Auto-submit IndexNow on deploy when the URL set changes (#130)

Hook the production deploy (deploy/deploy.sh) to ping IndexNow after the health
check passes, so new/changed pages reach Bing/DuckDuckGo/Yandex without a manual
run. Best-effort — wrapped so it can never fail a deploy — and it sources
/etc/thermograph.env so its key matches the one the running service serves.

To avoid re-blasting ~14k URLs on every code push, indexnow.py gains a
--if-changed mode gated by a signature of the URL set (persisted to
data/indexnow_state.txt): code-only deploys skip; a deploy that adds or removes a
city submits. `make indexnow` still forces a full submit.

indexnow.py

@@ -16,6 +16,7 @@ Usage (run after a content rebuild, or once to seed a fresh site):
     cd backend && python indexnow.py https://thermograph.org
     # or:  make indexnow URL=https://thermograph.org
 """
+import hashlib
 import logging
 import os
 import secrets
@@ -28,6 +29,7 @@ log = logging.getLogger("thermograph.indexnow")
 
 _DATA_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "data"))
 _KEY_PATH = os.environ.get("THERMOGRAPH_INDEXNOW_KEY_FILE") or os.path.join(_DATA_DIR, "indexnow_key.txt")
+_STATE_PATH = os.environ.get("THERMOGRAPH_INDEXNOW_STATE_FILE") or os.path.join(_DATA_DIR, "indexnow_state.txt")
 _ENDPOINT = "https://api.indexnow.org/indexnow"   # a shared endpoint; it fans out to all participants
 _BATCH = 10000                                    # IndexNow's max URLs per request
 
@@ -104,13 +106,51 @@ def submit_all(site_base_url: str, **kw) -> dict:
                   key_location=f"{site}/{key()}.txt", **kw)
 
 
+def url_signature() -> str:
+    """A stable fingerprint of the indexable URL set — changes only when pages are
+    added or removed (e.g. a new city), not on code-only deploys. Used to skip
+    resubmitting an unchanged set (see the --if-changed CLI flag)."""
+    import content
+    return hashlib.sha1("\n".join(content.public_paths()).encode()).hexdigest()
+
+
+def _read_state() -> str:
+    try:
+        with open(_STATE_PATH, encoding="utf-8") as f:
+            return f.read().strip()
+    except OSError:
+        return ""
+
+
+def _write_state(sig: str) -> None:
+    try:
+        os.makedirs(_DATA_DIR, exist_ok=True)
+        with open(_STATE_PATH, "w", encoding="utf-8") as f:
+            f.write(sig)
+    except OSError:
+        log.warning("could not persist IndexNow state to %s", _STATE_PATH)
+
+
 if __name__ == "__main__":
     import sys
 
-    arg = sys.argv[1].strip() if len(sys.argv) > 1 else ""
+    # Usage: indexnow.py [--if-changed] [BASE_URL]
-    base = arg or os.environ.get("THERMOGRAPH_BASE_URL", "https://thermograph.org")
+    #   --if-changed  submit only when the URL set changed since the last run
+    #                 (used by the deploy hook so code-only deploys don't resubmit).
+    argv = sys.argv[1:]
+    if_changed = "--if-changed" in argv
+    positional = [a for a in argv if not a.startswith("-") and a.strip()]
+    base = (positional[0] if positional else "") or os.environ.get("THERMOGRAPH_BASE_URL", "https://thermograph.org")
     logging.basicConfig(level=logging.INFO)
+
+    sig = url_signature()
+    if if_changed and sig == _read_state():
+        print("IndexNow: URL set unchanged since last submission — skipping.")
+        sys.exit(0)
+
     print(f"IndexNow key: {key()}  (served at {base.rstrip('/')}/{key()}.txt)")
     result = submit_all(base)
     print(f"Submitted {result['submitted']}/{result['total']} URLs "
           f"in {result['batches']} batch(es); statuses={result['statuses']}")
+    if result["total"] and result["submitted"] == result["total"]:
+        _write_state(sig)   # only remember a fully-successful submission

tests/test_content.py

@@ -231,6 +231,16 @@ def test_indexnow_submit_all_builds_payload(monkeypatch):
     assert all(len(c[1]["urlList"]) <= 10000 for c in calls)   # batched under the IndexNow cap
 
 
+def test_indexnow_if_changed_state(monkeypatch, tmp_path):
+    import indexnow
+    monkeypatch.setattr(indexnow, "_STATE_PATH", str(tmp_path / "state.txt"))
+    sig = indexnow.url_signature()
+    assert len(sig) == 40 and sig == indexnow.url_signature()   # stable sha1 of the URL set
+    assert indexnow._read_state() == ""                         # first deploy → would submit
+    indexnow._write_state(sig)
+    assert indexnow._read_state() == sig                        # unchanged → deploy would skip
+
+
 def test_search_verification_meta(client, monkeypatch):
     monkeypatch.setenv("THERMOGRAPH_GOOGLE_VERIFY", "gtok123")
     monkeypatch.setenv("THERMOGRAPH_BING_VERIFY", "btok456")