First Commit

src/paper_monitor/oa_resolver.py

@@ -0,0 +1,60 @@
+import logging
+
+import requests
+
+
+log = logging.getLogger(__name__)
+
+
+class UnpaywallResolver:
+    def __init__(self, email: str, timeout=(10, 30)):
+        self.email = (email or "").strip()
+        self.timeout = timeout
+        self.base_url = "https://api.unpaywall.org/v2"
+
+    def resolve(self, paper):
+        if not paper.doi:
+            return paper
+
+        if not self.email:
+            log.warning(
+                "Unpaywall email missing; OA lookup skipped: %s",
+                paper.title,
+            )
+            return paper
+
+        doi = paper.doi.strip()
+
+        try:
+            response = requests.get(
+                f"{self.base_url}/{doi}",
+                params={"email": self.email},
+                timeout=self.timeout,
+            )
+            response.raise_for_status()
+
+        except requests.exceptions.HTTPError as exc:
+            status = exc.response.status_code if exc.response else None
+
+            # DOI not present in Unpaywall is not fatal.
+            if status == 404:
+                paper.oa_status = "not_found"
+                return paper
+
+            raise
+
+        data = response.json()
+
+        paper.oa_status = str(
+            data.get("oa_status") or ""
+        )
+
+        best = data.get("best_oa_location") or {}
+
+        pdf_url = best.get("url_for_pdf") or ""
+
+        # Some OA records do not expose url_for_pdf but do expose a landing URL.
+        # We intentionally do NOT treat url as a PDF here.
+        paper.pdf_url = str(pdf_url).strip()
+
+        return paper