8643153954
Scraper loops with NEWS_SCRAPE_INTERVAL_S (default 10s after each crawl). Summarizer runs every NEWS_SUMMARIZE_INTERVAL_S (default 900) over the last 15 minutes of articles. Feed list replaced from the k8s scrapy-urls configmap (334 sources).
53 lines
1.6 KiB
Python
53 lines
1.6 KiB
Python
#!/usr/bin/env python3
|
|
"""Scheduler loop for the news scraper — crawl continuously.
|
|
|
|
As soon as one Scrapy pass finishes, wait NEWS_SCRAPE_INTERVAL_S seconds
|
|
and start the next. Two crawls never overlap (the loop is serial).
|
|
|
|
Env (all optional, 12-factor):
|
|
NEWS_SCRAPE_INTERVAL_S seconds between crawls (default 10)
|
|
NEWS_SCRAPE_RUN_ON_START "1" to crawl immediately on boot (default 1)
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import datetime
|
|
import logging
|
|
import os
|
|
import subprocess
|
|
import sys
|
|
import time
|
|
|
|
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(name)s: %(message)s")
|
|
logger = logging.getLogger("news.scraper")
|
|
|
|
INTERVAL_S = max(0, int(os.getenv("NEWS_SCRAPE_INTERVAL_S", "10")))
|
|
RUN_ON_START = os.getenv("NEWS_SCRAPE_RUN_ON_START", "1").lower() in ("1", "true", "yes")
|
|
|
|
CRAWL_CMD = ["scrapy", "crawl", "articles"]
|
|
|
|
|
|
def run_crawl() -> None:
|
|
logger.info("scrape starting at %s", datetime.datetime.now().isoformat(timespec="seconds"))
|
|
try:
|
|
proc = subprocess.run(CRAWL_CMD, cwd="/app")
|
|
logger.info("scrape finished rc=%s", proc.returncode)
|
|
except Exception: # noqa: BLE001 — keep the loop alive across failures
|
|
logger.exception("scrape failed")
|
|
|
|
|
|
def main() -> None:
|
|
logger.info(
|
|
"news scraper loop starting (interval_s=%s, run_on_start=%s)",
|
|
INTERVAL_S, RUN_ON_START,
|
|
)
|
|
if RUN_ON_START:
|
|
run_crawl()
|
|
while True:
|
|
logger.info("next scrape in %ss", INTERVAL_S)
|
|
time.sleep(INTERVAL_S)
|
|
run_crawl()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|