Kalimati Data Pipeline #77

	name: Kalimati Data Pipeline

	on:
	schedule:
	- cron: '55 9 * * *' # Runs at 9:55 AM UTC, which is 3:40 PM Nepal Time daily
	workflow_dispatch:

	jobs:
	run-scraper:
	runs-on: ubuntu-latest

	steps:
	- name: Checkout repository
	uses: actions/checkout@v2

	- name: Set up Python
	uses: actions/setup-python@v2
	with:
	python-version: '3.x'

	- name: Install dependencies
	run: \|
	python -m pip install --upgrade pip
	pip install -r requirements.txt
	pip install kaggle # Install Kaggle API

	- name: Set up Kaggle credentials
	env:
	KAGGLE_USERNAME: ${{ secrets.KAGGLEUSERNAME }}
	KAGGLE_KEY: ${{ secrets.KAGGLEKEY }}
	run: \|
	mkdir -p ~/.kaggle
	echo "{\"username\":\"$KAGGLE_USERNAME\",\"key\":\"$KAGGLE_KEY\"}" > ~/.kaggle/kaggle.json
	chmod 600 ~/.kaggle/kaggle.json

	- name: Run the scraper
	run: python scrape.py

	- name: Commit and Push Updated Dataset to GitHub
	env:
	GITHUB_TOKEN: ${{ secrets.GITHUBTOKEN }}
	run: \|
	git config --local user.name "github-actions[bot]"
	git config --local user.email "github-actions[bot]@users.noreply.github.com"
	git add data/
	git commit -m "Update dataset in data/ folder"
	git push origin main # Specify the branch to push to

	- name: Upload data to Kaggle
	run: python kaggleUpdate.py

Provide feedback