1 files changed, 62 insertions, 0 deletions
diff --git a/converter/extractors.py b/converter/extractors.py
index cd270a1..a564333 100644
--- a/converter/extractors.py
+++ b/converter/extractors.py
@@ -24,6 +24,14 @@ class Section(NamedTuple):
     text: str
 
 
+class Book(NamedTuple):
+    """A book's metadata plus its titled sections."""
+
+    title: str
+    author: str
+    sections: List[Section]
+
+
 def extract_text(file_path: Path) -> str:
     """Extract text from a book file based on its extension."""
     extension = file_path.suffix.lower()
@@ -52,6 +60,60 @@ def extract_sections(file_path: Path) -> List[Section]:
     return [Section(file_path.stem, extract_text(file_path))]
 
 
+def extract_book(file_path: Path) -> Book:
+    """Extract sections plus book-level metadata (title, author).
+
+    EPUB and PDF files carry embedded metadata; missing fields (and TXT
+    files, which have none) fall back to the file stem for the title and
+    an empty author.
+    """
+    title, author = "", ""
+    extension = file_path.suffix.lower()
+    if extension == ".epub":
+        title, author = _epub_metadata(file_path)
+    elif extension == ".pdf":
+        title, author = _pdf_metadata(file_path)
+    return Book(title or file_path.stem, author.strip(), extract_sections(file_path))
+
+
+def _epub_metadata(file_path: Path) -> tuple:
+    """Return (title, author) from an EPUB's Dublin Core metadata."""
+    try:
+        import ebooklib
+        from ebooklib import epub
+
+        book = epub.read_epub(str(file_path))
+        title = _first_dc_value(book.get_metadata("DC", "title"))
+        author = _first_dc_value(book.get_metadata("DC", "creator"))
+        return title, author
+    except Exception as exc:
+        logger.warning("Could not read EPUB metadata: %s", exc)
+        return "", ""
+
+
+def _pdf_metadata(file_path: Path) -> tuple:
+    """Return (title, author) from a PDF's document info dictionary."""
+    try:
+        from pypdf import PdfReader
+
+        reader = PdfReader(str(file_path))
+        info = reader.metadata or {}
+        title = str(info.get("/Title") or "")
+        author = str(info.get("/Author") or "")
+        return title, author
+    except Exception as exc:
+        logger.warning("Could not read PDF metadata: %s", exc)
+        return "", ""
+
+
+def _first_dc_value(entries) -> str:
+    """First value of an ebooklib DC metadata list: [(value, ...), ...]."""
+    if not entries:
+        return ""
+    value = entries[0][0]
+    return str(value).strip() if value else ""
+
+
 def _extract_epub_chapters(file_path: Path) -> List[Section]:
     """Return one Section per EPUB spine document (chapter), in reading order."""
     import ebooklib