feat: pdf reader

backend/apps/books/serializers.py

@@ -91,13 +91,15 @@ class EBookListSerializer(serializers.ModelSerializer):
             return None
 
     def get_started(self, obj):
-        """True when the user has opened the reader and has a saved EPUB location."""
+        """True when the user has opened the reader with saved progress."""
         try:
             rp = obj.reading_progress
         except ReadingProgress.DoesNotExist:
             return False
         if rp.current_position >= 99:
             return False
+        if obj.format == "pdf":
+            return rp.last_page > 0 or rp.current_position > 0
         return bool((rp.epub_location or "").strip())
 
 

backend/apps/books/services/process_ebook.py

@@ -89,7 +89,69 @@ def _process_epub(file_path: str) -> dict[str, Any]:
 
 
 def _process_pdf(file_path: str) -> dict[str, Any]:
-    return {"format": "pdf", "page_count": 0, "metadata": {}, "toc": []}
+    from pypdf import PdfReader
+
+    reader = PdfReader(file_path)
+    page_count = len(reader.pages)
+    metadata = _extract_pdf_metadata(reader)
+    toc = _extract_pdf_outline(reader)
+    if not toc and page_count > 0:
+        toc = [
+            {"title": f"Page {i}", "href": f"pdf:page:{i}", "children": []}
+            for i in range(1, page_count + 1)
+        ]
+    return {
+        "format": "pdf",
+        "page_count": page_count,
+        "metadata": metadata,
+        "toc": toc,
+    }
+
+
+def _extract_pdf_metadata(reader) -> dict[str, Any]:
+    metadata: dict[str, Any] = {}
+    info = reader.metadata
+    if not info:
+        return metadata
+    title = getattr(info, "title", None)
+    author = getattr(info, "author", None)
+    if title:
+        metadata["title"] = str(title)
+    if author:
+        metadata["author"] = str(author)
+    return metadata
+
+
+def _extract_pdf_outline(reader) -> list[dict[str, Any]]:
+    outline = getattr(reader, "outline", None)
+    if not outline:
+        return []
+    return _walk_pdf_outline(reader, outline)
+
+
+def _walk_pdf_outline(reader, outline: list[Any]) -> list[dict[str, Any]]:
+    entries: list[dict[str, Any]] = []
+    i = 0
+    while i < len(outline):
+        item = outline[i]
+        if isinstance(item, list):
+            if entries:
+                entries[-1]["children"] = _walk_pdf_outline(reader, item)
+            i += 1
+            continue
+        title = getattr(item, "title", None) or "Section"
+        page_num = 1
+        try:
+            page_num = reader.get_destination_page_number(item) + 1
+        except Exception:
+            logger.debug("Could not resolve PDF outline destination", exc_info=True)
+        entries.append({
+            "title": str(title),
+            "href": f"pdf:page:{page_num}",
+            "children": [],
+        })
+        i += 1
+    return entries
 
 
 def _extract_epub_metadata(book) -> dict[str, Any]:

backend/apps/books/views.py

@@ -168,18 +168,23 @@ class EBookViewSet(viewsets.ModelViewSet):
 
     @action(detail=True, methods=["get"])
     def file(self, request: Request, pk: int | None = None) -> FileResponse | Response:
-        """Stream the EPUB file for authenticated in-browser reading."""
+        """Stream the ebook file for authenticated in-browser reading."""
         ebook = self.get_object()
-        if ebook.format != "epub":
+        content_types = {
+            "epub": "application/epub+zip",
+            "pdf": "application/pdf",
+        }
+        content_type = content_types.get(ebook.format)
+        if not content_type:
             return Response(
-                {"error": "Reader supports EPUB only."},
+                {"error": "Unsupported format for in-browser reading."},
                 status=status.HTTP_400_BAD_REQUEST,
             )
         if not ebook.file:
             return Response({"error": "No file found for this e-book."}, status=status.HTTP_400_BAD_REQUEST)
         return FileResponse(
             ebook.file.open("rb"),
-            content_type="application/epub+zip",
+            content_type=content_type,
             filename=ebook.filename(),
         )
 

backend/pyproject.toml

@@ -21,4 +21,5 @@ dependencies = [
     "httpx>=0.28.0",
     "ebooklib>=0.18",
     "beautifulsoup4>=4.12.0",
+    "pypdf>=5.0.0",
 ]

backend/uv.lock

@@ -52,6 +52,7 @@ dependencies = [
     { name = "psycopg2-binary" },
     { name = "pydantic" },
     { name = "pydantic-settings" },
+    { name = "pypdf" },
     { name = "pytest" },
     { name = "pytest-cov" },
     { name = "pytest-django" },
@@ -74,6 +75,7 @@ requires-dist = [
     { name = "psycopg2-binary", specifier = "==2.9.10" },
     { name = "pydantic", specifier = "==2.10.5" },
     { name = "pydantic-settings", specifier = "==2.7.1" },
+    { name = "pypdf", specifier = ">=5.0.0" },
     { name = "pytest", specifier = "==8.3.4" },
     { name = "pytest-cov", specifier = "==6.0.0" },
     { name = "pytest-django", specifier = "==4.9.0" },
@@ -567,6 +569,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a3/5e/ecf12fdb62546d64385c158514e9b2b671f7832108ef2ecd2020ce0af2d1/pyjwt-2.13.0-py3-none-any.whl", hash = "sha256:66adcc2aff09b3f1bbd95fc1e1577df8ac8723c978552fd43304c8a290ac5728", size = 31274, upload-time = "2026-05-21T19:54:35.362Z" },
 ]
 
+[[package]]
+name = "pypdf"
+version = "6.12.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/0a/6d/20879428577c1e57ecd41b69dc86beabf43db9287ad2e702207f8b48c751/pypdf-6.12.2.tar.gz", hash = "sha256:111669eb6680c04495ae0c113a1476e3bf93a95761d23c7406b591c80a6490b1", size = 6468184, upload-time = "2026-05-26T13:31:26.911Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/9e/44/fee070a16639d9869bb6a7e0f3a1b3946da1d66f32b9260b4d19cb90d7b2/pypdf-6.12.2-py3-none-any.whl", hash = "sha256:67b2699357a1f3f4c945940ea80826349ee507c9e2577724a14b4941982c104d", size = 343865, upload-time = "2026-05-26T13:31:25.068Z" },
+]
+
 [[package]]
 name = "pytest"
 version = "8.3.4"