app.py

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

def scrape_jobs(link):
    # Send a GET request to the carrier website
    response = requests.get(link)

    # Parse the HTML content using BeautifulSoup
    soup = BeautifulSoup(response.content, 'html.parser')

    # Find all the job listings on the page
    job_elements = soup.find_all('div', class_='job-listing')

    jobs = []
    for job_element in job_elements:
        # Extract relevant information from each job listing
        job_title = job_element.find('h2', class_='job-title').text.strip()
        job_location = job_element.find('span', class_='job-location').text.strip()
        job_description = job_element.find('div', class_='job-description').text.strip()

        # Store the job information in a dictionary
        job = {
            'Title': job_title,
            'Location': job_location,
            'Description': job_description
        }

        jobs.append(job)

    return jobs

def export_to_excel(jobs, filename):
    # Create a DataFrame from the job data
    df = pd.DataFrame(jobs)

    # Save the DataFrame to an Excel file
    df.to_excel(filename, index=False)

def job_listing_scraper(link):
    job_listings = scrape_jobs(link)
    output_file = "job_listings.xlsx"
    export_to_excel(job_listings, output_file)
    return f"Job listings scraped successfully! Saved to {output_file}"

# Define the Gradio interface
interface = gr.Interface(
    fn=job_listing_scraper,
    inputs="text",
    outputs="text",
    title="Job Listing Scraper",
    description="Enter the link to the carrier website and click 'Submit' to scrape job listings and save them to an Excel file.",
    examples=[["https://example.com/carrier"]],
)

# Run the Gradio interface
interface.launch()