scopus.py

# scopus_simple_extract.py
# Extrae resultados Scopus por AF-ID y exporta UN CSV "amigable" con campos básicos.
# NO pide Abstract, Autores, Keywords, Funding, Conference, etc.

import time
import argparse
import urllib.parse as urlparse
from typing import Dict, List, Optional
import requests
import numpy as np
import pandas as pd

BASE_URL_SEARCH = "https://api.elsevier.com/content/search/scopus"

# -------------------------
# HTTP utilidades
# -------------------------
def build_headers(api_key: str, insttoken: Optional[str] = None) -> Dict[str, str]:
    h = {"Accept": "application/json", "X-ELS-APIKey": api_key.strip()}
    if insttoken:
        h["X-ELS-Insttoken"] = insttoken.strip()
    return h

def get_json(session: requests.Session, url: str, params: Dict[str, str],
             headers: Dict[str, str], max_retries: int = 6, sleep_base: float = 0.75) -> Dict:
    """
    GET con reintentos para 429/5xx. Si 401 por Insttoken mal pareado, reintenta SIN Insttoken.
    """
    last_exc = None
    tried_without_token = False

    for t in range(max_retries + 1):
        try:
            r = session.get(url, params=params, headers=headers, timeout=90)
        except Exception as ex:
            last_exc = ex
            time.sleep((2 ** t) * sleep_base)
            continue

        if r.status_code in (429, 500, 502, 503, 504):
            time.sleep((2 ** t) * sleep_base)
            continue

        if r.status_code == 401:
            # intentar una sola vez sin Insttoken si el problema es token no asociado
            try:
                j = r.json()
            except Exception:
                j = {}
            if ("Institution Token is not associated with API Key" in str(j)
                and not tried_without_token
                and "X-ELS-Insttoken" in headers):
                tried_without_token = True
                h2 = dict(headers)
                h2.pop("X-ELS-Insttoken", None)
                r2 = session.get(url, params=params, headers=h2, timeout=90)
                if r2.ok:
                    try:
                        return r2.json()
                    except Exception:
                        raise RuntimeError("La respuesta no es JSON decodificable.")
                else:
                    try:
                        j2 = r2.json()
                    except Exception:
                        j2 = {}
                    raise RuntimeError(f"HTTP {r2.status_code} – {j2 or r2.text}")

        if not r.ok:
            try:
                j = r.json()
            except Exception:
                j = {}
            raise RuntimeError(f"HTTP {r.status_code} – {j or r.text}")

        try:
            return r.json()
        except Exception:
            raise RuntimeError("La respuesta no es JSON decodificable.")

    if last_exc:
        raise RuntimeError(f"Error de red persistente: {last_exc}")
    raise RuntimeError("No se obtuvo respuesta estable tras varios reintentos.")

# -------------------------
# Paginación Search API
# -------------------------
def extract_by_year_cursor(session: requests.Session, headers: Dict[str, str],
                           afid: str, year: int, page_size: int, view: str) -> List[Dict]:
    params = {
        "query": f"AF-ID({afid}) AND PUBYEAR = {year}",
        "view": view,
        "count": str(page_size),
        "cursor": "*",
    }
    entries: List[Dict] = []
    while True:
        j = get_json(session, BASE_URL_SEARCH, params, headers)
        chunk = j.get("search-results", {}).get("entry", []) or []
        if chunk:
            entries.extend(chunk)

        next_token = None
        for ln in j.get("search-results", {}).get("link", []) or []:
            if ln.get("@ref") == "next":
                href = ln.get("@href")
                if href:
                    q = urlparse.urlparse(href).query
                    qd = urlparse.parse_qs(q)
                    next_token = (qd.get("cursor") or [None])[0]
                break
        if not next_token:
            break
        params["cursor"] = next_token
    return entries

def extract_by_year_startcount(session: requests.Session, headers: Dict[str, str],
                               afid: str, year: int, page_size: int, view: str,
                               hard_limit: int = 20000) -> List[Dict]:
    entries: List[Dict] = []
    start = 0
    while start < hard_limit:
        params = {
            "query": f"AF-ID({afid}) AND PUBYEAR = {year}",
            "view": view,
            "count": str(page_size),
            "start": str(start),
        }
        j = get_json(session, BASE_URL_SEARCH, params, headers)
        chunk = j.get("search-results", {}).get("entry", []) or []
        if not chunk:
            break
        entries.extend(chunk)
        if len(chunk) < page_size:
            break
        start += page_size
    return entries

def extract_no_year(session: requests.Session, headers: Dict[str, str],
                    afid: str, page_size: int, view: str, use_cursor: bool) -> List[Dict]:
    entries: List[Dict] = []
    if use_cursor:
        params = {"query": f"AF-ID({afid})", "view": view, "count": str(page_size), "cursor": "*"}
        while True:
            j = get_json(session, BASE_URL_SEARCH, params, headers)
            chunk = j.get("search-results", {}).get("entry", []) or []
            if chunk:
                entries.extend(chunk)
            next_token = None
            for ln in j.get("search-results", {}).get("link", []) or []:
                if ln.get("@ref") == "next":
                    href = ln.get("@href")
                    if href:
                        q = urlparse.urlparse(href).query
                        qd = urlparse.parse_qs(q)
                        next_token = (qd.get("cursor") or [None])[0]
                    break
            if not next_token:
                break
            params["cursor"] = next_token
    else:
        start = 0
        while True:
            params_sc = {"query": f"AF-ID({afid})", "view": view, "count": str(page_size), "start": str(start)}
            j = get_json(session, BASE_URL_SEARCH, params_sc, headers)
            chunk = j.get("search-results", {}).get("entry", []) or []
            if not chunk:
                break
            entries.extend(chunk)
            if len(chunk) < page_size:
                break
            start += page_size
    return entries

# -------------------------
# Normalización básica (sin autores/abstract/keywords/funding/etc.)
# -------------------------
TOP_FIELD_MAP = {
    "dc:title": "title",
    # NO pedimos abstract ni keywords
    "prism:coverDate": "coverDate",
    "prism:doi": "doi",
    "prism:publicationName": "sourceTitle",
    "prism:issn": "issn",
    "prism:eIssn": "eIssn",
    "prism:volume": "volume",
    "prism:issueIdentifier": "issue",
    "prism:pageRange": "pages",
    "citedby-count": "citedBy",
    "subtype": "subtype",
    "subtypeDescription": "subtypeDesc",
    "openaccessFlag": "openAccess",
    "dc:identifier": "identifier",
    "eid": "eid",
    "prism:url": "prismUrl",
}

def links_to_dict(links: List[Dict]) -> Dict[str, str]:
    d = {}
    for ln in links or []:
        ref = ln.get("@ref")
        href = ln.get("@href")
        if ref and href:
            d[f"link_{ref}"] = href
    return d

def normalize_entries(entries: List[Dict]) -> pd.DataFrame:
    rows: List[Dict] = []
    for e in entries:
        row = {}
        for k_src, k_dst in TOP_FIELD_MAP.items():
            if k_src in e:
                row[k_dst] = e.get(k_src)
        row.update(links_to_dict(e.get("link")))
        rows.append(row)

    df = pd.DataFrame(rows)
    if not df.empty:
        if "coverDate" in df.columns:
            df["coverDate"] = pd.to_datetime(df["coverDate"], errors="coerce")
        subset_cols = [c for c in ["eid", "identifier"] if c in df.columns]
        if subset_cols:
            df = df.drop_duplicates(subset=subset_cols, keep="first")
    return df

# -------------------------
# Fallbacks de vista/paginación
# -------------------------
def try_extract_year(session, headers, afid, year, page_size, view, use_cursor) -> List[Dict]:
    def do_extract(ps, cur, v):
        if cur:
            return extract_by_year_cursor(session, headers, afid, year, ps, v)
        else:
            return extract_by_year_startcount(session, headers, afid, year, ps, v)
    try:
        return do_extract(page_size, use_cursor, view)
    except RuntimeError as e:
        msg = str(e)
        if "AUTHORIZATION_ERROR" in msg:
            fallback = "STANDARD" if view == "COMPLETE" else ("BASIC" if view == "STANDARD" else None)
            if fallback:
                return do_extract(page_size, use_cursor, fallback)
            raise
        if "INVALID_INPUT" in msg and "maximum number allowed for the service level" in msg:
            # reduce page size y quita cursor
            return do_extract(25, False, view)
        if use_cursor:
            return do_extract(page_size, False, view)
        raise

def try_extract_no_year(session, headers, afid, page_size, view, use_cursor) -> List[Dict]:
    try:
        return extract_no_year(session, headers, afid, page_size, view, use_cursor)
    except RuntimeError as e:
        msg = str(e)
        if "AUTHORIZATION_ERROR" in msg:
            if view == "COMPLETE":  # bajar a STANDARD/BASIC
                return extract_no_year(session, headers, afid, page_size, "STANDARD", use_cursor)
            if view == "STANDARD":
                return extract_no_year(session, headers, afid, page_size, "BASIC", use_cursor)
            raise
        if "INVALID_INPUT" in msg and "maximum number allowed for the service level" in msg:
            return extract_no_year(session, headers, afid, 25, view, False)
        if use_cursor:
            return extract_no_year(session, headers, afid, page_size, view, False)
        raise

def fetch_scopus_affiliation(api_key: str,
                             afid: str = "60077378",
                             year_start: Optional[int] = 2020,
                             year_end: Optional[int] = 2024,
                             view: str = "STANDARD",
                             page_size: int = 100,
                             insttoken: Optional[str] = None,
                             use_cursor: bool = True) -> List[Dict]:
    headers = build_headers(api_key, insttoken)
    session = requests.Session()
    if year_start is None or year_end is None:
        return try_extract_no_year(session, headers, afid, page_size, view, use_cursor)
    entries: List[Dict] = []
    for yr in range(int(year_start), int(year_end) + 1):
        entries.extend(try_extract_year(session, headers, afid, yr, page_size, view, use_cursor))
    return entries

# -------------------------
# Export UN SOLO CSV (ligero)
# -------------------------
EXPORT_COLUMNS = [
    "Title","Year","Source title","Volume","Issue",
    "Page start","Page end","Page count",
    "Cited by","DOI","Link","ISSN","eISSN","Document Type","Open Access","EID"
]

def _pick_link(row: pd.Series) -> str:
    for c in ("prismUrl","link_scopus","prism:url","link_self"):
        if c in row and pd.notna(row[c]) and str(row[c]).strip():
            return str(row[c])
    return ""

def pick_col(df: pd.DataFrame, primary: str, secondary: str, default: str = "") -> pd.Series:
    """Fallback por fila: usa primary; si está vacío/NaN, toma secondary."""
    n = len(df)
    s1 = df[primary] if primary in df.columns else pd.Series([np.nan] * n, index=df.index)
    s2 = df[secondary] if secondary in df.columns else pd.Series([default] * n, index=df.index)
    s1 = s1.copy()
    mask = s1.isna() | (s1.astype(str).str.strip() == "")
    s1.loc[mask] = s2.loc[mask]
    return s1.fillna(default)

def make_export(df: pd.DataFrame) -> pd.DataFrame:
    # Derivar Year y páginas
    out = df.copy()

    if "coverDate" in out.columns:
        out["Year"] = pd.to_datetime(out["coverDate"], errors="coerce").dt.year
    else:
        out["Year"] = ""

    out["Page start"], out["Page end"], out["Page count"] = "", "", ""
    if "pages" in out.columns:
        starts, ends, counts = [], [], []
        for x in out["pages"].fillna(""):
            if "-" in x:
                a, b = x.split("-", 1)
                a_num = "".join(ch for ch in a if ch.isdigit())
                b_num = "".join(ch for ch in b if ch.isdigit())
                starts.append(a_num); ends.append(b_num)
                try:
                    counts.append(str(max(0, int(b_num) - int(a_num) + 1)) if a_num and b_num else "")
                except Exception:
                    counts.append("")
            else:
                starts.append(""); ends.append(""); counts.append("")
        out["Page start"], out["Page end"], out["Page count"] = starts, ends, counts

    # Link preferido
    out["Link"] = out.apply(_pick_link, axis=1)

    # Ensamblar columnas finales (usando pick_col para evitar 'Series' ambiguas)
    final = pd.DataFrame()
    final["Title"] = out.get("title", "")
    final["Year"]  = out.get("Year", "")

    final["Source title"] = pick_col(out, "sourceTitle", "prism:publicationName")
    final["Volume"]       = pick_col(out, "volume", "prism:volume")
    final["Issue"]        = pick_col(out, "issue", "prism:issueIdentifier")

    final["Page start"] = out["Page start"]
    final["Page end"]   = out["Page end"]
    final["Page count"] = out["Page count"]

    final["Cited by"] = pick_col(out, "citedBy", "citedby-count")
    final["DOI"]      = pick_col(out, "doi", "prism:doi")
    final["Link"]     = out["Link"]

    final["ISSN"]  = pick_col(out, "issn", "prism:issn")
    final["eISSN"] = pick_col(out, "eIssn", "prism:eIssn")

    final["Document Type"] = pick_col(out, "subtypeDesc", "subtypeDescription")
    final["Open Access"]   = pick_col(out, "openAccess", "openaccessFlag")

    final["EID"] = out.get("eid", "")

    # Ordenar por año descendente (coaccionando a numérico para evitar mezclas str/int)
    final["Year"] = pd.to_numeric(final["Year"], errors="coerce")
    final = final.sort_values(by="Year", ascending=False, na_position="last")

    # Reordenar/filtrar columnas
    return final[EXPORT_COLUMNS]

# -------------------------
# CLI
# -------------------------
def parse_args():
    p = argparse.ArgumentParser(description="Extrae publicaciones Scopus por AF-ID y exporta UN CSV básico (sin autores/abstract/etc.).")
    p.add_argument("--api-key", required=True, help="X-ELS-APIKey")
    p.add_argument("--insttoken", default=None, help="X-ELS-Insttoken (opcional)")
    p.add_argument("--afid", default="60077378", help="Scopus Affiliation ID (AF-ID)")
    p.add_argument("--year-start", default=2020, help="Año inicial o 'None'")
    p.add_argument("--year-end", default=2024, help="Año final o 'None'")
    p.add_argument("--view", default="STANDARD", choices=["BASIC", "STANDARD", "COMPLETE"], help="Vista del Search API")
    p.add_argument("--page-size", type=int, default=100, help="Tamaño de página (25..200)")
    p.add_argument("--use-cursor", action="store_true", help="Usar cursor pagination")
    p.add_argument("--no-cursor", dest="use_cursor", action="store_false", help="Usar start/count")
    p.set_defaults(use_cursor=True)
    p.add_argument("--out-prefix", default="scopus_afid", help="Prefijo de salida")
    return p.parse_args()

def main():
    args = parse_args()

    def norm_year(x):
        sx = str(x).strip().lower()
        return None if sx == "none" else int(x)
    y0 = norm_year(args.year_start)
    y1 = norm_year(args.year_end)

    print("Descargando desde Scopus (Search API)…")
    entries = fetch_scopus_affiliation(
        api_key=args.api_key,
        afid=args.afid,
        year_start=y0,
        year_end=y1,
        view=args.view,
        page_size=args.page_size,
        insttoken=args.insttoken,
        use_cursor=args.use_cursor
    )
    print(f"Entradas obtenidas: {len(entries)}")

    df = normalize_entries(entries)
    export_df = make_export(df)
    out_csv = f"{args.out_prefix}_scopus_export.csv"
    export_df.to_csv(out_csv, index=False, encoding="utf-8-sig")
    print(f"Listo: {out_csv}")

if __name__ == "__main__":
    main()