commonmeta-py 0.16.8__tar.gz → 0.16.10__tar.gz

{commonmeta_py-0.16.8 → commonmeta_py-0.16.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: commonmeta-py
-Version: 0.16.8
+Version: 0.16.10
 Summary: Library for conversions to/from the Commonmeta scholarly metadata format
 Home-page: https://python.commonmeta.org
 License: MIT
@@ -28,7 +28,7 @@ Requires-Dist: datacite (>=1.1,<2.0)
 Requires-Dist: dateparser (>=1.1.7,<2.0.0)
 Requires-Dist: docutils (>=0.19,<0.20)
 Requires-Dist: furl (>=2.1.3,<3.0.0)
-Requires-Dist: httpx (>=0.25,<0.26)
+Requires-Dist: httpx (>=0.24,<0.25)
 Requires-Dist: jsonschema (>=4.21,<5.0)
 Requires-Dist: jupyterlab (>=4.0.9,<5.0.0)
 Requires-Dist: jupyterlab-quarto (>=0.2.8,<0.3.0)

{commonmeta_py-0.16.8 → commonmeta_py-0.16.10}/commonmeta/readers/schema_org_reader.py

@@ -64,20 +64,29 @@ def get_schema_org(pid: str, **kwargs) -> dict:
             state = "bad_request"
         return {"@id": url, "@type": "WebPage", "state": state, "via": "schema_org"}
     elif response.headers.get("content-type") == "application/pdf":
-        pdf = pikepdf.Pdf.open(io.BytesIO(response.content))
-        meta = pdf.docinfo if pdf.docinfo else {}
-        if meta.get("/doi", None) is not None:
-            return get_doi_meta(meta.get("/doi"))
-        date_modified = get_datetime_from_pdf_time(meta.get("/ModDate")) if meta.get("/ModDate", None) else None
-        name = meta.get("/Title", None)
-        return compact({
-            "@id": url,
-            "@type": "DigitalDocument",
-            "via": "schema_org",
-            "name": str(name),
-            "datePublished": date_modified,
-            "dateAccessed": datetime.now().isoformat("T", "seconds") if date_modified is None else None,
-        })
+        try:
+            pdf = pikepdf.Pdf.open(io.BytesIO(response.content))
+            meta = pdf.docinfo if pdf.docinfo else {}
+            if meta.get("/doi", None) is not None:
+                return get_doi_meta(meta.get("/doi"))
+            date_modified = get_datetime_from_pdf_time(meta.get("/ModDate")) if meta.get("/ModDate", None) else None
+            name = meta.get("/Title", None)
+            return compact({
+                "@id": url,
+                "@type": "DigitalDocument",
+                "via": "schema_org",
+                "name": str(name),
+                "datePublished": date_modified,
+                "dateAccessed": datetime.now().isoformat("T", "seconds") if date_modified is None else None,
+            })
+        except Exception as error:
+            print(error)
+            return {
+                "@id": url,
+                "@type": "WebPage",
+                "state": "bad_request",
+                "via": "schema_org",
+            }
 
     soup = BeautifulSoup(response.text, "html.parser")
 

{commonmeta_py-0.16.8 → commonmeta_py-0.16.10}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name="commonmeta-py"
-version="0.16.8"
+version="0.16.10"
 repository = "https://github.com/front-matter/commonmeta-py"
 homepage = "https://python.commonmeta.org"
 documentation = "https://python.commonmeta.org"
@@ -17,7 +17,7 @@ docutils = "^0.19"
 setuptools = "^69.0"
 sphinxcontrib-issuetracker = "^0.11"
 sphinx-autodoc-typehints = "^1.19"
-httpx = "^0.25"
+httpx = "^0.24"
 dateparser = "^1.1.7"
 types-dateparser = "^1.1"
 PyYAML = "^6.0"