first commit

This commit is contained in:
2026-07-15 01:13:37 -04:00
commit f4c366f9aa
6 changed files with 802 additions and 0 deletions
+3
View File
@@ -0,0 +1,3 @@
/secrets.json
/client_secrets.json
/clips_database.db
+121
View File
@@ -0,0 +1,121 @@
#!/usr/bin/env python3
import os
import json
import argparse
from google.oauth2.credentials import Credentials
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
from googleapiclient.discovery import build
from googleapiclient.http import MediaFileUpload
from googleapiclient.errors import HttpError
def load_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
def upload_video(file_path, description):
"""
Upload a video to YouTube
Args:
file_path (str): Path to the video file
description (str): Video description
"""
try:
# Check if file exists
if not os.path.exists(file_path):
print(f"Error: File not found: {file_path}")
return False
# Load credentials
credentials = load_credentials()
if not credentials:
return False
# Create YouTube API client
youtube = build('youtube', 'v3', credentials=credentials)
# Get the filename without extension as default title
title = os.path.splitext(os.path.basename(file_path))[0]
# Prepare the video upload request
body = {
'snippet': {
'title': title,
'description': description,
'tags': [],
'categoryId': '22' # Default to 'People & Blogs' category
},
'status': {
'privacyStatus': 'private', # Default to private
'selfDeclaredMadeForKids': False
}
}
# 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("Starting upload...")
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']}")
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', help='Path to the video file')
parser.add_argument('description', help='Video description')
args = parser.parse_args()
upload_video(args.file, args.description)
if __name__ == "__main__":
main()
+191
View File
@@ -0,0 +1,191 @@
#!/usr/bin/env python3
import os
import requests
import sqlite3
import subprocess
CHANNEL_NAME = 'teampgp' # Replace with the streamer's username
def download_clips():
undownload_items = get_undownloaded_records()
print("Download Clips...")
# Updated unpack loop to include clip_by
for record_id, record_date, title, gamename, clip_by, downloaded in undownload_items:
print(f"Slug: {record_id} | Date: {record_date} | Game: {gamename} | By: {clip_by} | Title: {title}")
# Ensure output directory exists before running CLI tools
os.makedirs(f"save/clips/{record_id}", exist_ok=True)
# Uses the 'clipdownload' command
output = run_linux_command(f"TwitchDownloaderCLI clipdownload --id {record_id} -o save/clips/{record_id}/{record_id}.mp4")
if output["success"] is True:
print(f"Slug: {record_id} | Date: {record_date} | Game: {gamename} | By: {clip_by} | Title: {title} | was successful")
mark_as_downloaded(record_id)
else:
print(f"Slug: {record_id} | Date: {record_date} | Game: {gamename} | By: {clip_by} | Title: {title} | was Failed")
if not output["success"]: print(f"-> Clip Download Error: {output['stderr']}")
def run_linux_command(command: str):
"""Executes a Linux command, waits for completion, and returns output."""
try:
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:
return {"success": False, "stdout": e.stdout, "stderr": e.stderr}
def mark_as_downloaded(record_id: str):
"""Updates the downloaded status to True (1) for a specific clip slug."""
conn = sqlite3.connect("database.db")
cursor = conn.cursor()
cursor.execute(
"UPDATE clips SET downloaded = 1 WHERE id = ?",
(record_id,)
)
conn.commit()
conn.close()
def get_undownloaded_records():
"""Retrieves all rows where downloaded status is False (0)."""
conn = sqlite3.connect("database.db")
cursor = conn.cursor()
# Added clip_by to the SELECT fields
cursor.execute(
"SELECT id, date, title, gamename, clip_by, downloaded, uploaded FROM clips WHERE downloaded = 0"
)
records = cursor.fetchall()
conn.close()
return records
def insert_record(record_id: str, record_date: str, title: str, gamename: str, clip_by: str):
"""Inserts a clip record including its text slug string and creator username."""
conn = sqlite3.connect("database.db")
cursor = conn.cursor()
# Added clip_by TEXT NOT NULL field to table definition
cursor.execute(
"""
CREATE TABLE IF NOT EXISTS clips (
id TEXT PRIMARY KEY,
date TEXT NOT NULL,
title TEXT NOT NULL,
gamename TEXT NOT NULL,
clip_by TEXT NOT NULL,
downloaded INTEGER NOT NULL,
uploaded INTEGER NOT NULL
)
"""
)
# Handled database migration gracefully if running script on an older DB missing the column
try:
cursor.execute(
"INSERT OR IGNORE INTO clips (id, date, title, gamename, clip_by, downloaded, uploaded) VALUES (?, ?, ?, ?, ?, ?, ?)",
(str(record_id), str(record_date), title, gamename, clip_by, 0, 0),
)
except sqlite3.OperationalError as e:
if "has no column named clip_by" in str(e):
print("Upgrading database schema to support creator names...")
cursor.execute("ALTER TABLE clips ADD COLUMN clip_by TEXT DEFAULT 'Unknown'")
cursor.execute(
"INSERT OR IGNORE INTO clips (id, date, title, gamename, clip_by, downloaded, uploaded) VALUES (?, ?, ?, ?, ?, ?, ?)",
(str(record_id), str(record_date), title, gamename, clip_by, 0, 0),
)
else:
raise e
conn.commit()
conn.close()
def get_clip_slugs(channel_name):
session = requests.Session()
url = "https://twitch.tv"
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"
}
# Query updated to fetch the curator's login (the user who clipped it)
query_string = """
query GetChannelClips($login: String!, $limit: Int!) {
user(login: $login) {
clips(first: $limit, criteria: { period: ALL_TIME, sort: VIEWS_DESC }) {
edges {
node {
slug
title
createdAt
game {
displayName
}
curator {
login
}
}
}
}
}
}
"""
payload = [{
"operationName": "GetChannelClips",
"query": query_string,
"variables": {
"login": channel_name.lower(),
"limit": 30
}
}]
try:
req = requests.Request('POST', url, json=payload)
prepped = session.prepare_request(req)
response = session.send(prepped)
response.raise_for_status()
data = response.json()
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['clips']['edges']
clip_slugs = []
print(f"--- Top Clips for {channel_name} ---")
for edge in edges:
node = edge['node']
game_info = node.get('game')
game_name = game_info.get('displayName') if game_info else "Unknown/No Category"
# Safe extraction in case the curator account was deleted/missing
curator_info = node.get('curator')
clip_by = curator_info.get('login') if curator_info else "Unknown Creator"
print(f"Slug: {node['slug']} | Date: {node['createdAt']} | Game: {game_name} | By: {clip_by} | Title: {node['title']}")
# Passing clip_by to database writer block
insert_record(node['slug'], node['createdAt'], node['title'], game_name, clip_by)
clip_slugs.append(node['slug'])
return clip_slugs
except Exception as e:
print(f"An unexpected error occurred: {e}")
return []
if __name__ == "__main__":
get_clip_slugs(CHANNEL_NAME)
download_clips()
+190
View File
@@ -0,0 +1,190 @@
#!/usr/bin/env python3
import requests
import sqlite3
import subprocess
from datetime import datetime
CHANNEL_NAME = 'teampgp' # Replace with the streamer's username
# 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."""
try:
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:
return {"success": False, "stdout": e.stdout, "stderr": e.stderr}
def mark_as_downloaded(slug: str):
"""Flags a specific clip row record to downloaded (1)."""
CURSOR.execute(
"UPDATE clips SET downloaded = 1 WHERE slug = ?",
(slug,)
)
CONN.commit()
def get_undownloaded_clips():
"""Retrieves all clip rows remaining to be captured."""
CURSOR.execute(
"SELECT slug, date, title, gamename, clip_by, view_count, downloaded FROM clips WHERE downloaded = 0"
)
return CURSOR.fetchall()
def insert_record(slug: str, record_date_str: str, title: str, gamename: str, clip_by: str, views: int):
"""Cleans up ISO-8601 strings into unified date structures for the database."""
try:
clean_date = datetime.strptime(record_date_str, "%Y-%m-%dT%H:%M:%SZ").date()
except ValueError:
clean_date = record_date_str
CURSOR.execute(
"INSERT OR IGNORE INTO clips (slug, date, title, gamename, clip_by, view_count, downloaded, uploaded_yt) VALUES (?, ?, ?, ?, ?, ?, ?, ?)",
(slug, str(clean_date), title, gamename, clip_by, views, False, False),
)
CONN.commit()
def get_channel_clips(channel_name: str):
"""Queries Twitch's public endpoint directly for trending clips."""
session = requests.Session()
url = "https://gql.twitch.tv/gql"
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"
}
# Twitch GQL schema for channel discovery clips
query_string = """
query GetChannelClips($login: String!, $limit: Int!) {
user(login: $login) {
clips(first: $limit, criteria: { period: ALL_TIME }) {
edges {
node {
slug
title
createdAt
viewCount
game {
displayName
}
curator {
login
}
}
}
}
}
}
"""
payload = [{
"operationName": "GetChannelClips",
"query": query_string,
"variables": {
"login": channel_name.lower(),
"limit": 40
}
}]
try:
req = requests.Request('POST', url, json=payload)
prepped = session.prepare_request(req)
response = session.send(prepped)
response.raise_for_status()
data = response.json()
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['clips']['edges']
slugs = []
print(f"--- Top Clips for {channel_name} ---")
for edge in edges:
node = edge['node']
game_info = node.get('game')
game_name = game_info.get('displayName') if game_info else "Unknown/No Category"
slug_id = node['slug']
# Safe extraction in case the curator account was deleted/missing
curator_info = node.get('curator')
clip_by = curator_info.get('login') if curator_info else "Unknown Creator"
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']))
slugs.append(slug_id)
return slugs
except Exception as e:
print(f"An unexpected error occurred: {e}")
return []
if __name__ == "__main__":
create_database()
get_channel_clips(CHANNEL_NAME)
download_clips()
close_database()
+102
View File
@@ -0,0 +1,102 @@
import json
import os
import requests
CHANNEL_NAME = 'teampgp' # Replace with the streamer's username
DB_FILE = "twitch_vods.json"
def get_vod_data(channel_name):
session = requests.Session()
url = "https://twitch.tv"
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"
}
query_string = """
query GetChannelVideos($login: String!, $limit: Int!) {
user(login: $login) {
videos(first: $limit, types: [ARCHIVE]) {
edges {
node {
id
title
publishedAt
}
}
}
}
}
"""
payload = [{
"operationName": "GetChannelVideos",
"query": query_string,
"variables": {
"login": channel_name.lower(),
"limit": 30
}
}]
try:
req = requests.Request('POST', url, json=payload)
prepped = session.prepare_request(req)
response = session.send(prepped)
response.raise_for_status()
data = response.json()
result = data 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 []
return user_data['videos']['edges']
except Exception as e:
print(f"Failed to fetch data: {e}")
return []
def store_in_nosql_format(edges):
# Load existing NoSQL database if it exists, otherwise start fresh
if os.path.exists(DB_FILE):
with open(DB_FILE, 'r', encoding='utf-8') as f:
try:
db = json.load(f)
except json.JSONDecodeError:
db = {}
else:
db = {}
new_records_count = 0
# Process and structure data using VOD ID as the key
for edge in edges:
node = edge['node']
vod_id = node['id']
# This structures the document under the specific ID key
db[vod_id] = {
"title": node['title'],
"published_at": node['publishedAt'],
"channel": CHANNEL_NAME.lower()
}
new_records_count += 1
# Save the updated document store back to the disk
with open(DB_FILE, 'w', encoding='utf-8') as f:
json.dump(db, f, indent=4, ensure_ascii=False)
print(f"Successfully processed {new_records_count} VOD documents into '{DB_FILE}'.")
if __name__ == "__main__":
vod_edges = get_vod_data(CHANNEL_NAME)
if vod_edges:
store_in_nosql_format(vod_edges)
+195
View File
@@ -0,0 +1,195 @@
#!/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()