Update app.py

app.py

@@ -11,6 +11,9 @@ import PyPDF2
 from PIL import Image
 import pytesseract
 from pdf2image import convert_from_path
+import docx  # For DOCX processing
+import io
+import os
 
 # Download necessary NLTK data
 nltk.download('punkt')
@@ -54,6 +57,13 @@ def extract_text_with_ocr(pdf_file):
         text += pytesseract.image_to_string(image)
     return text
 
+# Function for DOCX text extraction
+def extract_text_from_docx(docx_file):
+    """Extract text from a DOCX file."""
+    doc = docx.Document(docx_file)
+    text = '\n'.join([para.text for para in doc.paragraphs])
+    return text
+
 # Unified PDF extraction function
 def extract_text_from_pdf(pdf_file):
     """Extract text using multiple methods."""
@@ -67,6 +77,9 @@ def extract_text_from_pdf(pdf_file):
     except Exception as e:
         print(f"Error with PyMuPDF: {e}")
 
+    # Reset file pointer
+    pdf_file.seek(0)
+    
     # Attempt PyPDF2 extraction
     try:
         text = extract_text_with_pypdf2(pdf_file)
@@ -75,6 +88,9 @@ def extract_text_from_pdf(pdf_file):
     except Exception as e:
         print(f"Error with PyPDF2: {e}")
 
+    # Reset file pointer
+    pdf_file.seek(0)
+    
     # Attempt OCR as a last resort
     try:
         text = extract_text_with_ocr(pdf_file)
@@ -134,6 +150,10 @@ def analyze_documents(resume_text, job_description):
     Resume: {resume_text}
     """
     
+    API_KEY = os.getenv("GEMINI_API_KEY")  # Ensure you set this environment variable securely
+    if not API_KEY:
+        return {"Match Percentage": "API Key Missing", "Recommendations": "Please set the GEMINI_API_KEY environment variable."}
+    
     url = f"https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash-latest:generateContent?key={API_KEY}"
     headers = {'Content-Type': 'application/json'}
     data = {
@@ -142,7 +162,19 @@ def analyze_documents(resume_text, job_description):
         ]
     }
     response = requests.post(url, headers=headers, json=data)
-    return response.json()
+    
+    if response.status_code == 200:
+        try:
+            result = response.json()
+            # Parse the response as needed. This is a placeholder.
+            return {
+                "Match Percentage": result.get('choices', [{}])[0].get('text', 'N/A').strip(),
+                "Recommendations": "Placeholder for actual recommendations."
+            }
+        except ValueError:
+            return {"Match Percentage": "Error", "Recommendations": "Failed to parse response."}
+    else:
+        return {"Match Percentage": "Error", "Recommendations": f"API request failed with status code {response.status_code}."}
 
 # Streamlit app configuration
 st.set_page_config(page_title="ATS Resume Evaluation System", layout="wide")
@@ -166,16 +198,28 @@ resume_file = st.file_uploader("Upload Resume (PDF or DOCX)", type=["pdf", "docx
 # Process the uploaded resume and job description
 if resume_file:
     if job_description:
-        resume_text = resume_file.read()  # Read the uploaded PDF or DOCX file
-        resume_text = extract_text_from_pdf(resume_text)  # Extract text from the PDF using the unified function
-        cleaned_resume = clean_and_normalize_text(resume_text)
-        cleaned_job_description = clean_and_normalize_text(job_description)
-        
-        # Analyze the resume and job description
-        result = analyze_documents(cleaned_resume, cleaned_job_description)
-
-        # Display the analysis results
-        st.write(f"**Match Percentage**: {result['Match Percentage']}")
-        st.write(f"**Recommendations**: {result['Recommendations']}")
+        try:
+            if resume_file.type == "application/pdf":
+                resume_text = extract_text_from_pdf(resume_file)
+            elif resume_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
+                resume_text = extract_text_from_docx(resume_file)
+            else:
+                st.error("Unsupported file type.")
+                resume_text = ""
+            
+            if resume_text:
+                cleaned_resume = clean_and_normalize_text(resume_text)
+                cleaned_job_description = clean_and_normalize_text(job_description)
+                
+                # Analyze the resume and job description
+                result = analyze_documents(cleaned_resume, cleaned_job_description)
+
+                # Display the analysis results
+                st.write(f"**Match Percentage**: {result.get('Match Percentage', 'N/A')}")
+                st.write(f"**Recommendations**: {result.get('Recommendations', 'N/A')}")
+            else:
+                st.error("Failed to extract text from the uploaded file.")
+        except Exception as e:
+            st.error(f"An error occurred during processing: {e}")
     else:
         st.warning("Please enter the job description to begin analysis.")