! Please run setup.py first.")
+        return None
+    except Exception as e:
+        print(f"Error loading credentials: {str(e)}")
+        return None
+
+CREDENTIALS = load_credentials()

package/youtube/find_tags.py

@@ -0,0 +1,122 @@
+#!/usr/bin/env python3
+from typing import Any
+
+from googleapiclient.discovery import build
+from googleapiclient.errors import HttpError
+
+import package.youtube.config as config
+
+def get_my_uploads_playlist_id(youtube: build) -> Any:
+    """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: build, uploads_playlist_id: str, target_tag: str) -> list:
+    """
+    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 find_tags():
+    
+    if not config.CREDENTIALS:
+        return
+        
+    youtube = build('youtube', 'v3', credentials=config.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__":
+    find_tags()

package/youtube/hashtags.py

@@ -0,0 +1,104 @@
+#!/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
+
+# Download necessary NLTK data modules
+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) -> str:
+    """
+    Extracts the text from the srt file.
+
+    Args:
+        file_path (str): is the path to the str file.
+
+    Returns:
+        returns (str): returns the cleaned up text.
+    """
+    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 extract_text_from_json(file_path: str) -> str:
+    """
+    Extracts the text from the json file.
+    
+    Args:
+        file_path (str): is the path to the json file.
+    
+    Returns:
+        returns (str): returns the cleaned up text.
+    """
+    with open(file_path, "r", encoding="utf-8") as file:
+        data = json.load(file)
+
+    messages = []
+    for comment in data.get("comments", []):
+        message_text = comment.get("message", {}).get("body", "")
+        messages.append(message_text)
+    
+    # Return a single merged string of all chat text
+    return " ".join(messages)
+
+def get_top_nouns(file_path: str, top_n: int = 10) -> list:
+    """
+    Gets the top number of nouns based on past (top_n) arg.
+    
+    Args:
+        file_path (str): is the path to the text file.
+        top_n (int): is the number of nouns to return.
+    
+    Returns:
+        returns (list): returns a list of nouns.
+    """
+    # 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:
+        word_lower = word.lower()
+        # Filter out short fragments and standard stopwords
+        if tag in ['NN', 'NNP', 'NNS'] and len(word_lower) > 2 and word_lower not in stop_words:
+            nouns.append(word_lower)
+            
+    # 6. Count frequencies
+    noun_counts = Counter(nouns)
+    return [noun for noun, count in noun_counts.most_common(top_n)]
+    
+
+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)
+    print("Trending Hashtags SRT:", results)
+
+    results = get_top_nouns("download/videos/2813112936/2813112936_chat.json", top_n=10)
+    print("Trending Hashtags JSON:", results)

package/youtube/shorts.py

@@ -0,0 +1,142 @@
+#!/usr/bin/env python3
+import os
+import json
+import package.utils as utils
+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 get_video_info(input_path: Path) -> tuple:
+    """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}"
+    # Run command and capture output (assumes linux.run_command prints or you use subprocess)
+    import subprocess
+    result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
+    #linux.run_command(cmd)
+    try:
+        data = json.loads(result.stdout)
+        stream = data['streams'][0]
+        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):
+    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):
+        if not force:
+            print(f"❌ Error: Short video already exists: {output_path}")
+            return
+        else:
+            os.remove(output_path)
+
+    # 1. Probe input metadata instantly
+    orig_w, orig_h, fps = get_video_info(input_file)
+    canvas_w = 1080
+    canvas_h = 1920
+
+    print("✍️ Generating text overlay graphics via MoviePy...")
+    # Render static images for text instead of running a video context
+    title_clip = TextClip(
+        text=top_text, font_size=55, color="white", font="DejaVuSans-Bold",
+        text_align="center", size=(canvas_w - 100, 300), method="caption"
+    )
+    bottom_clip = TextClip(
+        text=bottom_text, font_size=55, color="white", font="DejaVuSans-Bold",
+        text_align="center", size=(canvas_w - 100, 300), method="caption"
+    )
+
+    # Save text layers to temporary PNGs
+    top_png = tempfile.NamedTemporaryFile(suffix=".png", delete=False).name
+    bottom_png = tempfile.NamedTemporaryFile(suffix=".png", delete=False).name
+    title_clip.save_frame(top_png)
+    bottom_clip.save_frame(bottom_png)
+    
+    title_clip.close()
+    bottom_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:
+        utils.run_command(ffmpeg_cmd)
+        print(f"🎉 High-speed processing complete! Video saved to: {output_path}")
+    finally:
+        # Clean up temporary PNG picture files safely
+        for path in (top_png, bottom_png):
+            if os.path.exists(path):
+                os.unlink(path)
+
+if __name__ == "__main__":
+    import time
+
+    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.")

package/youtube/uploader.py

@@ -0,0 +1,173 @@
+#!/usr/bin/env python3
+import os
+import argparse
+from enum import Enum
+from datetime import datetime
+
+from googleapiclient.discovery import build
+from googleapiclient.http import MediaFileUpload
+from googleapiclient.errors import HttpError
+
+import package.youtube.config as config
+
+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 upload_video(file_path: str, title: str, category: CategoryId, description: str = "", privacyStatus: str = 'private', tags: list = None, release_time: datetime = None) -> bool:
+    """
+    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):
+            print(f"❌ Error: File not found: {file_path}")
+            return False
+
+        # Load credentials
+        if not config.CREDENTIALS:
+            return False
+
+        # Create YouTube API client
+        youtube = build('youtube', 'v3', credentials=config.CREDENTIALS)
+
+        # Configure the status object dynamically
+        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,
+                'categoryId': category.value
+            },
+            'status': status_body
+        }
+
+        # Create media file upload
+        media = MediaFileUpload(
+            file_path,
+            chunksize=1024*1024,
+            resumable=True
+        )
+
+        # Create the video insert request
+        insert_request = youtube.videos().insert(
+            part=','.join(body.keys()),
+            body=body,
+            media_body=media
+        )
+
+        print(f"Starting upload for '{title}'...")
+        response = None
+        while response is None:
+            status, response = insert_request.next_chunk()
+            if status:
+                print(f"Uploaded {int(status.progress() * 100)}%")
+
+        print(f"\nUpload Complete!")
+        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:
+        print(f"An HTTP error occurred: {str(e)}")
+        return False
+    except Exception as e:
+        print(f"An error occurred: {str(e)}")
+        return False
+
+def main():
+    parser = argparse.ArgumentParser(description='Upload a video to YouTube')
+    parser.add_argument('--file', required=True, help='Path to the video file')
+    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()
+    
+    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()