Containerize scraper and externalize credentials

Move DB host/user/password, Discord webhook, and log path to env vars
so the script can be deployed via Docker compose. Discord notifications
are now skipped silently when DISCORD_WEBHOOK is unset (the old
hardcoded webhook is removed pending rotation). Adds Dockerfile,
docker-compose.yml, requirements.txt, .env.example, and .gitignore for
the cyrion deployment.
This commit is contained in:
wes
2026-05-06 23:20:12 -04:00
parent b9864b36b4
commit 10bdee8e1f
6 changed files with 237 additions and 181 deletions
+16
View File
@@ -0,0 +1,16 @@
# Knoebels scraper environment configuration.
# Copy to .env on the deploy host and fill in real values.
# Never commit the real .env.
# PostgreSQL connection (phlegethon by default)
DB_HOST=192.168.88.9
DB_PORT=5432
DB_USER=kuhnobowls
DB_PASSWORD=
# Optional Discord webhook for notifications.
# Leave empty/unset to skip Discord calls entirely.
DISCORD_WEBHOOK=
# Log path inside the container. Mapped to the knb_logs named volume by compose.
LOG_PATH=/var/log/kuh-no-bowls/kuh-no-bowls.log
+7
View File
@@ -0,0 +1,7 @@
.env
__pycache__/
*.pyc
.venv/
venv/
historical_data/
*.log
+10
View File
@@ -0,0 +1,10 @@
FROM python:3.13-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY attractions_api_logger.py .
ENTRYPOINT ["python", "-u", "attractions_api_logger.py"]
+188 -181
View File
@@ -1,181 +1,188 @@
#!/usr/bin/env python3
from datetime import datetime, date, timedelta
import json, requests, psycopg2, logging, sys
from psycopg2 import sql
ATTRACTIONS_IO_ENDPOINT = "https://live-data.attractions.io/72f0ea9e-d196-508a-bee8-cce62c3228c7.json"
DISCORD_WEBHOOK = 'https://discord.com/api/webhooks/878651005015842827/o_KXXiPgor-DhZQ9vgL-MNOYb-RDmQCAbuYmgUpsoEOqu3XCfBdUM6rDmF1cMrZg12b0'
db_params = {
'dbname': 'gp0',
'user': 'kuhnobowls',
'password': 'saddog095',
'host': '192.168.88.5',
'port': '5432',
'options': '-c search_path=knoebels'
}
park_hours_query = """
SELECT *
FROM knoebels."LZ_attractions_io_resort"
ORDER BY datestamp DESC
LIMIT 1
"""
def send_to_discord(message):
# The payload to send to the webhook
data = {
"content": message
}
try:
# Send the POST request to the webhook URL
response = requests.post(DISCORD_WEBHOOK, json=data)
# Check if the request was successful
if response.status_code == 204:
print("Message sent successfully.")
else:
print(f"Failed to send message. Status code: {response.status_code}, Response: {response.text}")
except requests.exceptions.RequestException as e:
print(f"Error sending message: {e}")
def log_to_database(table_name, data):
with psycopg2.connect(**db_params) as conn:
with conn.cursor() as cursor:
columns = len(data[0])
query = sql.SQL("INSERT INTO {table} VALUES ({values})").format(
table=sql.Identifier(table_name),
values=sql.SQL(', ').join(sql.Placeholder() * columns)
)
cursor.executemany(query, data)
conn.commit()
def generic_query(q):
ret = []
with psycopg2.connect(**db_params) as conn:
with conn.cursor() as cursor:
cursor.execute(q)
rows = cursor.fetchall()
col_names = [desc[0] for desc in cursor.description]
for row in rows:
ret.append(row)
return ret
def fetch_webpage(url):
HEADERS = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:124.0) Gecko/20100101 Firefox/124.0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
'Accept-Language': 'en-US,en;q=0.5',
'DNT': '1',
'Sec-GPC': '1',
'Connection': 'keep-alive',
'Upgrade-Insecure-Requests': '1',
'Sec-Fetch-Dest': 'document',
'Sec-Fetch-Mode': 'navigate',
'Sec-Fetch-Site': 'none',
'Sec-Fetch-User': '?1',
}
try:
response = requests.get(url, headers=HEADERS)
if response.status_code == 200:
return response.json()
else:
return f"Error: {response.status_code} - Unable to fetch webpage"
except Exception as e:
return f"Error: {str(e)} - Unable to fetch webpage"
def pull_data_and_log(log_park_hours):
json_data = fetch_webpage(ATTRACTIONS_IO_ENDPOINT)
logging.debug('Parsing park hours...')
try:
park_opens = json.loads(json_data['entities']['Resort']['records'][0]['OpeningTimes'])['start']
park_closes = json.loads(json_data['entities']['Resort']['records'][0]['OpeningTimes'])['end']
except KeyError as e:
logging.error('Unable to pull park hours. Is the park open today?')
return
logging.debug('Checking that park hours from API are actually occuring today...')
if not datetime.today().date() == datetime.strptime(park_opens, "%Y-%m-%d %H:%M:%S").date():
logging.error('API not returning park hours for today yet. Exiting...')
return
resort_data = [[datetime.now(), json_data['entities']['Resort']['records'][0]['_id'], park_opens, park_closes]]
if log_park_hours:
logging.info('Inserting park hours into LZ_attractions_io_resort...')
log_to_database('LZ_attractions_io_resort', resort_data)
if not (datetime.strptime(park_opens, "%Y-%m-%d %H:%M:%S") - timedelta(minutes=5)) <= datetime.now() <= (datetime.strptime(park_closes, "%Y-%m-%d %H:%M:%S") + timedelta(minutes=5)):
logging.info('Park not open now. Exiting...')
return
attraction_data = []
for attraction in json_data['entities']['Item']['records']:
try:
isOperational = attraction['IsOperational']
except:
isOperational = None
try:
QueueTime = attraction['QueueTime']
except:
QueueTime = None
try:
QueueStatusMessage = attraction['QueueStatusMessage']
except:
QueueStatusMessage = None
try:
IsOpen = attraction['IsOpen']
except:
IsOpen = None
try:
OpeningTimes = json.loads(attraction['OpeningTimes'])
start = OpeningTimes['start']
end = OpeningTimes['end']
except:
start = None
end = None
row = [attraction['_id'], isOperational, QueueTime, QueueStatusMessage, IsOpen, start, end, datetime.now()]
attraction_data.append(row)
queueline_data = []
for queue in json_data['entities']['QueueLine']['records']:
row = [datetime.now(), queue['_id'], queue['QueueTime']]
queueline_data.append(row)
logging.debug('Inserting rows into LZ_attractions_io...')
log_to_database('LZ_attractions_io', attraction_data)
logging.debug('Inserting rows into LZ_attractions_io_queuetimes...')
log_to_database('LZ_attractions_io_queuetimes', queueline_data)
logging.basicConfig(format='%(asctime)s %(levelname)s %(message)s', level=logging.DEBUG, filename="/home/hoid/git_repos/kuh-no-bowls/knb.log",filemode="a")
logging.info('--------------------------------------------------------------------------------')
logging.info('Fetching most recent park hours entry from DB...')
park_hours_pull = generic_query(park_hours_query)[0]
logging.debug('%s - %s', park_hours_pull[2], park_hours_pull[3])
if park_hours_pull[2].date() == date.today():
logging.info('Park hours for today already in DB')
park_opens = park_hours_pull[2]
park_closes = park_hours_pull[3]
if (park_opens - timedelta(minutes=5)) <= datetime.now() <= (park_closes + timedelta(minutes=5)):
logging.info('Park is open! Pulling data from API...')
pull_data_and_log(False)
else:
logging.info('Park not currently open. Exiting...')
else:
logging.info('Park hours for today not in DB')
pull_data_and_log(True)
#!/usr/bin/env python3
import os
from datetime import datetime, date, timedelta
import json, requests, psycopg2, logging, sys
from psycopg2 import sql
ATTRACTIONS_IO_ENDPOINT = "https://live-data.attractions.io/72f0ea9e-d196-508a-bee8-cce62c3228c7.json"
DISCORD_WEBHOOK = os.environ.get('DISCORD_WEBHOOK', '').strip()
DB_PASSWORD = os.environ.get('DB_PASSWORD')
if not DB_PASSWORD:
sys.stderr.write("ERROR: DB_PASSWORD env var is required\n")
sys.exit(1)
db_params = {
'dbname': 'gp0',
'user': os.environ.get('DB_USER', 'kuhnobowls'),
'password': DB_PASSWORD,
'host': os.environ.get('DB_HOST', '192.168.88.9'),
'port': os.environ.get('DB_PORT', '5432'),
'options': '-c search_path=knoebels'
}
LOG_PATH = os.environ.get('LOG_PATH', '/var/log/kuh-no-bowls.log')
park_hours_query = """
SELECT *
FROM knoebels."LZ_attractions_io_resort"
ORDER BY datestamp DESC
LIMIT 1
"""
def send_to_discord(message):
if not DISCORD_WEBHOOK:
# Discord notifications disabled — skip silently.
return
data = {
"content": message
}
try:
response = requests.post(DISCORD_WEBHOOK, json=data)
if response.status_code == 204:
print("Message sent successfully.")
else:
print(f"Failed to send message. Status code: {response.status_code}, Response: {response.text}")
except requests.exceptions.RequestException as e:
print(f"Error sending message: {e}")
def log_to_database(table_name, data):
with psycopg2.connect(**db_params) as conn:
with conn.cursor() as cursor:
columns = len(data[0])
query = sql.SQL("INSERT INTO {table} VALUES ({values})").format(
table=sql.Identifier(table_name),
values=sql.SQL(', ').join(sql.Placeholder() * columns)
)
cursor.executemany(query, data)
conn.commit()
def generic_query(q):
ret = []
with psycopg2.connect(**db_params) as conn:
with conn.cursor() as cursor:
cursor.execute(q)
rows = cursor.fetchall()
col_names = [desc[0] for desc in cursor.description]
for row in rows:
ret.append(row)
return ret
def fetch_webpage(url):
HEADERS = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:124.0) Gecko/20100101 Firefox/124.0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
'Accept-Language': 'en-US,en;q=0.5',
'DNT': '1',
'Sec-GPC': '1',
'Connection': 'keep-alive',
'Upgrade-Insecure-Requests': '1',
'Sec-Fetch-Dest': 'document',
'Sec-Fetch-Mode': 'navigate',
'Sec-Fetch-Site': 'none',
'Sec-Fetch-User': '?1',
}
try:
response = requests.get(url, headers=HEADERS)
if response.status_code == 200:
return response.json()
else:
return f"Error: {response.status_code} - Unable to fetch webpage"
except Exception as e:
return f"Error: {str(e)} - Unable to fetch webpage"
def pull_data_and_log(log_park_hours):
json_data = fetch_webpage(ATTRACTIONS_IO_ENDPOINT)
logging.debug('Parsing park hours...')
try:
park_opens = json.loads(json_data['entities']['Resort']['records'][0]['OpeningTimes'])['start']
park_closes = json.loads(json_data['entities']['Resort']['records'][0]['OpeningTimes'])['end']
except KeyError as e:
logging.error('Unable to pull park hours. Is the park open today?')
return
logging.debug('Checking that park hours from API are actually occuring today...')
if not datetime.today().date() == datetime.strptime(park_opens, "%Y-%m-%d %H:%M:%S").date():
logging.error('API not returning park hours for today yet. Exiting...')
return
resort_data = [[datetime.now(), json_data['entities']['Resort']['records'][0]['_id'], park_opens, park_closes]]
if log_park_hours:
logging.info('Inserting park hours into LZ_attractions_io_resort...')
log_to_database('LZ_attractions_io_resort', resort_data)
if not (datetime.strptime(park_opens, "%Y-%m-%d %H:%M:%S") - timedelta(minutes=5)) <= datetime.now() <= (datetime.strptime(park_closes, "%Y-%m-%d %H:%M:%S") + timedelta(minutes=5)):
logging.info('Park not open now. Exiting...')
return
attraction_data = []
for attraction in json_data['entities']['Item']['records']:
try:
isOperational = attraction['IsOperational']
except:
isOperational = None
try:
QueueTime = attraction['QueueTime']
except:
QueueTime = None
try:
QueueStatusMessage = attraction['QueueStatusMessage']
except:
QueueStatusMessage = None
try:
IsOpen = attraction['IsOpen']
except:
IsOpen = None
try:
OpeningTimes = json.loads(attraction['OpeningTimes'])
start = OpeningTimes['start']
end = OpeningTimes['end']
except:
start = None
end = None
row = [attraction['_id'], isOperational, QueueTime, QueueStatusMessage, IsOpen, start, end, datetime.now()]
attraction_data.append(row)
queueline_data = []
for queue in json_data['entities']['QueueLine']['records']:
row = [datetime.now(), queue['_id'], queue['QueueTime']]
queueline_data.append(row)
logging.debug('Inserting rows into LZ_attractions_io...')
log_to_database('LZ_attractions_io', attraction_data)
logging.debug('Inserting rows into LZ_attractions_io_queuetimes...')
log_to_database('LZ_attractions_io_queuetimes', queueline_data)
logging.basicConfig(format='%(asctime)s %(levelname)s %(message)s', level=logging.DEBUG, filename=LOG_PATH, filemode="a")
logging.info('--------------------------------------------------------------------------------')
logging.info('Fetching most recent park hours entry from DB...')
park_hours_pull = generic_query(park_hours_query)[0]
logging.debug('%s - %s', park_hours_pull[2], park_hours_pull[3])
if park_hours_pull[2].date() == date.today():
logging.info('Park hours for today already in DB')
park_opens = park_hours_pull[2]
park_closes = park_hours_pull[3]
if (park_opens - timedelta(minutes=5)) <= datetime.now() <= (park_closes + timedelta(minutes=5)):
logging.info('Park is open! Pulling data from API...')
pull_data_and_log(False)
else:
logging.info('Park not currently open. Exiting...')
else:
logging.info('Park hours for today not in DB')
pull_data_and_log(True)
+14
View File
@@ -0,0 +1,14 @@
services:
scraper:
build: .
image: kuh-no-bowls:latest
container_name: kuh-no-bowls-scraper
env_file: .env
environment:
LOG_PATH: /var/log/kuh-no-bowls/kuh-no-bowls.log
TZ: America/New_York
volumes:
- knb_logs:/var/log/kuh-no-bowls
volumes:
knb_logs:
+2
View File
@@ -0,0 +1,2 @@
requests
psycopg2-binary