mirror of
https://github.com/mblanke/Gov_Travel_App.git
synced 2026-03-01 14:10:22 -05:00
mblanke
15094ac94b
- Implemented Python scraper using BeautifulSoup and pandas to automatically collect travel rates from official NJC website - Added currency extraction from table titles (supports EUR, USD, AUD, CAD, ARS, etc.) - Added country extraction from table titles for international rates - Flatten pandas MultiIndex columns for cleaner data structure - Default to CAD for domestic Canadian sources (accommodations and domestic tables) - Created SQLite database schema (raw_tables, rate_entries, exchange_rates, accommodations) - Successfully scraped 92 tables with 17,205 rate entries covering 25 international cities - Added migration script to convert scraped data to Node.js database format - Updated .gitignore for Python files (.venv/, __pycache__, *.pyc, *.sqlite3) - Fixed city validation and currency conversion in main app - Added comprehensive debug and verification scripts This replaces manual JSON maintenance with automated data collection from official government source.
50 lines
1.3 KiB
Python
50 lines
1.3 KiB
Python
from __future__ import annotations
|
|
|
|
import argparse
|
|
from pathlib import Path
|
|
|
|
from gov_travel import db
|
|
from gov_travel.scrapers import (
|
|
SOURCES,
|
|
extract_accommodations,
|
|
extract_exchange_rates,
|
|
extract_rate_entries,
|
|
scrape_tables_from_source,
|
|
)
|
|
|
|
|
|
def parse_args() -> argparse.Namespace:
|
|
parser = argparse.ArgumentParser(description="Scrape travel rates into SQLite")
|
|
parser.add_argument(
|
|
"--db",
|
|
type=Path,
|
|
default=Path("data/travel_rates.sqlite3"),
|
|
help="Path to the SQLite database",
|
|
)
|
|
return parser.parse_args()
|
|
|
|
|
|
def main() -> None:
|
|
args = parse_args()
|
|
connection = db.connect(args.db)
|
|
db.init_db(connection)
|
|
|
|
for source in SOURCES:
|
|
tables = scrape_tables_from_source(source)
|
|
db.insert_raw_tables(connection, source.name, source.url, tables)
|
|
|
|
rate_entries = extract_rate_entries(source, tables)
|
|
db.insert_rate_entries(connection, rate_entries)
|
|
|
|
exchange_rates = extract_exchange_rates(source, tables)
|
|
db.insert_exchange_rates(connection, exchange_rates)
|
|
|
|
if source.name == "accommodations":
|
|
accommodations = extract_accommodations(source, tables)
|
|
db.insert_accommodations(connection, accommodations)
|
|
|
|
connection.close()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main() |