Scraping Job Listings

{
  "jobs": {
    "selector": ".job-card",
    "type": "obj",
    "multiple": true,
    "children": {
      "title": { "selector": "h2, h3, .job-title", "type": "text" },
      "company": { "selector": ".company-name", "type": "text" },
      "location": { "selector": ".location", "type": "text" },
      "salary": { "selector": ".salary", "type": "text" },
      "description": { "selector": ".job-snippet, .description", "type": "text" },
      "posted": { "selector": ".date, time", "type": "text" },
      "job_type": { "selector": ".job-type, .employment-type", "type": "text" },
      "url": { "selector": "a", "type": "link" }
    }
  },
  "total_results": { "selector": ".results-count, .job-count", "type": "text" },
  "next_page": { "selector": "a.next, a[rel='next']", "type": "link" }
}

import requests
import json
import time

extract_rules = {
    "jobs": {
        "selector": ".job-card",
        "type": "obj",
        "multiple": True,
        "children": {
            "title": {"selector": "h2, h3", "type": "text"},
            "company": {"selector": ".company-name", "type": "text"},
            "location": {"selector": ".location", "type": "text"},
            "salary": {"selector": ".salary", "type": "text"},
            "url": {"selector": "a", "type": "link"}
        }
    },
    "next_page": {"selector": "a[rel='next']", "type": "link"}
}

def scrape_jobs(search_url):
    response = requests.post("https://api.ujeebu.com/scrape",
        headers={
            "ApiKey": "YOUR_API_KEY",
            "Content-Type": "application/json"
        },
        json={
            "url": search_url,
            "js": True,
            "wait_for": ".job-card",
            "extract_rules": extract_rules
        })
    return response.json()["result"]

# Search for Python developer jobs
data = scrape_jobs("https://example-jobboard.com/search?q=python+developer")
print(f"Found {len(data['jobs'])} jobs")

for job in data['jobs'][:5]:
    print(f"\n{job['title']}")
    print(f"  Company: {job['company']}")
    print(f"  Location: {job['location']}")
    print(f"  Salary: {job.get('salary', 'Not listed')}")

const axios = require('axios');

// Generic extract rules - adapt selectors to your target job board
const extractRules = {
  jobs: {
    selector: '.job-card',
    type: 'obj',
    multiple: true,
    children: {
      title: { selector: 'h2, h3, .job-title', type: 'text' },
      company: { selector: '.company-name', type: 'text' },
      location: { selector: '.location', type: 'text' },
      salary: { selector: '.salary', type: 'text' },
      url: { selector: 'a', type: 'link' }
    }
  },
  next_page: { selector: "a[rel='next']", type: 'link' }
};

async function scrapeJobs(searchUrl) {
  const response = await axios.post('https://api.ujeebu.com/scrape', {
    url: searchUrl,
    js: true,
    wait_for: '.job-card',
    extract_rules: extractRules
  }, {
    headers: {
      'ApiKey': 'YOUR_API_KEY',
      'Content-Type': 'application/json'
    }
  });
  return response.data.result;
}

// Scrape developer jobs
const data = await scrapeJobs('https://example-jobboard.com/search?q=developer');
console.log(`Found ${data.jobs.length} jobs`);

data.jobs.slice(0, 5).forEach(job => {
  console.log(`${job.title} at ${job.company}`);
  console.log(`  Salary: ${job.salary || 'Not listed'}`);
});

def scrape_all_jobs(base_url, max_pages=10):
    """Scrape jobs across multiple pages."""
    all_jobs = []
    current_url = base_url
    page = 1

    while current_url and page <= max_pages:
        print(f"Scraping page {page}...")
        data = scrape_jobs(current_url)

        jobs = data.get('jobs', [])
        if not jobs:
            break

        all_jobs.extend(jobs)

        # Get next page URL
        next_page = data.get('next_page')
        if next_page:
            current_url = next_page if next_page.startswith('http') else base_url + next_page
        else:
            break

        page += 1
        time.sleep(2)  # Rate limiting

    return all_jobs

# Scrape up to 10 pages
all_jobs = scrape_all_jobs("https://example-jobboard.com/search?q=developer", max_pages=10)
print(f"Total jobs collected: {len(all_jobs)}")