Update app/pdf_utils.py

app/pdf_utils.py

@@ -1,9 +1,12 @@
+import io
+from typing import List, Dict
+
 import fitz  # PyMuPDF
+import pdfplumber
 from PIL import Image
-import io
 
 
-def pdf_to_images(pdf_bytes: bytes) -> list[Image.Image]:
+def pdf_to_images(pdf_bytes: bytes) -> List[Image.Image]:
     doc = fitz.open(stream=pdf_bytes, filetype="pdf")
     images = []
 
@@ -12,4 +15,26 @@ def pdf_to_images(pdf_bytes: bytes) -> list[Image.Image]:
         img = Image.open(io.BytesIO(pix.tobytes("png"))).convert("RGB")
         images.append(img)
 
-    return images
+    return images
+
+
+def extract_text_from_pdf(pdf_bytes: bytes) -> List[Dict]:
+    """
+    Extract text page-by-page directly from the PDF.
+    Returns a list like:
+    [
+      {"page": 1, "text": "..."},
+      {"page": 2, "text": "..."}
+    ]
+    """
+    results: List[Dict] = []
+
+    with pdfplumber.open(io.BytesIO(pdf_bytes)) as pdf:
+        for idx, page in enumerate(pdf.pages, start=1):
+            text = page.extract_text() or ""
+            results.append({
+                "page": idx,
+                "text": text
+            })
+
+    return results