Files
test/powercounty.py
2025-12-06 11:56:02 +00:00

594 lines
23 KiB
Python

# powercounty.py
import logging
import requests
import json
import psycopg2
from datetime import datetime
import re
from collections import defaultdict
import threading
# Set up logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s',
handlers=[
logging.FileHandler('powercounty.log'),
logging.StreamHandler()
]
)
# Set up a logger for this module
logger = logging.getLogger(__name__)
# Database connection parameters
DB_PARAMS = {
'host': 'localhost',
'database': 'nws',
'user': 'nws',
'password': 'nws'
}
# Set up a requests session
S = requests.Session()
# Power company metadata and URLs (from power3.py)
AEP_OH_META = "http://outagemap.aepohio.com.s3.amazonaws.com/resources/data/external/interval_generation_data/metadata.json"
AEP_WV_META = "http://outagemap.appalachianpower.com.s3.amazonaws.com/resources/data/external/interval_generation_data/metadata.json"
AEP_KY_META = 'http://outagemap.kentuckypower.com.s3.amazonaws.com/resources/data/external/interval_generation_data/metadata.json'
WV_FE_META = 'https://kubra.io/stormcenter/api/v1/stormcenters/6c715f0e-bbec-465f-98cc-0b81623744be/views/5ed3ddf1-3a6f-4cfd-8957-eba54b5baaad/currentState?preview=false'
AEP_WV_KUBRA_META = "https://kubra.io/stormcenter/api/v1/stormcenters/6674f49e-0236-4ed8-a40a-b31747557ab7/views/8cfe790f-59f3-4ce3-a73f-a9642227411f/currentState?preview=false"
AEP_OH_KUBRA_META = 'https://kubra.io/stormcenter/api/v1/stormcenters/9c0735d8-b721-4dce-b80b-558e98ce1083/views/9b2feb80-69f8-4035-925e-f2acbcf1728e/currentState?preview=false'
AEP_KY_KUBRA_META = 'https://kubra.io/stormcenter/api/v1/stormcenters/23dcd38e-2573-4e20-a463-959b11cae011/views/60f31606-5702-4a1e-a74c-08d866b7a6fa/currentState?preview=false'
AEP_WV_BASE = "http://outagemap.appalachianpower.com.s3.amazonaws.com/resources/data/external/interval_generation_data/"
AEP_OH_BASE = "http://outagemap.aepohio.com.s3.amazonaws.com/resources/data/external/interval_generation_data/"
AEP_KY_BASE = 'http://outagemap.kentuckypower.com.s3.amazonaws.com/resources/data/external/interval_generation_data/'
GRAYSON_COUNTY = 'https://outages.graysonrecc.com/data/boundaries.json'
# Additional URLs from power3.py
flemingjson = 'https://outage.fme.coop/data/boundaries.json'
bigsandy_url = 'http://outagemap.bigsandyrecc.com/data/boundaries.json'
southcentralpower_url = 'https://outage.southcentralpower.com/data/boundaries.json'
# Global list to collect all outage data
allcountyoutages = []
# This function will try to get a URL and log any errors
def safe_request(url, description="Fetching data"):
try:
logger.info(f"{description}: {url}")
response = S.get(url)
response.raise_for_status() # Raise an exception for bad status codes
logger.info(f"Successfully fetched data from {url}")
return response
except requests.exceptions.RequestException as e:
logger.error(f"Failed to {description} from {url}: {e}")
return None
# This function will parse a JSON response and log errors
def safe_json_load(response, description="Parsing JSON"):
try:
logger.info(f"{description}")
data = json.loads(response.text)
logger.info("Successfully parsed JSON data")
return data
except (json.JSONDecodeError, AttributeError) as e:
logger.error(f"Failed to {description}: {e}")
return None
# Ported functions from power3.py with enhanced logging
def fleming():
"""Fetch outage data for Fleming County, KY"""
logger.info("Fetching Fleming County outage data")
state = 'KY'
company = 'FLEM'
temp = safe_request(flemingjson, "fetching Fleming data")
if temp is None:
return
tempdata = safe_json_load(temp, "parsing Fleming JSON")
if tempdata is None:
return
try:
for j in tempdata[0]['boundaries']:
outageinfo = j.get('customersOutNow'), j.get('customersServed'), j.get('name'), state, company
allcountyoutages.append(outageinfo)
logger.info(f"Successfully processed {len(tempdata[0]['boundaries'])} Fleming County boundaries")
except (KeyError, IndexError) as e:
logger.error(f"Error processing Fleming County data: {e}")
def bigsandy():
"""Fetch outage data for Big Sandy RECC"""
logger.info("Fetching Big Sandy RECC outage data")
state = 'OH'
company = 'BS'
temp = safe_request(bigsandy_url, "fetching Big Sandy data")
if temp is None:
return
tempdata = safe_json_load(temp, "parsing Big Sandy JSON")
if tempdata is None:
return
try:
for j in tempdata[0]['boundaries']:
outageinfo = j.get('customersOutNow'), j.get('customersServed'), j.get('name'), state, company
allcountyoutages.append(outageinfo)
logger.info(f"Successfully processed {len(tempdata[0]['boundaries'])} Big Sandy boundaries")
except (KeyError, IndexError) as e:
logger.error(f"Error processing Big Sandy data: {e}")
def southcentralpower():
"""Fetch outage data for South Central Power"""
logger.info("Fetching South Central Power outage data")
company = 'SCP'
url = southcentralpower_url
temp = safe_request(url, "fetching South Central Power data")
if temp is None:
return
tempdata = safe_json_load(temp, "parsing South Central Power JSON")
if tempdata is None:
return
state = 'OH'
try:
for j in tempdata[0]['boundaries']:
outageinfo = j.get('customersOutNow'), j.get('customersServed'), j.get('name'), state, company
allcountyoutages.append(outageinfo)
logger.info(f"Successfully processed {len(tempdata[0]['boundaries'])} South Central Power boundaries")
except (KeyError, IndexError) as e:
logger.error(f"Error processing South Central Power data: {e}")
def ku_get_url():
"""Get KU outage data URL"""
logger.info("Getting KU outage data URL")
url = 'https://stormcenter.lge-ku.com/reports/1d6f7e68-e192-43c1-bfdc-d809333d8e40'
r = safe_request(url, "fetching KU report page")
if r is None:
return None
try:
x = re.search(r"instanceId: '(.*?)',", r.text)
if not x:
logger.error("Could not extract instanceId from KU report page")
return None
urlcom = x.group(1)
urlcom = 'https://kubra.io/stormcenter/api/v1/stormcenters/' + urlcom + '/views/a6cee9e4-312b-4b77-9913-2ae371eb860d/currentState?preview=false'
stuff = safe_request(urlcom, "fetching KU stormcenter data")
if stuff is None:
return None
jsonstuff = safe_json_load(stuff, "parsing KU stormcenter JSON")
if jsonstuff is None:
return None
interval_data = jsonstuff.get('data').get('interval_generation_data')
urlcom = 'https://kubra.io/' + interval_data + '/public/reports/1d6f7e68-e192-43c1-bfdc-d809333d8e40_report.json'
logger.info(f"Successfully constructed KU data URL: {urlcom}")
return urlcom
except Exception as e:
logger.error(f"Error getting KU URL: {e}")
return None
def county_json(meta, url, jsonname):
"""Generic function to get county JSON data"""
metainfo_response = safe_request(meta, "fetching metadata for county JSON")
if metainfo_response is None:
return None
metainfo = safe_json_load(metainfo_response, "parsing metadata for county JSON")
if metainfo is None:
return None
try:
metadir = metainfo['directory']
url = url + metadir + jsonname
outage_response = safe_request(url, "fetching county JSON data")
return outage_response
except KeyError as e:
logger.error(f"Error accessing metadata directory: {e}")
return None
def ku():
"""Fetch KU outage data"""
logger.info("Fetching KU outage data")
ku_list = []
url = ku_get_url()
if url is None:
return
data_response = safe_request(url, "fetching KU data")
if data_response is None:
return
tempdata = safe_json_load(data_response, "parsing KU data JSON")
if tempdata is None:
return
try:
temp = tempdata['file_data']['areas'][2]['areas'][0]['areas']
temp1 = tempdata['file_data']['areas'][2]['areas'][1]['areas']
temp2 = tempdata['file_data']['areas'][1]['areas'][0]['areas']
for i in temp:
ku_list.append(i)
for i in temp1:
ku_list.append(i)
for i in temp2:
ku_list.append(i)
for o in ku_list:
outageinfo = o['cust_a']['val'], o['cust_s'], o['name'].capitalize(), o['state'], o['utility']
allcountyoutages.append(outageinfo)
logger.info(f"Successfully processed {len(ku_list)} KU outage records")
except (KeyError, IndexError) as e:
logger.error(f"Error processing KU data: {e}")
def grayson():
"""Fetch Grayson County outage data"""
logger.info("Fetching Grayson County outage data")
company = 'GRE'
outage_response = safe_request(GRAYSON_COUNTY, "fetching Grayson County data")
if outage_response is None:
return
if not outage_response.headers.get('Content-Type', '').startswith('application/json'):
logger.error(f"Unexpected content type from Grayson County: {outage_response.headers.get('Content-Type')}")
return
tempdata = safe_json_load(outage_response, "parsing Grayson County JSON")
if tempdata is None:
return
state = 'KY'
try:
for j in tempdata[0]['boundaries']:
outageinfo = j.get('customersOutNow'), j.get('customersServed'), j.get('name'), state, company
allcountyoutages.append(outageinfo)
logger.info(f"Successfully processed {len(tempdata[0]['boundaries'])} Grayson County boundaries")
except (KeyError, IndexError) as e:
logger.error(f"Error processing Grayson County data: {e}")
def aep_county_vawv(meta, url, jsonname):
"""Fetch AEP county data for VA and WV"""
logger.info("Fetching AEP county data for VA and WV")
company = 'AEP'
outage_response = county_json(meta, url, jsonname)
if outage_response is None:
return
if not outage_response.headers.get('Content-Type', '').startswith('application/octet-stream'):
logger.error(f"Unexpected content type from AEP VA/WV: {outage_response.headers.get('Content-Type')}")
return
tempdata = safe_json_load(outage_response, "parsing AEP VA/WV JSON")
if tempdata is None:
return
try:
# WV data
state = 'WV'
for j in tempdata['file_data']['areas'][0]['areas'][2]['areas']:
outageinfo = j.get('cust_a').get('val'), j.get('cust_s'), j.get('area_name'), state, company
allcountyoutages.append(outageinfo)
# VA data
state = 'VA'
for j in tempdata['file_data']['areas'][0]['areas'][1]['areas']:
outageinfo = j.get('cust_a').get('val'), j.get('cust_s'), j.get('area_name').capitalize(), state, company
allcountyoutages.append(outageinfo)
logger.info("Successfully processed AEP VA/WV county data")
except (KeyError, IndexError) as e:
logger.error(f"Error processing AEP VA/WV data: {e}")
def aep_county_oh(meta, url, jsonname):
"""Fetch AEP county data for Ohio"""
logger.info("Fetching AEP county data for Ohio")
company = 'AEP'
state = 'OH'
outage_response = county_json(meta, url, jsonname)
if outage_response is None:
return
tempdata = safe_json_load(outage_response, "parsing AEP OH JSON")
if tempdata is None:
return
try:
for j in tempdata['file_data']['areas'][0]['areas'][0]['areas']:
outageinfo = j.get('cust_a').get('val'), j.get('cust_s'), j.get('area_name').capitalize(), state, company
allcountyoutages.append(outageinfo)
logger.info("Successfully processed AEP OH county data")
except (KeyError, IndexError) as e:
logger.error(f"Error processing AEP OH data: {e}")
def aep_county_ky(meta, url, jsonname):
"""Fetch AEP county data for Kentucky"""
logger.info("Fetching AEP county data for Kentucky")
company = 'AEP'
state = 'KY'
outage_response = county_json(meta, url, jsonname)
if outage_response is None:
return
tempdata = safe_json_load(outage_response, "parsing AEP KY JSON")
if tempdata is None:
return
try:
for j in tempdata['file_data']['areas'][0]['areas'][0]['areas']:
outageinfo = j.get('cust_a').get('val'), j.get('cust_s'), j.get('area_name').capitalize(), state, company
allcountyoutages.append(outageinfo)
logger.info("Successfully processed AEP KY county data")
except (KeyError, IndexError) as e:
logger.error(f"Error processing AEP KY data: {e}")
def firstenergy_county(meta, url, jsonname):
"""Fetch First Energy county data"""
logger.info("Fetching First Energy county data")
company = 'FE'
state = 'WV'
outage_response = county_json(meta, url, jsonname)
if outage_response is None:
return
if not outage_response.headers.get('Content-Type', '').startswith('application/octet-stream'):
logger.error(f"Unexpected content type from First Energy: {outage_response.headers.get('Content-Type')}")
return
tempdata = safe_json_load(outage_response, "parsing First Energy JSON")
if tempdata is None:
return
try:
for j in tempdata['file_data']['areas'][0]['areas'][0]['areas']:
outageinfo = j.get('cust_a').get('val'), j.get('cust_s'), j.get('area_name').capitalize(), state, company
allcountyoutages.append(outageinfo)
logger.info("Successfully processed First Energy county data")
except (KeyError, IndexError) as e:
logger.error(f"Error processing First Energy data: {e}")
def get_kubra_hexes(url):
"""Get Kubra hex data"""
outage_response = safe_request(url, "fetching Kubra hex data")
if outage_response is None:
return None, None
if not outage_response.headers.get('Content-Type', '').startswith('application/json'):
logger.error(f"Unexpected content type from Kubra: {outage_response.headers.get('Content-Type')}")
return None, None
tempdata = safe_json_load(outage_response, "parsing Kubra hex JSON")
if tempdata is None:
return None, None
try:
bothhex = tempdata.get('data').get('cluster_interval_generation_data')
hexes = bothhex.split('/')
logger.info(f"Successfully extracted Kubra hexes: {hexes}")
return hexes[2], hexes[3]
except (KeyError, AttributeError) as e:
logger.error(f"Error extracting Kubra hexes: {e}")
return None, None
def kubra_fe(baseurl1, baseurl2, meta):
"""Fetch Kubra First Energy data"""
logger.info("Fetching Kubra First Energy data")
hex2 = get_kubra_hexes(meta)
if hex2[0] is None:
return
url = baseurl1 + hex2[1] + baseurl2
company = 'FE'
state = 'WV'
outage_response = safe_request(url, "fetching Kubra FE data")
if outage_response is None:
return
if not outage_response.headers.get('Content-Type', '').startswith('application/json'):
logger.error(f"Unexpected content type from Kubra FE: {outage_response.headers.get('Content-Type')}")
return
tempdata = safe_json_load(outage_response, "parsing Kubra FE JSON")
if tempdata is None:
return
try:
for j in tempdata['file_data']['areas']:
if j.get('key') == "county":
outageinfo = j.get('cust_a').get('val'), j.get('cust_s'), j.get('name').capitalize(), state, company
allcountyoutages.append(outageinfo)
logger.info("Successfully processed Kubra FE county data")
except (KeyError, IndexError) as e:
logger.error(f"Error processing Kubra FE data: {e}")
def kubra_aep(baseurl1, baseurl2, meta, company='AEP'):
"""Fetch Kubra AEP data"""
logger.info(f"Fetching Kubra AEP data for company: {company}")
hex2 = get_kubra_hexes(meta)
if hex2[0] is None:
return
url = baseurl1 + hex2[1] + baseurl2
outage_response = safe_request(url, "fetching Kubra AEP data")
if outage_response is None:
return
if not outage_response.headers.get('Content-Type', '').startswith('application/json'):
logger.error(f"Unexpected content type from Kubra AEP: {outage_response.headers.get('Content-Type')}")
return
tempdata = safe_json_load(outage_response, "parsing Kubra AEP JSON")
if tempdata is None:
return
process_outage_data(tempdata, company)
def process_outage_data(data, company):
"""Process outage data with enhanced error handling"""
try:
# Navigate to the primary list of areas
primary_areas = data.get("file_data", {}).get("areas", [])
# If the list is empty, there's nothing to process
if not primary_areas:
logger.warning("No 'areas' data found in outage data.")
return
# Check the key of the first item to determine the format
first_item_key = primary_areas[0].get("key")
if first_item_key == "state":
# Format 1: Loop through each state object
for state_area in primary_areas:
state_name = state_area.get("name", "Unknown State")
# Get the nested list of counties for this state
county_list = state_area.get("areas", [])
for county in county_list:
# We are now at the county level
if county.get("key") == "county":
outageinfo = county.get('cust_a').get('val'), county.get('cust_s'), county.get('name').capitalize(), county.get('state'), company
allcountyoutages.append(outageinfo)
elif first_item_key == "county":
# Format 2: The primary list is already the county list
for county in primary_areas:
# We are now at the county level
if county.get("key") == "county":
outageinfo = county.get('cust_a').get('val'), county.get('cust_s'), county.get('name').capitalize(), county.get('state'), company
allcountyoutages.append(outageinfo)
else:
logger.warning(f"Unknown data format. Could not find 'state' or 'county' key. Found: {first_item_key}")
except (KeyError, IndexError) as e:
logger.error(f"Error processing outage data: {e}")
def insert_outage_data(cursor, outage_data, current_timestamp):
"""Insert outage data into the new table"""
if not outage_data:
logger.info("No outage data to insert into the database.")
return
sql = 'INSERT INTO newcountyoutages (outages, served, county, state, update, company) VALUES (%s, %s, %s, %s, %s, %s)'
try:
logger.info(f"Inserting {len(outage_data)} rows into the database.")
cursor.executemany(sql, outage_data)
logger.info("Successfully inserted data into the database.")
except Exception as e:
logger.error(f"Failed to insert data into the database: {e}")
raise
def main():
"""Main function to collect and insert outage data"""
conn = None
try:
conn = psycopg2.connect(**DB_PARAMS)
cursor = conn.cursor()
logger.info("Successfully connected to the database.")
# Clear the global list at the start
global allcountyoutages
allcountyoutages = []
# Collect outage data for each provider
logger.info("Starting data collection.")
# --- Kubra First Energy ---
try:
kubra_fe('https://kubra.io/data/', '/public/reports/8c3b0b30-c9e8-4e8f-8b0d-999c568bb085_report.json', WV_FE_META)
except Exception as e:
logger.error(f"Error collecting Kubra FE data: {e}")
# --- Kubra AEP WV ---
try:
kubra_aep('https://kubra.io/data/', '/public/reports/7929429f-635d-4761-b6c7-78f646cef3c2_report.json', AEP_WV_KUBRA_META)
except Exception as e:
logger.error(f"Error collecting Kubra AEP WV data: {e}")
# --- Kubra AEP OH ---
try:
kubra_aep('https://kubra.io/data/', '/public/reports/1bc6bd19-2315-4548-980a-6df73b93b355_report.json', AEP_OH_KUBRA_META)
except Exception as e:
logger.error(f"Error collecting Kubra AEP OH data: {e}")
# --- Kubra AEP KY ---
try:
kubra_aep('https://kubra.io/data/', '/public/reports/8c3b0b30-c9e8-4e8f-8b0d-999c568bb085_report.json', AEP_KY_KUBRA_META)
except Exception as e:
logger.error(f"Error collecting Kubra AEP KY data: {e}")
# --- Grayson County ---
try:
grayson()
except Exception as e:
logger.error(f"Error collecting Grayson County data: {e}")
# --- KU ---
try:
ku()
except Exception as e:
logger.error(f"Error collecting KU data: {e}")
# --- South Central Power ---
try:
southcentralpower()
except Exception as e:
logger.error(f"Error collecting South Central Power data: {e}")
# --- Big Sandy ---
try:
bigsandy()
except Exception as e:
logger.error(f"Error collecting Big Sandy data: {e}")
# --- AEP Direct (OH, WV, KY) ---
try:
aep_county_oh(AEP_OH_META, AEP_OH_BASE, "metadata.json")
except Exception as e:
logger.error(f"Error collecting AEP OH data: {e}")
try:
aep_county_vawv(AEP_WV_META, AEP_WV_BASE, "metadata.json")
except Exception as e:
logger.error(f"Error collecting AEP WV/VA data: {e}")
try:
aep_county_ky(AEP_KY_META, AEP_KY_BASE, "metadata.json")
except Exception as e:
logger.error(f"Error collecting AEP KY data: {e}")
# --- First Energy Direct ---
try:
firstenergy_county(WV_FE_META, 'https://s3.amazonaws.com/outages.sc4.firstenergycorp.com/resources/data/mdwv/interval_generation_data/', "metadata.json")
except Exception as e:
logger.error(f"Error collecting First Energy data: {e}")
# Insert collected data into the new table
current_timestamp = str(datetime.utcnow())
insert_outage_data(cursor, allcountyoutages, current_timestamp)
conn.commit()
logger.info("Data collection and database insert completed successfully.")
except Exception as e:
logger.exception("An error occurred during the main execution.")
if conn:
conn.rollback()
finally:
if conn:
cursor.close()
conn.close()
logger.info("Database connection closed.")
if __name__ == '__main__':
main()