Skip to content

Arxiv Paper Crawler

Arxiv Paper Crawler #5

Workflow file for this run

name: Arxiv Paper Crawler
on:
schedule:
- cron: '0 12 */1 * *' # Runs at UTC 12:00, every 2 days. --> UTC+8 20:00
workflow_dispatch:
# A workflow run is made up of one or more jobs that can run sequentially or in parallel
jobs:
crawl:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v3
- name: Setup Python
uses: actions/setup-python@v4
with:
python-version: '3.x'
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install requests beautifulsoup4 pytz
- name: Run crawler and update arxiv.md
run: |
python tools/paper.py
- name: Commit changes
run: |
git config --local user.name "zhixin612"
git config --local user.email "zhao612@tju.edu.cn"
git commit -a -m "Update daily arxiv papers" || echo "No changes to commit"
git push
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}