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.
28 lines
640 B
Python
28 lines
640 B
Python
import sqlite3
|
|
|
|
conn = sqlite3.connect('data/travel_rates_scraped.sqlite3')
|
|
cursor = conn.cursor()
|
|
|
|
print("All sources and their currency distributions:")
|
|
cursor.execute("""
|
|
SELECT source, currency, COUNT(*) as count
|
|
FROM rate_entries
|
|
GROUP BY source, currency
|
|
ORDER BY source, currency
|
|
""")
|
|
for row in cursor.fetchall():
|
|
print(f" {row[0]} / {row[1]}: {row[2]}")
|
|
|
|
print("\nInternational source countries:")
|
|
cursor.execute("""
|
|
SELECT DISTINCT country
|
|
FROM rate_entries
|
|
WHERE source = 'international'
|
|
ORDER BY country
|
|
LIMIT 20
|
|
""")
|
|
for row in cursor.fetchall():
|
|
print(f" {row[0]}")
|
|
|
|
conn.close()
|