Upload 2 files

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+spacy
+PyPDF2
+python-docx

resume.py

@@ -0,0 +1,46 @@
+import streamlit as st
+import PyPDF2
+import docx
+import spacy
+
+# Load NLP model
+@st.cache_resource
+def load_model():
+    return spacy.load("en_core_web_sm")
+
+nlp = load_model()
+
+# Function to extract text
+def extract_text(file):
+    if file.type == "application/pdf":
+        reader = PyPDF2.PdfFileReader(file)
+        return "".join([reader.getPage(i).extract_text() for i in range(reader.numPages)])
+    elif file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
+        return "\n".join([para.text for para in docx.Document(file).paragraphs])
+
+# Function to extract and display information
+def analyze_resume(text, job_desc):
+    doc = nlp(text)
+    extracted_info = {"skills": [], "education": [], "experience": []}
+    
+    for ent in doc.ents:
+        if ent.label_ in ["ORG", "GPE"]:
+            extracted_info["education"].append(ent.text)
+        elif ent.label_ == "DATE":
+            extracted_info["experience"].append(ent.text)
+
+    match_score = sum(1 for token in nlp(job_desc) if token.text in text) / len(job_desc.split()) * 100
+    return extracted_info, match_score
+
+# Streamlit interface
+st.title("Resume Scanner with NLP")
+uploaded_file = st.file_uploader("Upload a resume (PDF or DOCX)", type=["pdf", "docx"])
+job_description = st.text_area("Paste the job description here")
+
+if uploaded_file and job_description:
+    resume_text = extract_text(uploaded_file)
+    extracted_info, match_score = analyze_resume(resume_text, job_description)
+    
+    st.subheader("Extracted Information:")
+    st.write(extracted_info)
+    st.subheader(f"Match Score: {match_score:.2f}%")