mirror of
https://github.com/mblanke/Gov_Travel_App.git
synced 2026-03-01 22:20:21 -05:00
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:
37
scripts/debug_argentina.py
Normal file
37
scripts/debug_argentina.py
Normal file
@@ -0,0 +1,37 @@
|
||||
"""Debug the scraper to see what currencies are being assigned"""
|
||||
import sys
|
||||
sys.path.insert(0, 'src')
|
||||
|
||||
from gov_travel.scrapers import SourceConfig, scrape_tables_from_source, extract_rate_entries
|
||||
|
||||
# Test international source with Argentina
|
||||
source = SourceConfig(name="international", url="https://www.njc-cnm.gc.ca/directive/app_d.php?lang=en")
|
||||
|
||||
print("Fetching tables...")
|
||||
tables = scrape_tables_from_source(source)
|
||||
|
||||
# Find Argentina table
|
||||
argentina_table = None
|
||||
for table in tables:
|
||||
if table['title'] and 'Argentina' in table['title']:
|
||||
argentina_table = table
|
||||
break
|
||||
|
||||
if argentina_table:
|
||||
print(f"\nArgentina Table:")
|
||||
print(f" Title: {argentina_table['title']}")
|
||||
print(f" Rows: {len(argentina_table['data'])}")
|
||||
|
||||
# Extract entries
|
||||
entries = extract_rate_entries(source, [argentina_table])
|
||||
print(f"\n Generated {len(entries)} entries")
|
||||
|
||||
if entries:
|
||||
# Show first few entries
|
||||
print(f"\n First 3 entries:")
|
||||
for i, entry in enumerate(entries[:3]):
|
||||
print(f" {i+1}. City: {entry['city']}, Type: {entry['rate_type']}, Amount: {entry['rate_amount']}, Currency: {entry['currency']}")
|
||||
|
||||
# Check unique currencies
|
||||
currencies = set(e['currency'] for e in entries)
|
||||
print(f"\n Unique currencies in Argentina entries: {currencies}")
|
||||
Reference in New Issue
Block a user