scrape.yml

name: >
  [MANUAL] Scrape Term

on:
  workflow_dispatch:
    inputs:
      term:
        required: true
        description: Term to scrape (e.g. sp2021)
      source:
        required: false
        default: sis.nyu.edu
        description: Source to scrape from (either schedge-v1 or sis.nyu.edu)

jobs:
  scrape:
    name: "Scrape ${{ github.event.inputs.term }} from ${{ github.event.inputs.source }}"
    runs-on: ubuntu-latest
    environment: admin
    permissions:
      contents: read

    steps:
      - name: Install Websocat
        run: wget https://github.com/vi/websocat/releases/download/v1.11.0/websocat.x86_64-unknown-linux-musl -O ./websocat

      - name: Update Permissions
        run: chmod +x ./websocat

      - name: Run Scrape on ${{ github.event.inputs.term }}
        run: >
          exec ./websocat
          "wss://nyu.a1liu.com/api/scrape/${{ github.event.inputs.term }}?source=${{ github.event.inputs.source }}"
          -n --basic-auth "${{ secrets.SCHEDGE_PASSWORD }}"
          | tee output.txt

      - name: Check for success
        run: |
          output=$(tail output.txt)
          if [[ "$output" =~ "Failed: ".* ]]; then
            echo "Scraping failed"
            exit 1
          fi