Update app.py

app.py

@@ -21,6 +21,42 @@ from typing import Optional, List, Dict, Tuple
 from bs4 import BeautifulSoup
 import requests
 from io import BytesIO
+import docx
+import PyPDF2
+import pptx
+import cv2
+
+class FileProcessor:
+    @staticmethod
+    def read_txt(file):
+        return file.read().decode('utf-8')
+    
+    @staticmethod
+    def read_pdf(file):
+        pdf_reader = PyPDF2.PdfReader(file)
+        text = ""
+        for page in pdf_reader.pages:
+            text += page.extract_text() + "\n"
+        return text
+    
+    @staticmethod
+    def read_docx(file):
+        doc = docx.Document(file)
+        text = ""
+        for para in doc.paragraphs:
+            text += para.text + "\n"
+        return text
+    
+    @staticmethod
+    def read_pptx(file):
+        prs = pptx.Presentation(file)
+        text = ""
+        for slide in prs.slides:
+            for shape in slide.shapes:
+                if hasattr(shape, "text"):
+                    text += shape.text + "\n"
+        return text
+
 
 class ImageScraper:
     def __init__(self):