EN-side research pillars: tools/ol.py (Open Library) + tools/wd.py (Wikidata), Google Books ISBN pattern, archive.org verification, HSE shop-directory + NikBook/Skifiya/beta2alpha sources, workflow v2 (full names first, reverse publisher sweep, community lists, content verification gate); full EN author names resolved for all 39 items (AUTHORS-EN.md); CONTEXT round 3 (Neumann cogito finds, 1959 disambiguation)

tools/wd.py

@@ -0,0 +1,51 @@
+#!/usr/bin/env python3
+"""Wikidata identity check — EN author -> life dates + OFFICIAL RU name.
+
+Usage: tools/wd.py "Erich Neumann" [top]
+
+Resolves the Q-entity, prints birth/death (P569/P570), EN/DE/RU labels, RU aliases
+(P725-equivalent via aliases block), and the P50 works list (often sparse).
+Primary value: (1) disambiguation via life dates, (2) the canonical RU label — the
+single most reliable RU spelling for RSL/libgen queries.
+"""
+import json, sys, urllib.parse, urllib.request
+
+UA = "research-tools/1.0 (jung booklist research; contact: dmitry@kokorin.org)"
+
+def api(params):
+    url = "https://www.wikidata.org/w/api.php?" + urllib.parse.urlencode(params)
+    req = urllib.request.Request(url, headers={"User-Agent": UA})
+    with urllib.request.urlopen(req, timeout=40) as r:
+        return json.load(r)
+
+def main():
+    if len(sys.argv) < 2:
+        sys.exit(__doc__)
+    name = " ".join(sys.argv[1:-1]) if len(sys.argv) > 2 and sys.argv[-1].isdigit() else " ".join(sys.argv[1:])
+    top = int(sys.argv[-1]) if len(sys.argv) > 2 and sys.argv[-1].isdigit() else 3
+    d = api({"action": "wbsearchentities", "search": name, "language": "en",
+             "limit": top, "format": "json"})
+    for r in d.get("search", []):
+        qid = r["id"]
+        label = r.get("label")
+        desc = (r.get("description") or "")[:100]
+        try:
+            ed = api({"action": "wbgetentities", "ids": qid, "format": "json"})
+            ent = ed["entities"][qid]
+            c = ent.get("claims", {})
+            bd = c.get("P569", [{}])[0].get("mainsnak", {}).get("datavalue", {}).get("value", {}).get("time", "?")
+            dd = c.get("P570", [{}])[0].get("mainsnak", {}).get("datavalue", {}).get("value", {}).get("time", "?")
+            labels = {k: v["value"] for k, v in ent.get("labels", {}).items() if k in ("en", "de", "ru")}
+            ru_al = [a["value"] for a in ent.get("aliases", {}).get("ru", [])]
+            works = [w["mainsnak"]["datavalue"]["value"].get("id") for w in c.get("P50", [])]
+            print(f"{qid} | {label} | {desc}")
+            print(f"    born/died: {bd} / {dd}")
+            print(f"    labels: {labels}")
+            if ru_al: print(f"    RU aliases: {ru_al}")
+            if works: print(f"    P50 works: {works[:15]}")
+        except Exception as e:
+            print(f"{qid} | {label} | (entity fetch failed: {e})")
+        print()
+
+if __name__ == "__main__":
+    main()