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.
26 lines
705 B
Python
26 lines
705 B
Python
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
|
|
|
|
# Test cases
|
|
test_titles = [
|
|
"Argentina - Currency: Argentine Peso (ARS)",
|
|
"Albania - Currency: Euro (EUR)",
|
|
"Afghanistan - Currency: US Dollar (USD)",
|
|
"Canada - Currency: Canadian Dollar (CAD)",
|
|
None,
|
|
"Some random text"
|
|
]
|
|
|
|
for title in test_titles:
|
|
result = _extract_currency_from_title(title)
|
|
print(f"{title!r} -> {result}")
|