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:
22
pyproject.toml
Normal file
22
pyproject.toml
Normal file
@@ -0,0 +1,22 @@
|
||||
[build-system]
|
||||
requires = ["setuptools>=68", "wheel"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
name = "gov-travel"
|
||||
version = "0.1.0"
|
||||
description = "Scrape NJC travel rates into SQLite"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
dependencies = [
|
||||
"beautifulsoup4==4.12.3",
|
||||
"lxml==5.3.0",
|
||||
"pandas==2.2.3",
|
||||
"requests==2.32.3",
|
||||
]
|
||||
|
||||
[tool.setuptools]
|
||||
package-dir = {"" = "src"}
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
where = ["src"]
|
||||
Reference in New Issue
Block a user