fix: skip unreadable PDFs during metadata extraction

2026-08-10 23:58:42 -04:00
parent 1415cb6244
commit 3091cc879d
1 changed files with 6 additions and 2 deletions
@@ -155,7 +155,11 @@ class PdfExtractor(FileExtractor):
        if isinstance(data, UploadFile):
            data = data.file

-        doc = pypdfium2.PdfDocument(data)
+        try:
+            doc = pypdfium2.PdfDocument(data)
+        except Exception as e:
+            logger.error(f"Error extracting metadata from pdf: {e}")
+            return {}

        basic_metadata = doc.get_metadata_dict(skip_empty=False)
        metadata["title"] = basic_metadata["Title"]