Update app.py

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 from transformers import pipeline
 import logging
+from PyPDF2 import PdfReader
 
 # Setup logging
 def setup_logging():
@@ -12,6 +13,14 @@ def setup_logging():
         ]
     )
 
+# Function to extract text from a PDF file
+def extract_text_from_pdf(pdf_file):
+    pdf_reader = PdfReader(pdf_file)
+    text = ""
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+    return text
+
 def main():
     setup_logging()
     logging.info("Starting the Streamlit app.")
@@ -35,21 +44,30 @@ def main():
 
     if input_type == "Text":
         text = st.text_area("Enter your text here:", placeholder="Type your text here...")
-    elif input_type in ["Text File", "PDF", "DOCX"]:
-        file = st.file_uploader(f"Upload your {input_type}:", type=["txt", "pdf", "docx"])
+    elif input_type == "Text File":
+        file = st.file_uploader("Upload your text file:", type=["txt"])
+    elif input_type == "PDF":
+        file = st.file_uploader("Upload your PDF file:", type=["pdf"])
+    elif input_type == "DOCX":
+        file = st.file_uploader("Upload your DOCX file:", type=["docx"])
     elif input_type == "Audio":
         audio = st.file_uploader("Upload your audio file:", type=["wav", "mp3", "m4a"])
 
     if st.button("Report Result"):
         try:
+            summary = None
             if input_type == "Text" and text:
                 logging.info("Processing text input.")
                 summary = summarizer(text, max_length=130, min_length=30, do_sample=False)
                 logging.info("Text input processed successfully.")
-            elif input_type in ["Text File", "PDF", "DOCX"] and file:
-                logging.info(f"Processing {input_type} file: {file.name}")
-                # Add file reading logic here
-                summary = "File processing not implemented yet."
+            elif input_type == "Text File" and file:
+                logging.info(f"Processing text file: {file.name}")
+                text = file.read().decode("utf-8")  # Assuming UTF-8 encoding
+                summary = summarizer(text, max_length=130, min_length=30, do_sample=False)
+            elif input_type == "PDF" and file:
+                logging.info(f"Processing PDF file: {file.name}")
+                text = extract_text_from_pdf(file)
+                summary = summarizer(text, max_length=130, min_length=30, do_sample=False)
             elif input_type == "Audio" and audio:
                 logging.info("Processing audio input.")
                 # Add audio processing logic here
@@ -66,4 +84,4 @@ def main():
     logging.info("Closing the Streamlit app.")
 
 if __name__ == "__main__":
-    main()
+    main()