How to Scrape Charter Global | IT Services & Job Board Scraper

from playwright.sync_api import sync_playwright

def run():
    with sync_playwright() as p:
        # Launching browser with headless mode
        browser = p.chromium.launch(headless=True)
        context = browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/120.0.0.0')
        page = context.new_page()
        
        # Navigating to the careers page which requires JS execution
        page.goto('https://www.charterglobal.com/careers/', wait_until='networkidle')
        
        # Wait for the job listing container to appear
        page.wait_for_selector('.job-title', timeout=10000)
        
        # Extracting data from job cards
        jobs = page.query_selector_all('.job-listing-container')
        for job in jobs:
            title = job.query_selector('.job-title').inner_text()
            location = job.query_selector('.location').inner_text()
            print(f'Job Open: {title} | Location: {location}')
            
        browser.close()

run()

import scrapy

class CharterGlobalSpider(scrapy.Spider):
    name = 'charter_spider'
    allowed_domains = ['charterglobal.com']
    start_urls = ['https://www.charterglobal.com/blog/']

    def parse(self, response):
        # Iterate through blog posts on the page
        for post in response.css('article'):
            yield {
                'title': post.css('h2.entry-title a::text').get(),
                'url': post.css('h2.entry-title a::attr(href)').get(),
                'date': post.css('time.entry-date::text').get()
            }

        # Handle pagination using 'Next' link
        next_page = response.css('a.next.page-numbers::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();
  
  // Mimic a real user browser session
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/118.0.0.0 Safari/537.36');
  
  try {
    await page.goto('https://www.charterglobal.com/insights/', { waitUntil: 'networkidle2' });
    
    // Extract insight titles
    const insights = await page.evaluate(() => {
      const elements = document.querySelectorAll('h2.entry-title');
      return Array.from(elements).map(el => el.innerText.trim());
    });
    
    console.log('Latest Insights:', insights);
  } catch (err) {
    console.error('Error fetching page:', err);
  }

  await browser.close();
})();