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.
29 lines
630 B
Python
29 lines
630 B
Python
import sqlite3
|
|
|
|
conn = sqlite3.connect('data/travel_rates_scraped.sqlite3')
|
|
cursor = conn.cursor()
|
|
|
|
# Get a raw table with title
|
|
cursor.execute("""
|
|
SELECT title, data
|
|
FROM raw_tables
|
|
WHERE title LIKE '%Argentina%'
|
|
LIMIT 1
|
|
""")
|
|
row = cursor.fetchone()
|
|
print(f"Title: {row[0]}")
|
|
print(f"Data length: {len(row[1])} chars")
|
|
|
|
# Now check the actual rate_entries for Argentina
|
|
cursor.execute("""
|
|
SELECT country, city, rate_type, currency, rate_amount
|
|
FROM rate_entries
|
|
WHERE country LIKE '%Argentina%'
|
|
LIMIT 3
|
|
""")
|
|
print("\nRate Entries:")
|
|
for r in cursor.fetchall():
|
|
print(f" {r}")
|
|
|
|
conn.close()
|