Init

src/pdf_to_kcf/pdf_reader.py

@@ -0,0 +1,47 @@
+"""PDF reading and text extraction utilities."""
+
+from pathlib import Path
+from typing import List
+from pypdf import PdfReader
+
+
+class PDFDocument:
+    """Wrapper for PDF document reading."""
+
+    def __init__(self, pdf_path: str):
+        """Initialize PDF reader with the given path.
+
+        Args:
+            pdf_path: Path to the PDF file
+        """
+        self.pdf_path = Path(pdf_path)
+        if not self.pdf_path.exists():
+            raise FileNotFoundError(f"PDF file not found: {pdf_path}")
+
+        self.reader = PdfReader(str(self.pdf_path))
+        self.total_pages = len(self.reader.pages)
+
+    def get_page_text(self, page_number: int) -> str:
+        """Extract text from a specific page.
+
+        Args:
+            page_number: 0-indexed page number
+
+        Returns:
+            Extracted text content from the page
+        """
+        if page_number < 0 or page_number >= self.total_pages:
+            raise ValueError(
+                f"Invalid page number {page_number}. Document has {self.total_pages} pages."
+            )
+
+        page = self.reader.pages[page_number]
+        return page.extract_text()
+
+    def get_all_pages(self) -> List[str]:
+        """Extract text from all pages.
+
+        Returns:
+            List of text content for each page
+        """
+        return [self.get_page_text(i) for i in range(self.total_pages)]