Job Board Scraping with CAPTCHA Handling Using CaptchaAI

Job boards like Indeed, LinkedIn, and Glassdoor deploy CAPTCHAs when they detect automated access patterns. Recruitment platforms, market researchers, and HR analytics tools need reliable CAPTCHA solving to collect job listing data at scale.

CAPTCHAs on Major Job Boards

Job Board Scraper with CAPTCHA Handling

import requests
import time
import re
from bs4 import BeautifulSoup

CAPTCHAAI_KEY = "YOUR_API_KEY"
CAPTCHAAI_URL = "https://ocr.captchaai.com"


def solve_captcha(method, sitekey, pageurl, **kwargs):
    data = {
        "key": CAPTCHAAI_KEY,
        "method": method,
        "googlekey": sitekey,
        "pageurl": pageurl,
        "json": 1,
    }
    data.update(kwargs)
    resp = requests.post(f"{CAPTCHAAI_URL}/in.php", data=data)
    task_id = resp.json()["request"]

    for _ in range(60):
        time.sleep(5)
        result = requests.get(f"{CAPTCHAAI_URL}/res.php", params={
            "key": CAPTCHAAI_KEY, "action": "get",
            "id": task_id, "json": 1,
        })
        r = result.json()
        if r["request"] != "CAPCHA_NOT_READY":
            return r["request"]
    raise TimeoutError("Solve timeout")


class JobBoardScraper:
    def __init__(self, proxy=None):
        self.session = requests.Session()
        if proxy:
            self.session.proxies = {"http": proxy, "https": proxy}
        self.session.headers.update({
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
            "AppleWebKit/537.36 Chrome/126.0.0.0 Safari/537.36",
            "Accept-Language": "en-US,en;q=0.9",
        })

    def search_jobs(self, base_url, query, location, pages=5):
        """Search job listings across multiple pages."""
        all_jobs = []

        for page in range(pages):
            url = f"{base_url}/jobs?q={query}&l={location}&start={page * 10}"
            resp = self.session.get(url, timeout=30)

            # Check for CAPTCHA
            if self._has_captcha(resp.text):
                resp = self._solve_and_retry(resp.text, url)

            if resp.status_code == 200:
                jobs = self._parse_listings(resp.text)
                all_jobs.extend(jobs)
                print(f"Page {page + 1}: {len(jobs)} jobs found")
            else:
                print(f"Page {page + 1}: Request failed ({resp.status_code})")

            time.sleep(3)  # Rate limit

        return all_jobs

    def _has_captcha(self, html):
        indicators = [
            'data-sitekey=',
            'g-recaptcha',
            'cf-turnstile',
            'captcha-delivery',
        ]
        return any(ind in html.lower() for ind in indicators)

    def _solve_and_retry(self, html, url):
        # Try reCAPTCHA first
        match = re.search(r'data-sitekey="([^"]+)"', html)
        if match:
            sitekey = match.group(1)

            # Detect Turnstile vs reCAPTCHA
            if 'cf-turnstile' in html:
                token = solve_captcha("turnstile", sitekey, url)
                field = "cf-turnstile-response"
            else:
                token = solve_captcha("userrecaptcha", sitekey, url)
                field = "g-recaptcha-response"

            return self.session.post(url, data={field: token})

        return self.session.get(url)

    def _parse_listings(self, html):
        soup = BeautifulSoup(html, "html.parser")
        jobs = []

        for card in soup.select(".job_seen_beacon, .jobsearch-ResultsList > li"):
            title_el = card.select_one("h2 a, .jobTitle a")
            company_el = card.select_one(".companyName, [data-testid='company-name']")
            location_el = card.select_one(".companyLocation, [data-testid='text-location']")
            salary_el = card.select_one(".salary-snippet, .estimated-salary")

            if title_el:
                jobs.append({
                    "title": title_el.get_text(strip=True),
                    "company": company_el.get_text(strip=True) if company_el else "",
                    "location": location_el.get_text(strip=True) if location_el else "",
                    "salary": salary_el.get_text(strip=True) if salary_el else "",
                    "url": title_el.get("href", ""),
                })

        return jobs


# Usage
scraper = JobBoardScraper(
    proxy="http://user:pass@residential.proxy.com:5000"
)
jobs = scraper.search_jobs(
    base_url="https://jobs.example.com",
    query="python developer",
    location="New York",
    pages=10,
)
print(f"Total jobs collected: {len(jobs)}")

Salary Data Collection

import csv


def collect_salary_data(titles, locations, output_file):
    """Collect salary data across job titles and locations."""
    scraper = JobBoardScraper(
        proxy="http://user:pass@residential.proxy.com:5000"
    )

    results = []
    for title in titles:
        for location in locations:
            try:
                jobs = scraper.search_jobs(
                    "https://jobs.example.com",
                    title, location, pages=3,
                )
                salaries = [j["salary"] for j in jobs if j["salary"]]
                results.append({
                    "title": title,
                    "location": location,
                    "listings": len(jobs),
                    "with_salary": len(salaries),
                    "salary_samples": "; ".join(salaries[:5]),
                })
                time.sleep(5)
            except Exception as e:
                results.append({
                    "title": title,
                    "location": location,
                    "error": str(e),
                })

    with open(output_file, "w", newline="") as f:
        writer = csv.DictWriter(
            f, fieldnames=["title", "location", "listings",
                           "with_salary", "salary_samples", "error"],
        )
        writer.writeheader()
        writer.writerows(results)

    return results


# Collect salary data for market analysis
collect_salary_data(
    titles=["Data Engineer", "ML Engineer", "DevOps Engineer"],
    locations=["San Francisco", "New York", "Austin", "Remote"],
    output_file="salary_data.csv",
)

Stealth-Configuredion Tips for Job Boards

Troubleshooting

FAQ

How many job listings can I scrape per day?

With rotating residential proxies and proper delays, 500-2000 pages per domain is achievable without hitting persistent CAPTCHAs.

Do job boards block scraping?

Most job boards have terms discouraging automated access but vary in enforcement. CAPTCHAs are their primary defense, which CaptchaAI handles.

Which proxy type works best for job boards?

Rotating residential proxies are the best balance of cost and success rate. Datacenter IPs are frequently blocked by LinkedIn and Glassdoor.

Related Guides

• Rotating Residential Proxies
• Proxy Quality Affects Solve Rate
• Sticky vs Rotating Sessions

Collect job market data at scale — get your CaptchaAI key for automated CAPTCHA solving.