Delete openalex.py

openalex.py

@@ -1,88 +0,0 @@
-"""
-OpenAlex enrichment — journal metadata + peer percentile calculation.
-Free API, no key required. Uses polite pool with mailto header.
-"""
-import httpx, asyncio
-from typing import Optional
-
-UA = "ResearchNavigator/1.0 (mailto:library@ku.ac.ae)"
-BASE = "https://api.openalex.org"
-
-def _norm_issn(raw: str) -> Optional[str]:
-    if not raw: return None
-    d = raw.strip().upper().replace(" ","").replace("-","")
-    if len(d) == 8:
-        return f"{d[:4]}-{d[4:]}"
-    return None
-
-async def enrich_journal(name: str, issn: Optional[str]) -> Optional[dict]:
-    try:
-        async with httpx.AsyncClient(timeout=8.0) as client:
-            if issn:
-                clean = _norm_issn(issn) or issn.strip()
-                r = await client.get(f"{BASE}/sources/issn:{clean}", headers={"User-Agent": UA})
-            else:
-                r = await client.get(f"{BASE}/sources", params={"search": name, "per_page": 1}, headers={"User-Agent": UA})
-            if not r.is_success: return None
-            d = r.json()
-            s = d if issn else (d.get("results") or [None])[0]
-            if not s: return None
-            return {
-                "openalex_id":           s.get("id"),
-                "display_name":          s.get("display_name"),
-                "issn_l":                s.get("issn_l"),
-                "issns":                 s.get("issn", []),
-                "host_organization":     s.get("host_organization_name"),
-                "is_oa":                 s.get("is_oa"),
-                "is_in_doaj":            s.get("is_in_doaj"),
-                "works_count":           s.get("works_count"),
-                "cited_by_count":        s.get("cited_by_count"),
-                "h_index":               (s.get("summary_stats") or {}).get("h_index"),
-                "two_yr_mean_citedness": (s.get("summary_stats") or {}).get("2yr_mean_citedness"),
-                "homepage_url":          s.get("homepage_url"),
-                "top_concept":           ((s.get("x_concepts") or [{}])[0]).get("display_name"),
-                "top_concept_id":        ((s.get("x_concepts") or [{}])[0]).get("id"),
-            }
-    except Exception as e:
-        print(f"[OpenAlex] enrich error for {name}: {e}")
-        return None
-
-async def compute_percentile(openalex: dict) -> Optional[dict]:
-    try:
-        if not openalex or not openalex.get("top_concept_id"): return None
-        val = openalex.get("two_yr_mean_citedness")
-        if val is None: return None
-        concept_id = str(openalex["top_concept_id"]).split("/")[-1]
-        async with httpx.AsyncClient(timeout=10.0) as client:
-            r = await client.get(
-                f"{BASE}/sources",
-                params={"filter": f"concepts.id:{concept_id},type:journal",
-                        "per_page": 200, "sort": "summary_stats.2yr_mean_citedness:desc"},
-                headers={"User-Agent": UA}
-            )
-            if not r.is_success: return None
-            peers = [s.get("summary_stats", {}).get("2yr_mean_citedness")
-                     for s in r.json().get("results", [])]
-            peers = [v for v in peers if isinstance(v, (int, float))]
-            if len(peers) < 10: return None
-            below = sum(1 for v in peers if v < val)
-            pct = round(below / len(peers) * 100)
-            q = "Q1" if pct >= 75 else "Q2" if pct >= 50 else "Q3" if pct >= 25 else "Q4"
-            return {"percentile": pct, "quartile": q,
-                    "peer_count": len(peers), "concept": openalex.get("top_concept")}
-    except Exception as e:
-        print(f"[OpenAlex] percentile error: {e}")
-        return None
-
-async def enrich_all(journals: list) -> list:
-    """Enrich a list of journal dicts in parallel."""
-    async def _enrich_one(j: dict) -> dict:
-        oa = await enrich_journal(j.get("name",""), j.get("issn"))
-        pct = await compute_percentile(oa) if oa else None
-        j["openalex"] = oa
-        j["oa_percentile"] = pct
-        # Supplement ISSN from OpenAlex if missing
-        if not j.get("issn") and oa:
-            j["issn"] = oa.get("issn_l") or (oa.get("issns") or [None])[0]
-        return j
-    return list(await asyncio.gather(*[_enrich_one(j) for j in journals]))