import gradio as gr
import requests
from bs4 import BeautifulSoup
import pandas as pd

def scrape_jobs(url):
    # Fetch the webpage
    response = requests.get(url)
    response.encoding = 'utf-8'  # Ensure correct encoding
    
    # Parse the HTML content
    soup = BeautifulSoup(response.text, 'html.parser')
    
    # Extract job titles and descriptions
    jobs = soup.find_all('article', class_='js-job-item')
    
    job_titles = [job.find('a', class_='js-job-link').text.strip() for job in jobs]
    job_descriptions = [job.find('p').text.strip() for job in jobs]
    
    # Store the extracted data in a Pandas DataFrame
    data = {
        'Job Title': job_titles,
        'Job Description': job_descriptions
    }
    df = pd.DataFrame(data)
    
    # Convert DataFrame to HTML for display in Gradio
    return df.to_html()

# Gradio interface
iface = gr.Interface(
    fn=scrape_jobs, 
    inputs=gr.Textbox(label="Enter Job Search URL"), 
    outputs="html",
    title="104 人力銀行職缺爬取",
    description="Enter a URL to scrape job titles and descriptions."
)

# Launch the Gradio app
iface.launch()