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.
36 lines
1.2 KiB
Python
36 lines
1.2 KiB
Python
import sqlite3
|
|
import json
|
|
|
|
conn = sqlite3.connect('data/travel_rates_scraped.sqlite3')
|
|
|
|
print('\n=== RAW TABLE INSPECTION ===\n')
|
|
|
|
# Check first few raw tables
|
|
for row in conn.execute('SELECT source, source_url, table_index, title, data_json FROM raw_tables LIMIT 5').fetchall():
|
|
print(f'\nSource: {row[0]}')
|
|
print(f'URL: {row[1]}')
|
|
print(f'Table Index: {row[2]}')
|
|
print(f'Title: {row[3]}')
|
|
|
|
data = json.loads(row[4])
|
|
print(f'Columns: {list(data[0].keys()) if data else "No data"}')
|
|
print(f'First row sample: {data[0] if data else "No data"}')
|
|
print('-' * 80)
|
|
|
|
# Check specific Argentina table
|
|
print('\n\n=== ARGENTINA RAW DATA ===\n')
|
|
for row in conn.execute('SELECT source, title, data_json FROM raw_tables WHERE data_json LIKE "%Argentina%"').fetchone() or []:
|
|
print(f'Source: {row[0]}')
|
|
print(f'Title: {row[1]}')
|
|
data = json.loads(row[2])
|
|
if data:
|
|
# Find Argentina entry
|
|
for entry in data:
|
|
if 'Argentina' in str(entry.values()):
|
|
print(f'\nArgentina entry columns: {entry.keys()}')
|
|
print(f'Argentina entry data: {entry}')
|
|
break
|
|
break
|
|
|
|
conn.close()
|