Update app.py

app.py

@@ -1,139 +1,116 @@
-import streamlit as st
-from langchain_google_genai import ChatGoogleGenerativeAI
-import re
-
-def generate_question(role, topic, difficulty_level):
-    prompt = f"Generate an interview question for the role of {role} on the topic of {topic} with difficulty level {difficulty_level}."
-    llm = ChatGoogleGenerativeAI(model="gemini-pro", google_api_key=st.secrets["GOOGLE_API_KEY"])
-    response = llm.invoke(prompt)
-    response = response.content
- 
-    return response
-
-def evaluate_answer(question, user_answer):
-    prompt = f"Question: {question}\nUser's Answer: {user_answer}\nEvaluate the answer and provide feedback. Also, provide the best possible answer."
-    llm = ChatGoogleGenerativeAI(model="gemini-pro", google_api_key=st.secrets["GOOGLE_API_KEY"])
-    response = llm.invoke(prompt)
-    response = response.content
- 
-    return response
-
-# ----------------------
-def generate_question(role, topic, difficulty_level):
-    prompt = f"Generate an interview question for the role of {role} on the topic of {topic} with difficulty level {difficulty_level}."
-    llm = ChatGoogleGenerativeAI(model="gemini-pro", google_api_key=st.secrets["GOOGLE_API_KEY"])
-    response = llm.invoke(prompt)
-    response = response.content
- 
-    return response
-
-def evaluate_answer(question, user_answer):
-    prompt = f"Question: {question}\nUser's Answer: {user_answer}\nEvaluate the answer, give a score out of 100, and provide feedback. Also, provide the best possible answer."
-    llm = ChatGoogleGenerativeAI(model="gemini-pro", google_api_key=st.secrets["GOOGLE_API_KEY"])
-    response = llm.invoke(prompt)
-   
-    evaluation = response.content
-    # Extract score and feedback from the evaluation
-     # Extract score using regular expressions
-    score_match = re.search(r'(\d+)/100', evaluation)
-    score = int(score_match.group(1)) if score_match else 0
-
-    # Extract feedback
-    feedback = evaluation.split('\n', 1)[1] if '\n' in evaluation else evaluation
-    return score, feedback
-
-def generate_report():
-    st.write("### Interview Report")
-    for i in range(st.session_state['total_questions']):
-        st.write(f"**Question {i+1}:** {st.session_state['questions'][i]}")
-        st.write(f"**Your Answer:** {st.session_state['answers'][i]}")
-        st.write(f"**Score:** {st.session_state['scores'][i]}")
-        st.write(f"**Feedback:** {st.session_state['feedback'][i]}")
-        st.write("---")
-
-# Initialize session state
-if 'questions' not in st.session_state:
-    st.session_state['questions'] = []
-if 'answers' not in st.session_state:
-    st.session_state['answers'] = []
-if 'feedback' not in st.session_state:
-    st.session_state['feedback'] = []
-if 'scores' not in st.session_state:
-    st.session_state['scores'] = []
-if 'current_question' not in st.session_state:
-    st.session_state['current_question'] = 0
-if 'total_questions' not in st.session_state:
-    st.session_state['total_questions'] = 10
-if 'question_answered' not in st.session_state:
-    st.session_state['question_answered'] = False
-if 'interview_started' not in st.session_state:
-    st.session_state['interview_started'] = False
-
-st.title("Mock Interview Bot")
-
-if not st.session_state['interview_started']:
-    roles_and_topics = {      
-  
-    "Front-End Developer": ["HTML/CSS", "JavaScript and Frameworks (React, Angular, Vue.js)", "Responsive Design", "Browser Compatibility"],
-    "Back-End Developer": ["Server-Side Languages (Node.js, Python, Ruby, PHP)", "Database Management (SQL, NoSQL)", "API Development", "Server and Hosting Management"],
-    "Full-Stack Developer": ["Combination of Front-End and Back-End Topics", "Integration of Systems", "DevOps Basics"],
-    "Mobile Developer": ["Android Development (Java, Kotlin)", "iOS Development (Swift, Objective-C)", "Cross-Platform Development (Flutter, React Native)"],
-    "Data Scientist": ["Statistical Analysis", "Machine Learning Algorithms", "Data Wrangling and Cleaning", "Data Visualization"],
-    "Data Analyst": ["Data Collection and Processing", "SQL and Database Querying", "Data Visualization Tools (Tableau, Power BI)", "Basic Statistics"],
-    "Machine Learning Engineer": ["Supervised and Unsupervised Learning", "Model Deployment", "Deep Learning", "Natural Language Processing"],
-    "DevOps Engineer": ["Continuous Integration/Continuous Deployment (CI/CD)", "Containerization (Docker, Kubernetes)", "Infrastructure as Code (Terraform, Ansible)", "Cloud Platforms (AWS, Azure, Google Cloud)"],
-    "Cloud Engineer": ["Cloud Architecture", "Cloud Services (Compute, Storage, Networking)", "Security in the Cloud", "Cost Management"],
-    "Cybersecurity Analyst": ["Threat Detection and Mitigation", "Security Protocols and Encryption", "Network Security", "Incident Response"],
-    "Penetration Tester": ["Vulnerability Assessment", "Ethical Hacking Techniques", "Security Tools (Metasploit, Burp Suite)", "Report Writing and Documentation"],
-    "Project Manager": ["Project Planning and Scheduling", "Risk Management", "Agile and Scrum Methodologies", "Stakeholder Communication"],
-    "UX/UI Designer": ["User Research", "Wireframing and Prototyping", "Design Principles", "Usability Testing"],
-    "Quality Assurance (QA) Engineer": ["Testing Methodologies", "Automation Testing", "Bug Tracking", "Performance Testing"],
-    "Blockchain Developer": ["Blockchain Fundamentals", "Smart Contracts", "Cryptographic Algorithms", "Decentralized Applications (DApps)"],
-    "Digital Marketing Specialist": ["SEO/SEM", "Social Media Marketing", "Content Marketing", "Analytics and Reporting"],
-    "AI Research Scientist": ["AI Theory", "Algorithm Development", "Neural Networks", "Natural Language Processing"],
-    "AI Engineer": ["AI Model Deployment", "Machine Learning Engineering", "Deep Learning", "AI Tools and Frameworks"],
-    "Generative AI Specialist (GenAI)": ["Generative Models", "GANs (Generative Adversarial Networks)", "Creative AI Applications", "Ethics in AI"],
-    "Generative Business Intelligence Specialist (GenBI)": ["Automated Data Analysis", "Business Intelligence Tools", "Predictive Analytics", "AI in Business Strategy"]
-
-
-    }
-
-
-
-
-    
-    role = st.selectbox('Select Role', list(roles_and_topics.keys()))
-    topic = st.selectbox('Select Topic', roles_and_topics[role])
-    difficulty_level = st.selectbox("Select difficulty level:", ["Easy", "Medium", "Hard"])
-
-    if st.button("Start Interview"):
-        if role and topic and difficulty_level:
-            st.session_state['questions'] = [generate_question(role, topic, difficulty_level) for _ in range(st.session_state['total_questions'])]
-            st.session_state['current_question'] = 0
-            st.session_state['interview_started'] = True
-            st.session_state['question_answered'] = False
-
-if st.session_state['interview_started']:
-    current_question = st.session_state['current_question']
-    if current_question < st.session_state['total_questions']:
-        st.write(f"Question {current_question + 1}: {st.session_state['questions'][current_question]}")
-        
-        if not st.session_state['question_answered']:
-            answer = st.text_area("Your Answer:", key=f"answer_{current_question}")
-            if st.button("Submit Answer"):
-                if answer:
-                    st.session_state['answers'].append(answer)
-                    score, feedback = evaluate_answer(st.session_state['questions'][current_question], answer)
-                    st.session_state['scores'].append(score)
-                    st.session_state['feedback'].append(feedback)
-                    st.session_state['question_answered'] = True
-                    st.write(f"Score: {score}")
-                    st.write(f"Feedback: {feedback}")
-        
-        if st.session_state['question_answered']:
-            if st.button("Next Question"):
-                st.session_state['current_question'] += 1
-                st.session_state['question_answered'] = False
-    else:
-        st.write("Interview Complete! Generating Report...")
-        generate_report()
+import gradio as gr
+import logging
+from linkedin_jobs_scraper import LinkedinScraper
+from linkedin_jobs_scraper.events import Events, EventData, EventMetrics
+from linkedin_jobs_scraper.query import Query, QueryOptions, QueryFilters
+from linkedin_jobs_scraper.filters import RelevanceFilters, TimeFilters, OnSiteOrRemoteFilters
+import pandas as pd
+
+# Configure logging
+logging.basicConfig(filename="job_scraper.log", level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
+
+# Initialize job data storage
+job_data = []
+
+# Event Handlers
+def on_data(data: EventData):
+    job_data.append({
+        'Date Posted': data.date,
+        'Title': data.title,
+        'Company': data.company,
+        'Location': data.location,
+        'Job Link': data.link,
+        'Description Length': len(data.description),
+        'Description': data.description,
+    })
+
+def on_end():
+    logging.info("[ON_END] Scraping completed.")
+
+# Scraper function
+def scrape_jobs(query, locations, time_filter):
+    global job_data
+    try:
+        job_data = []
+
+        scraper = LinkedinScraper(
+            chrome_executable_path=None,
+            chrome_binary_location=None,
+            chrome_options=None,
+            headless=True,
+            max_workers=5,
+            slow_mo=0.8,
+            page_load_timeout=100,
+        )
+
+        scraper.on(Events.DATA, on_data)
+        scraper.on(Events.END, on_end)
+
+        if time_filter == "From Past Month":
+            time_filter = TimeFilters.MONTH
+        elif time_filter == "From Last 24 Hours":
+            time_filter = TimeFilters.DAY
+        else:
+            time_filter = TimeFilters.MONTH  
+
+        queries = [
+            Query(
+                query=query,
+                options=QueryOptions(
+                    locations=locations.split(','),
+                    apply_link=True,
+                    skip_promoted_jobs=False,
+                    page_offset=0,
+                    limit=100,
+                    filters=QueryFilters(
+                        # relevance=RelevanceFilters.RECENT,
+                        time=time_filter,
+                    ),
+                ),
+            ),
+        ]
+
+        scraper.run(queries)
+        
+        if job_data:
+            df = pd.DataFrame(job_data) 
+            message = f"Jobs ({len(job_data)}) data successfully scraped."
+            logging.info(message)
+            return df, message
+        else:
+            logging.warning("No job data found.")
+            return pd.DataFrame(), 'No jobs found.'
+
+    except Exception as e:
+        # Handle specific exceptions and log detailed information
+        logging.error(f"An error occurred during scraping: {e}", exc_info=True)
+        message = f"An error occurred during scraping: {e}. Please check the logs for more details."
+        return None, message
+
+def gradio_interface(query, locations, time_filter):
+    df, message = scrape_jobs(query, locations, time_filter)
+    return df, message
+
+# App Layout
+iface = gr.Interface(
+    fn=gradio_interface,
+    inputs=[
+        gr.Textbox(label="Job Query", placeholder="e.g., Data Scientist", value="Blockchain developers"),
+        gr.Textbox(label="Locations (comma-separated)", placeholder="e.g., United States, India", value="United States, United Kingdom, India"),
+        gr.Dropdown(
+            label="Time Filter",
+            choices=["From Past Month", "From Last 24 Hours"],
+            value="From Last 24 Hours",  # Default option
+            type="value",
+            ),
+    ],
+    outputs=[
+        gr.Dataframe(label="Job Results", headers=['Date','Company', 'ApplyLink'], interactive=True),
+        gr.Textbox(label="Message"),
+    ],
+    title="Job Scraper",
+    description="Enter a job query and locations to scrape job postings and display the results in a table.",
+)
+
+if __name__ == "__main__":
+    iface.launch()