structured data extraction from pdf

backend/main.py

@@ -10,8 +10,39 @@ from pypdf import PdfReader
 import pytesseract
 from PIL import Image
 from pdf2image import convert_from_bytes
+import pdfplumber
 from sqlalchemy.orm import Session
 
+
+
+# 2. OCR Module
+def extract_text_from_pdf(file_bytes: bytes) -> str:
+    # Try pdfplumber first for layout preservation
+    try:
+        with pdfplumber.open(io.BytesIO(file_bytes)) as pdf:
+            text = ""
+            for page in pdf.pages:
+                page_text = page.extract_text(layout=True)
+                if page_text:
+                    text += page_text + "\n"
+            if text.strip():
+                return text.strip()
+    except Exception as e:
+        print(f"pdfplumber error: {e}")
+
+    # Fallback to pypdf
+    try:
+        reader = PdfReader(io.BytesIO(file_bytes))
+        text = ""
+        for page in reader.pages:
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text + "\n"
+        return text.strip()
+    except Exception as e:
+        print(f"Error reading PDF: {e}")
+        return ""
+
 # Internal modules
 from database import get_db, Email
 from scheduler import start_scheduler, stop_scheduler
@@ -57,19 +88,7 @@ class LoginResponse(BaseModel):
 class NERResponse(BaseModel):
     text: str
 
-# 2. OCR Module
-def extract_text_from_pdf(file_bytes: bytes) -> str:
-    try:
-        reader = PdfReader(io.BytesIO(file_bytes))
-        text = ""
-        for page in reader.pages:
-            page_text = page.extract_text()
-            if page_text:
-                text += page_text + "\n"
-        return text.strip()
-    except Exception as e:
-        print(f"Error reading PDF: {e}")
-        return ""
+
 
 def extract_text_from_image(file_bytes: bytes) -> str:
     try:

backend/requirements.txt

@@ -9,3 +9,4 @@ psycopg2-binary
 imap-tools
 apscheduler
 python-dotenv
+pdfplumber