wikidata-enrich: add --byCredits to rank people by credit count (target high-recall enrichment)

40aa91fc6b755642fe9e614ebd3ae1ed44769014 · 2026-05-12 15:30:02 -0700 · SteveStudio2

Files touched

M scrapers/wikidata-enrich.js

Diff

commit 40aa91fc6b755642fe9e614ebd3ae1ed44769014
Author: SteveStudio2 <stevestudio2@SteveStacStudio.lan>
Date:   Tue May 12 15:30:02 2026 -0700

    wikidata-enrich: add --byCredits to rank people by credit count (target high-recall enrichment)
---
 scrapers/wikidata-enrich.js | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/scrapers/wikidata-enrich.js b/scrapers/wikidata-enrich.js
index 5a8d42e..30fdbf4 100644
--- a/scrapers/wikidata-enrich.js
+++ b/scrapers/wikidata-enrich.js
@@ -33,6 +33,7 @@ const LIMIT       = parseInt(args.limit || '1000', 10);
 const BATCH       = Math.min(parseInt(args['batch-size'] || '80', 10), 100);
 const SLEEP_MS    = parseInt(args.sleep || '1200', 10);
 const PRIORITY    = !!args.priority;
+const BY_CREDITS  = !!args.byCredits;   // rank people by credit count DESC (most-credited first)
 const DRY         = !!args.dry;
 const UA          = 'AsSeenInMovies/0.1 (https://asseeninmovies.com; steve@designerwallcoverings.com)';
 
@@ -162,7 +163,17 @@ async function enrichMovies() {
 async function enrichPeople() {
   const priorityClause = PRIORITY ? `
     AND p.id IN (SELECT DISTINCT person_id FROM asim_credits)` : '';
-  const sel = await pool.query(`
+  // BY_CREDITS = join credit-count and rank desc — most-credited untouched people first.
+  // Hit rate on bg1/bg2 random ordering was ~7-11%; credit-ranked should jump
+  // because famous actors have wikipedia articles.
+  const sel = BY_CREDITS ? await pool.query(`
+    SELECT p.id, p.imdb_id
+      FROM asim_people p
+      JOIN (SELECT person_id, count(*) AS c FROM asim_credits GROUP BY person_id) cc
+        ON cc.person_id = p.id
+     WHERE p.imdb_id LIKE 'nm%' AND p.wikidata_id IS NULL
+     ORDER BY cc.c DESC
+     LIMIT $1`, [LIMIT]) : await pool.query(`
     SELECT p.id, p.imdb_id
       FROM asim_people p
      WHERE p.imdb_id LIKE 'nm%' AND p.wikidata_id IS NULL ${priorityClause}

← bdd362c feat(asseeninmovies): /movies + /people paginated index page · back to AsSeenInMovies · scaffold wikidata-commons-fallback.js — search Commons for h 96cf4db →