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/ol.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+"""Open Library search — the "English RSL" for author works lists.
+
+Usage: tools/ol.py "Neumann, Erich" [title_words] [limit]
+
+Output: one line per title: title | years | languages | sample publishers | sample ISBN.
+Open Library aggregates all editions of a work into one doc (author_name, publish_year[],
+language[], publisher[], isbn[]) — i.e. it answers "what did this EN author write" and
+"which languages/years exist" — the missing half of our RSL (RU-only) pipeline.
+NO RU editions are indexed (checked: language=rus → 0 for known RU books) — RU hunting
+still goes through RSL/libgen/flibusta.
+"""
+import json, sys, time, urllib.parse, urllib.request
+
+UA = "research-tools/1.0 (jung booklist research; contact: dmitry@kokorin.org)"
+
+def ol_search(q, fields="title,author_name,publish_year,language,publisher,isbn,original_title", limit=40):
+    url = "https://openlibrary.org/search.json?" + urllib.parse.urlencode({
+        "q": q, "fields": fields, "limit": min(limit, 100)})
+    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__)
+    first = sys.argv[1]
+    # raw query passthrough (e.g. 'title:"..."'); else treat as author name
+    if first.startswith(("title:", "subject:", "isbn:", "publisher:")):
+        q = " ".join(sys.argv[1:-1]) if sys.argv[-1].isdigit() else " ".join(sys.argv[1:])
+    else:
+        rest = " ".join(sys.argv[2:-1]) if sys.argv[-1].isdigit() else " ".join(sys.argv[2:])
+        q = f"author:{first}" + (f" title:{rest}" if rest else "")
+    limit = int(sys.argv[-1]) if sys.argv[-1].isdigit() else 40
+    d = ol_search(q, limit=limit)
+    print(f"numFound: {d.get('numFound')}")
+    for doc in d.get("docs", []):
+        years = sorted(set(doc.get("publish_year") or []))
+        ys = f"{years[0]}-{years[-1]}" if len(years) > 1 else (str(years[0]) if years else "?")
+        langs = ",".join(doc.get("language") or [])
+        pubs = sorted(set(p[:30] for p in (doc.get("publisher") or [])))[:3]
+        isbns = (doc.get("isbn") or [])[:2]
+        ot = doc.get("original_title") or ""
+        an = ", ".join(doc.get("author_name") or [])
+        print(f"- {doc.get('title')} | {an} | {ys} | {langs} | {'; '.join(pubs)} | {isbns} | {doc.get('key','')} | {ot}")
+    time.sleep(1)
+
+if __name__ == "__main__":
+    main()