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.
40 lines
1.1 KiB
Python
40 lines
1.1 KiB
Python
import sqlite3
|
|
|
|
conn = sqlite3.connect('data/travel_rates_scraped.sqlite3')
|
|
cursor = conn.cursor()
|
|
|
|
print("Tables by source:\n")
|
|
cursor.execute("""
|
|
SELECT source, COUNT(*) as count
|
|
FROM raw_tables
|
|
GROUP BY source
|
|
""")
|
|
for row in cursor.fetchall():
|
|
print(f" {row[0]}: {row[1]} tables")
|
|
|
|
print("\nRate entries by source:\n")
|
|
cursor.execute("""
|
|
SELECT source, COUNT(*) as count,
|
|
SUM(CASE WHEN currency IS NULL THEN 1 ELSE 0 END) as null_count,
|
|
SUM(CASE WHEN currency IS NOT NULL THEN 1 ELSE 0 END) as has_currency_count
|
|
FROM rate_entries
|
|
GROUP BY source
|
|
""")
|
|
for row in cursor.fetchall():
|
|
print(f" {row[0]}: {row[1]} total | {row[2]} NULL | {row[3]} with currency")
|
|
|
|
print("\nSample titles by source:\n")
|
|
for source in ['international', 'domestic', 'accommodations']:
|
|
cursor.execute(f"""
|
|
SELECT title
|
|
FROM raw_tables
|
|
WHERE source = '{source}'
|
|
LIMIT 3
|
|
""")
|
|
print(f"\n{source}:")
|
|
for row in cursor.fetchall():
|
|
title = row[0] if row[0] else "NO TITLE"
|
|
print(f" {title[:80]}")
|
|
|
|
conn.close()
|