Migrate site probes to github action

.github/workflows/probe.yml

@@ -0,0 +1,51 @@
+# Simple workflow for deploying static content to GitHub Pages
+name: Probe
+
+on:
+  # Runs on pushes targeting the default branch
+  push:
+    branches: [ "master" ]
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+  repository_dispatch:
+    types: [ probe-hn-sites ]
+
+  schedule:
+   - cron: "*/10 * * * *"
+
+# Allow one concurrent deployment
+concurrency:
+  group: probe-event-${{ github.event_name }}  # So UT won't be interrupted by cronjobs
+  cancel-in-progress: true # Avoid batch pending when one job hangs
+
+jobs:
+  # Single deploy job since we're just deploying
+  probe:
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Setup Python
+        uses: actions/[email protected]
+        with:
+          python-version: 3.9
+          cache: 'pip'
+
+      - name: Install Python Dependencies
+        run: pip install --upgrade -r requirements.txt
+
+      - name: Blog
+        run: python probe.py blog
+        if: ${{ always() }}
+
+      - name: HN Summary
+        run: python probe.py hn
+        if: ${{ always() }}
+
+      - name: HN Summary ZH
+        run: python probe.py hn-zh
+        if: ${{ always() }}

config.py

@@ -23,7 +23,7 @@
 logging.basicConfig(level=logging.DEBUG if DEBUG else logging.INFO,
                     format='%(asctime)s %(levelname)s [%(filename)s:%(lineno)d %(funcName)s] - %(message)s',
                     handlers=log_handlers)
-logger = logging.getLogger()
+logger = logging.getLogger(__name__)
 
 
 def int_env(name, default):

probe.py

@@ -0,0 +1,62 @@
+# coding: utf-8
+import argparse
+import logging
+import re
+from datetime import datetime, timedelta
+
+from page_content_extractor.http import session
+
+parser = argparse.ArgumentParser(description='Probe betacat.io sites')
+parser.add_argument("site", choices=['hn', 'hn-zh', 'blog'], help="Specify site to probe")
+args = parser.parse_args()
+logger = logging.getLogger(__name__)
+
+
+def probe_hn_summary():
+    url = 'https://hackernews.betacat.io/'
+    resp = session.get(url)
+    resp.raise_for_status()
+    body = resp.text
+
+    assert "Hacker News" in body, '"Hacker News" not in response'
+    assert body.count("OpenAI") > 5, "Too few OpenAI summaries, only got %d" % body.count("OpenAI")
+    logger.info(f'OpenAI summaries {body.count("OpenAI")} times')
+
+    pattern = r'Last updated: <span>(.*?)<\/span>'
+    matches = re.search(pattern, body)
+
+    time_updated_str = matches.group(1)
+    time_updated = datetime.strptime(time_updated_str, "%Y-%m-%d %H:%M:%S %Z")
+
+    current_time = datetime.utcnow()
+
+    assert current_time <= time_updated + timedelta(hours=1), "Haven't been updated for one hour, last update: " + time_updated_str
+
+
+def probe_hn_zh():
+    url = 'https://hackernews.betacat.io/zh.html'
+    resp = session.get(url)
+    resp.raise_for_status()
+    body = resp.text
+
+    assert '摘要' in body
+
+
+def probe_blog():
+    url = 'https://blog.betacat.io/'
+    resp = session.get(url)
+    resp.raise_for_status()
+    body = resp.text
+
+    assert '喵叔没话说' in body
+
+
+if __name__ == '__main__':
+    if args.site == 'blog':
+        probe_blog()
+    elif args.site == 'hn-zh':
+        probe_hn_zh()
+    elif args.site == 'hn':
+        probe_hn_summary()
+    else:
+        assert False