Skip to content

multiple crawl files #1

multiple crawl files

multiple crawl files #1

Workflow file for this run

name: Old Terms Crawling
on:
push:
branches:
- crawler
schedule:
- cron: "0 0 * * 1"
concurrency:
group: crawling
jobs:
crawling:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v2
with:
ref: crawler
persist-credentials: false
- name: Checkout data
uses: actions/checkout@v2
with:
persist-credentials: false
ref: crawler-gh-pages
path: ./data
- name: Install
run: yarn install --frozen-lockfile
- name: Pip
uses: actions/setup-python@v4
with:
python-version: '3.9'
cache: 'pip' # caching pip dependencies
- name: Pip Install
run: pip install -r requirements.txt
- name: Crawling
run: yarn start
env:
LOG_FORMAT: json
NUM_TERMS: 16
ALWAYS_SCRAPE_CURRENT_TERM: 1
DETAILS_CONCURRENCY: 256
DATA_FOLDER: ./data
NODE_EXTRA_CA_CERTS: ${{ github.workspace }}/intermediate.pem
- name: Revision
run: python ./src/Revise.py
- name: Upload
uses: JamesIves/github-pages-deploy-action@releases/v4
with:
branch: crawler-gh-pages
folder: ./data
single-commit: true