link-check.yml

name: Link check

on:
  pull_request:
    paths:
      - README.rst
      - .github/workflows/link-check.yml
  schedule:
    - cron: "17 6 * * 1"
  workflow_dispatch:

permissions:
  contents: read

jobs:
  lychee:
    runs-on: ubuntu-latest
    steps:
      - name: Check out repository
        uses: actions/checkout@v4

      - name: Check README links
        uses: lycheeverse/lychee-action@v2.8.0
        with:
          args: >-
            --accept 200,202,403,429
            --exclude 'http://dfreelon\.org/2012/02/11/arab-spring-twitter-data-now-available-sort-of/'
            --exclude 'http://covid19research\.site/geo-tagged_twitter_datasets/'
            --exclude 'https://revealproject\.eu/geoparse-benchmark-open-dataset/'
            --exclude 'http://socialcomputing\.asu\.edu/datasets/Twitter'
            --exclude 'http://an\.kaist\.ac\.kr/traces/WWW2010\.html'
            --exclude 'http://mir\.dcs\.gla\.ac\.uk/resources/'
            --exclude 'http://ilpubs\.stanford\.edu:8090/984/1/paper-memeshapes\.pdf'
            --exclude 'https://archive\.org/details/2011-05-calufa-twitter-sql'
            --exclude 'https://ankeshanand\.carto\.com/tables/fifatweets/public'
            --exclude 'http://followthehashtag\.com/datasets/'
            --exclude 'https://github\.com/shaypal5/speks'
            --exclude 'http://wwbp\.org/papers/emnlp2014_developingLexica\.pdf'
            --exclude 'http://ww1\.gbsheli\.com/2009/03/twitgraph-en\.html'
            --exclude 'https://twitter\.com/'
            --exclude 'https://x\.com/'
            README.rst
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}