Create app.py

app.py

@@ -0,0 +1,109 @@
+import streamlit as st
+import spacy
+import requests
+from bs4 import BeautifulSoup
+import PyPDF2
+from io import BytesIO
+
+# Load SpaCy model for NLP processing
+nlp = spacy.load("en_core_web_sm")
+
+def extract_text_from_pdf(pdf_file):
+    pdf_reader = PyPDF2.PdfReader(pdf_file)
+    text = ""
+    for page in pdf_reader.pages:
+        text += page.extract_text() or ""
+    return text
+
+def extract_skills_and_location(text):
+    doc = nlp(text)
+    skills = []
+    location = None
+
+    # Sample skill keywords; can be expanded for a more comprehensive list
+    skill_keywords = ['Python', 'Data Analysis', 'Machine Learning', 'SQL', 'Java', 'Project Management']
+
+    for token in doc:
+        if token.text in skill_keywords and token.text not in skills:
+            skills.append(token.text)
+    
+    for ent in doc.ents:
+        if ent.label_ == 'GPE':  # GPE (Geopolitical Entity) is often used for cities/countries
+            location = ent.text
+            break
+    
+    return skills, location
+
+def fetch_job_listings(job_title, location):
+    base_url = "https://www.careerjet.co.in/jobs"
+    params = {
+        's': job_title.replace(' ', '+'),
+        'l': location.replace(' ', '+')
+    }
+
+    response = requests.get(base_url, params=params)
+
+    if response.status_code != 200:
+        st.error("Failed to retrieve the job listings.")
+        return []
+
+    soup = BeautifulSoup(response.text, 'html.parser')
+    job_cards = soup.find_all('article', class_='job clicky')
+
+    job_listings = []
+    for job in job_cards:
+        title_tag = job.find('h2').find('a')
+        company_tag = job.find('p', class_='company').find('a')
+        location_tag = job.find('ul', class_='location').find('li')
+        description_tag = job.find('div', class_='desc')
+        date_posted_tag = job.find('span', class_='badge badge-r badge-s badge-icon')
+
+        job_info = {
+            'title': title_tag.text.strip() if title_tag else 'N/A',
+            'company': company_tag.text.strip() if company_tag else 'N/A',
+            'location': location_tag.text.strip() if location_tag else 'N/A',
+            'description': description_tag.text.strip() if description_tag else 'N/A',
+            'date_posted': date_posted_tag.text.strip() if date_posted_tag else 'N/A',
+            'url': f"https://www.careerjet.co.in{title_tag['href']}" if title_tag else ''
+        }
+        job_listings.append(job_info)
+
+    return job_listings
+
+# Streamlit app
+st.title("Resume-Based Job Recommender")
+
+uploaded_file = st.file_uploader("Upload your resume (PDF format)", type=["pdf"])
+
+if uploaded_file is not None:
+    # Extract text from the uploaded resume
+    resume_text = extract_text_from_pdf(uploaded_file)
+    st.text_area("Extracted Resume Text", resume_text, height=300)
+
+    # Extract skills and location
+    skills, location = extract_skills_and_location(resume_text)
+    st.write("### Extracted Skills")
+    st.write(", ".join(skills) if skills else "No skills found.")
+    st.write("### Extracted Location")
+    st.write(location if location else "No location found.")
+
+    # Prompt user to enter their preferred job title if necessary
+    job_title = st.text_input("Enter the job title (e.g., 'Data Scientist')", value=skills[0] if skills else "")
+
+    if st.button("Find Jobs"):
+        if location and job_title:
+            job_listings = fetch_job_listings(job_title, location)
+            if job_listings:
+                st.write("### Job Listings")
+                for job in job_listings:
+                    st.write(f"**Title**: {job['title']}")
+                    st.write(f"**Company**: {job['company']}")
+                    st.write(f"**Location**: {job['location']}")
+                    st.write(f"**Posted**: {job['date_posted']}")
+                    st.write(f"**Description**: {job['description']}")
+                    st.write(f"[Job Link]({job['url']})")
+                    st.write("---")
+            else:
+                st.write("No job listings found for the given job title and location.")
+        else:
+            st.warning("Please ensure your resume has a detectable location and skills or enter them manually.")