Healthcare Data Collection Behind CAPTCHA Walls

Healthcare data portals — provider directories, drug pricing databases, and clinical trial registries — use CAPTCHAs to prevent automated data harvesting. Researchers and health-tech platforms need this data for analytics, compliance, and informed decision-making.

Where CAPTCHAs Appear

Provider Directory Scraper

import requests
import time
import re
import base64
from bs4 import BeautifulSoup
import csv

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


def solve_recaptcha(sitekey, pageurl):
    resp = requests.post(f"{CAPTCHAAI_URL}/in.php", data={
        "key": CAPTCHAAI_KEY, "method": "userrecaptcha",
        "googlekey": sitekey, "pageurl": pageurl, "json": 1,
    })
    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,
        })
        data = result.json()
        if data["request"] != "CAPCHA_NOT_READY":
            return data["request"]
    raise TimeoutError("Timeout")


def solve_image_captcha(image_bytes):
    img_b64 = base64.b64encode(image_bytes).decode()
    resp = requests.post(f"{CAPTCHAAI_URL}/in.php", data={
        "key": CAPTCHAAI_KEY, "method": "base64",
        "body": img_b64, "json": 1,
    })
    task_id = resp.json()["request"]
    for _ in range(20):
        time.sleep(3)
        result = requests.get(f"{CAPTCHAAI_URL}/res.php", params={
            "key": CAPTCHAAI_KEY, "action": "get",
            "id": task_id, "json": 1,
        })
        data = result.json()
        if data["request"] != "CAPCHA_NOT_READY":
            return data["request"]
    raise TimeoutError("Timeout")


class HealthcareDataCollector:
    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",
        })

    def search_providers(self, portal_url, specialty, location, sitekey=None):
        """Search provider directory with CAPTCHA handling."""
        resp = self.session.get(portal_url, timeout=30)

        data = {"specialty": specialty, "location": location}

        # Handle CAPTCHA
        if sitekey:
            token = solve_recaptcha(sitekey, portal_url)
            data["g-recaptcha-response"] = token
        else:
            captcha_img = re.search(r'src="(/captcha[^"]+)"', resp.text)
            if captcha_img:
                img_url = portal_url.rstrip("/") + captcha_img.group(1)
                img = self.session.get(img_url)
                data["captcha"] = solve_image_captcha(img.content)

        resp = self.session.post(portal_url, data=data)
        return self._parse_providers(resp.text)

    def lookup_drug_prices(self, pricing_url, drug_name, zip_code, sitekey):
        """Look up drug prices with CAPTCHA solving."""
        # Load search page
        self.session.get(pricing_url)

        # Solve CAPTCHA
        token = solve_recaptcha(sitekey, pricing_url)

        resp = self.session.post(pricing_url, data={
            "drug": drug_name,
            "zip": zip_code,
            "g-recaptcha-response": token,
        })

        if resp.status_code == 200:
            return self._parse_prices(resp.text)
        return []

    def batch_provider_lookup(self, portal_url, specialties, locations, output_file):
        """Batch search across specialties and locations."""
        all_providers = []

        for specialty in specialties:
            for location in locations:
                try:
                    providers = self.search_providers(
                        portal_url, specialty, location,
                    )
                    for p in providers:
                        p["specialty_search"] = specialty
                        p["location_search"] = location
                    all_providers.extend(providers)
                    print(f"{specialty} / {location}: {len(providers)} providers")
                    time.sleep(5)
                except Exception as e:
                    print(f"Error: {specialty} / {location}: {e}")

        # Export
        if all_providers:
            keys = all_providers[0].keys()
            with open(output_file, "w", newline="", encoding="utf-8") as f:
                writer = csv.DictWriter(f, fieldnames=keys)
                writer.writeheader()
                writer.writerows(all_providers)

        return all_providers

    def _parse_providers(self, html):
        soup = BeautifulSoup(html, "html.parser")
        providers = []
        for card in soup.select(".provider-card, .doctor-result, tr.provider"):
            providers.append({
                "name": self._text(card, ".name, .provider-name"),
                "specialty": self._text(card, ".specialty"),
                "address": self._text(card, ".address"),
                "phone": self._text(card, ".phone"),
                "accepting": self._text(card, ".accepting-patients"),
            })
        return providers

    def _parse_prices(self, html):
        soup = BeautifulSoup(html, "html.parser")
        prices = []
        for row in soup.select(".pharmacy-row, .price-result"):
            prices.append({
                "pharmacy": self._text(row, ".pharmacy-name"),
                "price": self._text(row, ".price, .drug-price"),
                "quantity": self._text(row, ".quantity"),
            })
        return prices

    def _text(self, el, selector):
        found = el.select_one(selector)
        return found.get_text(strip=True) if found else ""


# Usage
collector = HealthcareDataCollector(
    proxy="http://user:pass@residential.proxy.com:5000"
)

# Provider search
providers = collector.search_providers(
    portal_url="https://provider-directory.example.com/search",
    specialty="Cardiology",
    location="New York, NY",
)

# Drug pricing
prices = collector.lookup_drug_prices(
    pricing_url="https://drug-prices.example.com/compare",
    drug_name="atorvastatin",
    zip_code="10001",
    sitekey="6Lc_xxxxxxx",
)

Clinical Trial Data Collection

def collect_clinical_trials(search_url, condition, sitekey):
    """Collect clinical trial data for a medical condition."""
    collector = HealthcareDataCollector(
        proxy="http://user:pass@residential.proxy.com:5000"
    )

    token = solve_recaptcha(sitekey, search_url)
    resp = collector.session.post(search_url, data={
        "condition": condition,
        "status": "recruiting",
        "g-recaptcha-response": token,
    })

    if resp.status_code != 200:
        return []

    soup = BeautifulSoup(resp.text, "html.parser")
    trials = []
    for item in soup.select(".trial-item, .study-result"):
        trials.append({
            "title": collector._text(item, ".title, h3"),
            "status": collector._text(item, ".status"),
            "sponsor": collector._text(item, ".sponsor"),
            "phase": collector._text(item, ".phase"),
            "enrollment": collector._text(item, ".enrollment"),
            "location": collector._text(item, ".location"),
        })

    return trials

Data Privacy Considerations

Important: Never attempt to collect protected health information (PHI). Focus only on publicly available, non-patient-specific data.

Troubleshooting

FAQ

Is collecting healthcare pricing data allowed?

Drug pricing transparency is encouraged by regulation (CMS Price Transparency Rule). Public provider directory data is generally accessible.

Can I compare drug prices across pharmacies?

Yes. Services like GoodRx do this at scale. CaptchaAI handles the CAPTCHAs that pricing portals use to limit automated access.

How do I handle HIPAA when scraping healthcare sites?

HIPAA applies to protected health information (PHI). Public data like provider directories, drug prices, and clinical trial registries are not PHI. Never scrape individual patient records.

Related Guides

• Government Portal Automation
• Academic Research Scraping
• Rotating Residential Proxies

Collect healthcare data efficiently — get your CaptchaAI key and automate provider and pricing lookups.