Initial commit

modules/pdf_utils.py

@@ -0,0 +1,43 @@
+from pathlib import Path
+import PyPDF2
+from typing import Optional
+
+class PDFUtils:
+    @staticmethod
+    def extract_text_from_pdf(pdf_file: Path) -> str:
+        """
+        Extract text content from a PDF file
+        """
+        if not pdf_file.exists():
+            raise FileNotFoundError(f"PDF file not found: {pdf_file}")
+
+        text = ""
+        with open(pdf_file, 'rb') as file:
+            pdf_reader = PyPDF2.PdfReader(file)
+            for page in pdf_reader.pages:
+                text += page.extract_text() + "\n"
+
+        return text
+
+    @staticmethod
+    def get_pdf_metadata(pdf_file: Path) -> dict:
+        """
+        Get metadata from a PDF file
+        """
+        if not pdf_file.exists():
+            raise FileNotFoundError(f"PDF file not found: {pdf_file}")
+
+        with open(pdf_file, 'rb') as file:
+            pdf_reader = PyPDF2.PdfReader(file)
+            metadata = pdf_reader.metadata or {}
+            
+            # Convert metadata to a dictionary
+            result = {}
+            for key, value in metadata.items():
+                if value:
+                    result[key] = str(value)
+            
+            # Add additional information
+            result['num_pages'] = len(pdf_reader.pages)
+            
+            return result