Add Python web scraper for NJC travel rates with currency extraction

- 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.
This commit is contained in:
2026-01-13 09:21:43 -05:00
commit 15094ac94b
84 changed files with 19859 additions and 0 deletions

View File

@@ -0,0 +1,61 @@
"""Test currency extraction step by step"""
import sqlite3
import re
def _extract_currency_from_title(title):
"""Extract currency code from table title like 'Albania - Currency: Euro (EUR)'"""
if not title:
return None
# Pattern: "Currency: [Name] ([CODE])"
match = re.search(r"Currency:\s*[^(]+\(([A-Z]{3})\)", title)
if match:
return match.group(1)
return None
conn = sqlite3.connect('data/travel_rates_scraped.sqlite3')
cursor = conn.cursor()
print("Testing currency extraction from stored titles:\n")
# Get Argentina table title
cursor.execute("""
SELECT title
FROM raw_tables
WHERE title LIKE '%Argentina%'
""")
row = cursor.fetchone()
if row:
title = row[0]
print(f"Argentina Title: {title}")
currency = _extract_currency_from_title(title)
print(f"Extracted Currency: {currency}")
# Get Albania table title
cursor.execute("""
SELECT title
FROM raw_tables
WHERE title LIKE '%Albania%'
""")
row = cursor.fetchone()
if row:
title = row[0]
print(f"\nAlbania Title: {title}")
currency = _extract_currency_from_title(title)
print(f"Extracted Currency: {currency}")
# Check what entries we actually have
cursor.execute("""
SELECT COUNT(*)
FROM rate_entries
WHERE currency IS NOT NULL
""")
print(f"\nTotal entries with currency: {cursor.fetchone()[0]}")
cursor.execute("""
SELECT COUNT(*)
FROM rate_entries
WHERE currency IS NULL
""")
print(f"Total entries WITHOUT currency: {cursor.fetchone()[0]}")
conn.close()