news-npr.yaml

vectara:
  corpus_id: 155
  customer_id: 1526022105
  reindex: false

crawling:
  crawler_type: rss

rss_crawler:
  source: npr
  rss_pages: [
    "https://feeds.npr.org/1001/rss.xml", "https://www.npr.org/rss/rss.php?id=1001", "https://www.npr.org/rss/rss.php?id=1032",
    "https://www.npr.org/rss/rss.php?id=1006", "https://www.npr.org/rss/rss.php?id=1128", "https://www.npr.org/rss/rss.php?id=1007",
    "https://www.npr.org/rss/rss.php?id=1019", "https://www.npr.org/rss/rss.php?id=1004", "https://www.npr.org/rss/rss.php?id=1003",
    "https://www.npr.org/rss/rss.php?id=1014", "https://www.npr.org/rss/rss.php?id=1013", "https://www.npr.org/rss/rss.php?id=1008",
    "https://www.npr.org/rss/rss.php?id=1101", "https://www.npr.org/rss/rss.php?id=1045"
  ]
  days_past: 30
  delay: 1
  extraction: playwright           # pdf or playwright