mirror of
https://github.com/mblanke/Gov_Travel_App.git
synced 2026-03-01 14:10:22 -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:
33
scripts/test_scraper.py
Normal file
33
scripts/test_scraper.py
Normal file
@@ -0,0 +1,33 @@
|
||||
"""Test the scraper extract_rate_entries function with debug output"""
|
||||
import sys
|
||||
sys.path.insert(0, 'src')
|
||||
|
||||
from gov_travel.scrapers import SourceConfig, scrape_tables_from_source, extract_rate_entries
|
||||
|
||||
# Create a test source config
|
||||
source = SourceConfig(name="international", url="https://www.njc-cnm.gc.ca/directive/app_d.php?lang=en")
|
||||
|
||||
# Get just the first few tables
|
||||
print("Fetching tables...")
|
||||
tables = scrape_tables_from_source(source)
|
||||
print(f"Got {len(tables)} tables")
|
||||
|
||||
# Check first table
|
||||
first_table = tables[0]
|
||||
print(f"\nFirst table:")
|
||||
print(f" Index: {first_table['table_index']}")
|
||||
print(f" Title: {first_table['title']}")
|
||||
print(f" Data rows: {len(first_table['data'])}")
|
||||
|
||||
# Extract rate entries from just first table
|
||||
print("\nExtracting rate entries from first table...")
|
||||
entries = extract_rate_entries(source, [first_table])
|
||||
print(f"Got {len(entries)} entries")
|
||||
|
||||
if entries:
|
||||
print(f"\nFirst entry:")
|
||||
print(f" Country: {entries[0]['country']}")
|
||||
print(f" City: {entries[0]['city']}")
|
||||
print(f" Currency: {entries[0]['currency']}")
|
||||
print(f" Rate Type: {entries[0]['rate_type']}")
|
||||
print(f" Rate Amount: {entries[0]['rate_amount']}")
|
||||
Reference in New Issue
Block a user