Skip to content

Update scraping

Update scraping #1301

Workflow file for this run

name: Update scraping
on:
schedule:
# 7am UTC = 9am CET, 3am EDT, 0am PDT − should be light hours globally for WikiCFP.
- cron: '0 7 * * *'
workflow_dispatch:
jobs:
update:
name: Update scraping
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v1
- name: Install dependencies
run: |
python3 -m pip install -r ./requirements.txt
git config --global user.email "github-actions[bot]@users.noreply.github.com"
git config --global user.name "github-actions[bot]"
- name: Do the scraping
run: |
# Takes ~3h50 with 2.5s delay, limit for github actions is 6h.
# wikicfp recommends 5s delay but with 4s the process already would last est. 6h09.
# Alternately 3s (est. 4h37) or 3.5s (est. 5h23)?
(( $RANDOM < 32768 / 30 )) && python3 ./updater.py --no-cache --delay 2.5 core | cat
(( $RANDOM < 32768 / 30 )) && python3 ./updater.py --no-cache ggs | cat
python3 ./updater.py --no-cache --delay 2.5 cfps | cat
- name: Push to GitHub
run: |
git add core.csv cfp.json parsing_errors.txt
git commit -m "Update scraping $(date --rfc-3339=date)"
git push https://${TOKEN}@github.com/${GITHUB_REPOSITORY} HEAD:master
env:
TOKEN: ${{ secrets.CORE_CFP_PUSHER }}