mirror of
https://github.com/feder-cr/Jobs_Applier_AI_Agent.git
synced 2026-11-07 02:35:57 -10:00
Federico EliaandClaude Fable 5.1
f8d7093c5a
The biggest source, jobhive, publishes around 15:00 UTC and the new-grad lists commit every hour; the 04:23 build read them up to a day late. Cron 23 */5 * * *, off the top of the hour; timeout 200 minutes so a hung run does not take the next slot; six dated releases kept, about thirty hours. Texts say five hours, and the search log gives the build's hour. Co-Authored-By: Claude Fable 5.1 <[email protected]>
37 lines
1.2 KiB
YAML
37 lines
1.2 KiB
YAML
name: job database
|
|
|
|
# Every five hours: read the public job databases, merge them and publish the result as a release, which AIHawk reads when it searches.
|
|
# Five hours because the biggest source, jobhive, publishes around 15:00 UTC and the small new-grad lists every hour; a daily build read them up to a day late.
|
|
# Minute 23 because GitHub delays schedules at the top of the hour.
|
|
# Users never scrape anything.
|
|
on:
|
|
schedule:
|
|
- cron: "23 */5 * * *"
|
|
workflow_dispatch:
|
|
|
|
permissions:
|
|
contents: write
|
|
|
|
concurrency:
|
|
group: job-database
|
|
cancel-in-progress: false
|
|
|
|
jobs:
|
|
build:
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: 200 # shorter than the five hours to the next run, so a hung build does not take its slot
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
- uses: actions/setup-python@v5
|
|
with:
|
|
python-version: "3.12"
|
|
- name: room on disk
|
|
run: |
|
|
sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
|
|
df -h /
|
|
- run: pip install duckdb
|
|
- run: python pipeline/build.py --out work
|
|
- run: python pipeline/publish.py --out work/out --repo "$GITHUB_REPOSITORY"
|
|
env:
|
|
GH_TOKEN: ${{ github.token }}
|