CAPTCHA Handling for GIS and Mapping Data Extraction

Government GIS portals, county assessor systems, and mapping platforms protect geospatial queries with Image and OCR CAPTCHAs. These portals serve parcel boundaries, zoning designations, flood zones, and property assessments — data that's valuable for real estate analysis, urban planning, and environmental research. Here's how to handle the CAPTCHAs.

CAPTCHA Patterns on GIS Portals

GIS Data Extractor

import requests
import base64
import time
import re

class GISDataExtractor:
    def __init__(self, api_key):
        self.api_key = api_key
        self.session = requests.Session()
        self.session.headers.update({
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
        })

    def lookup_parcel(self, portal_url, parcel_id):
        """Look up parcel data by ID, solving CAPTCHAs as needed."""
        response = self.session.get(
            f"{portal_url}/parcel", params={"id": parcel_id}
        )

        if self._has_image_captcha(response.text):
            captcha_url = self._extract_captcha_url(response.text, portal_url)
            captcha_text = self._solve_captcha(captcha_url)

            # Re-submit with solved CAPTCHA
            response = self.session.post(f"{portal_url}/parcel", data={
                "id": parcel_id,
                "captcha": captcha_text,
                **self._extract_hidden_fields(response.text)
            })

        return self._parse_parcel_data(response.text)

    def search_by_address(self, portal_url, address):
        """Search GIS records by street address."""
        response = self.session.get(
            f"{portal_url}/search", params={"address": address}
        )

        if self._has_image_captcha(response.text):
            captcha_url = self._extract_captcha_url(response.text, portal_url)
            captcha_text = self._solve_captcha(captcha_url)

            response = self.session.post(f"{portal_url}/search", data={
                "address": address,
                "captcha": captcha_text,
                **self._extract_hidden_fields(response.text)
            })

        return self._parse_search_results(response.text)

    def bulk_extract(self, portal_url, parcel_ids, delay=3):
        """Extract data for multiple parcels with rate limiting."""
        results = {}

        for parcel_id in parcel_ids:
            try:
                results[parcel_id] = self.lookup_parcel(portal_url, parcel_id)
            except Exception as e:
                results[parcel_id] = {"error": str(e)}
            time.sleep(delay)

        return results

    def _has_image_captcha(self, html):
        return bool(re.search(
            r'captcha|verification.?image|security.?code',
            html, re.IGNORECASE
        ))

    def _extract_captcha_url(self, html, base_url):
        from bs4 import BeautifulSoup
        from urllib.parse import urljoin
        soup = BeautifulSoup(html, "html.parser")

        img = (
            soup.find("img", attrs={"src": lambda s: s and "captcha" in s.lower()}) or
            soup.find("img", {"id": re.compile(r"captcha", re.I)}) or
            soup.find("img", {"class": re.compile(r"captcha", re.I)})
        )

        if img and img.get("src"):
            return urljoin(base_url, img["src"])
        raise ValueError("CAPTCHA image not found")

    def _solve_captcha(self, captcha_url):
        """Download and solve image CAPTCHA."""
        img_response = self.session.get(captcha_url)
        img_base64 = base64.b64encode(img_response.content).decode("utf-8")

        resp = requests.post("https://ocr.captchaai.com/in.php", data={
            "key": self.api_key,
            "method": "base64",
            "body": img_base64,
            "json": 1
        })
        task_id = resp.json()["request"]

        for _ in range(30):
            time.sleep(3)
            result = requests.get("https://ocr.captchaai.com/res.php", params={
                "key": self.api_key,
                "action": "get",
                "id": task_id,
                "json": 1
            })
            data = result.json()
            if data["status"] == 1:
                return data["request"]

        raise TimeoutError("CAPTCHA solve timed out")

    def _extract_hidden_fields(self, html):
        from bs4 import BeautifulSoup
        soup = BeautifulSoup(html, "html.parser")
        fields = {}
        for inp in soup.select("input[type='hidden']"):
            name = inp.get("name")
            if name:
                fields[name] = inp.get("value", "")
        return fields

    def _parse_parcel_data(self, html):
        from bs4 import BeautifulSoup
        soup = BeautifulSoup(html, "html.parser")
        return {
            "parcel_id": soup.select_one(".parcel-id, #parcelId")?.text?.strip(),
            "owner": soup.select_one(".owner, .owner-name")?.text?.strip(),
            "address": soup.select_one(".address, .situs")?.text?.strip(),
            "zoning": soup.select_one(".zoning, .zone-code")?.text?.strip(),
            "acreage": soup.select_one(".acreage, .area")?.text?.strip(),
            "assessed_value": soup.select_one(".assessed, .value")?.text?.strip(),
            "land_use": soup.select_one(".land-use, .use-code")?.text?.strip()
        }

    def _parse_search_results(self, html):
        from bs4 import BeautifulSoup
        soup = BeautifulSoup(html, "html.parser")
        results = []
        for row in soup.select(".result-row, tr.parcel"):
            results.append({
                "parcel_id": row.select_one(".parcel-id")?.text?.strip(),
                "address": row.select_one(".address")?.text?.strip(),
                "owner": row.select_one(".owner")?.text?.strip()
            })
        return results


# Usage
extractor = GISDataExtractor("YOUR_API_KEY")

# Single parcel lookup
parcel = extractor.lookup_parcel(
    "https://gis.county.example.gov",
    "12-34-567-890"
)
print(f"Owner: {parcel['owner']}, Zoning: {parcel['zoning']}")

# Bulk extraction
parcels = extractor.bulk_extract(
    "https://gis.county.example.gov",
    ["12-34-567-890", "12-34-567-891", "12-34-567-892"]
)

Coordinate-Based Extraction (JavaScript)

class GISExtractor {
  constructor(apiKey) {
    this.apiKey = apiKey;
  }

  async extractByCoordinates(portalUrl, lat, lng) {
    const url = `${portalUrl}/identify?lat=${lat}&lng=${lng}`;
    const response = await fetch(url);
    const html = await response.text();

    if (this.hasCaptcha(html)) {
      return this.solveAndExtract(portalUrl, html, { lat, lng });
    }

    return this.parseGISData(html);
  }

  async extractRegion(portalUrl, bounds, gridSize = 0.01) {
    const results = [];
    const { north, south, east, west } = bounds;

    for (let lat = south; lat <= north; lat += gridSize) {
      for (let lng = west; lng <= east; lng += gridSize) {
        try {
          const data = await this.extractByCoordinates(portalUrl, lat, lng);
          if (data.parcelId) results.push(data);
        } catch (error) {
          console.error(`Failed at ${lat},${lng}: ${error.message}`);
        }
        // Rate limit
        await new Promise(r => setTimeout(r, 2000));
      }
    }

    return results;
  }

  hasCaptcha(html) {
    return /captcha|verification.?image|security.?code/i.test(html);
  }

  async solveAndExtract(portalUrl, html, params) {
    const imgMatch = html.match(/src="([^"]*captcha[^"]*)"/i);
    if (!imgMatch) throw new Error('CAPTCHA image not found');

    const imgUrl = new URL(imgMatch[1], portalUrl).href;
    const imgResp = await fetch(imgUrl);
    const buffer = await imgResp.arrayBuffer();
    const base64 = Buffer.from(buffer).toString('base64');

    const submitResp = await fetch('https://ocr.captchaai.com/in.php', {
      method: 'POST',
      body: new URLSearchParams({
        key: this.apiKey,
        method: 'base64',
        body: base64,
        json: '1'
      })
    });
    const { request: taskId } = await submitResp.json();

    for (let i = 0; i < 30; i++) {
      await new Promise(r => setTimeout(r, 3000));
      const result = await fetch(
        `https://ocr.captchaai.com/res.php?key=${this.apiKey}&action=get&id=${taskId}&json=1`
      );
      const data = await result.json();
      if (data.status === 1) {
        const response = await fetch(portalUrl, {
          method: 'POST',
          body: new URLSearchParams({
            ...params,
            captcha: data.request
          })
        });
        return this.parseGISData(await response.text());
      }
    }
    throw new Error('CAPTCHA solve timed out');
  }

  parseGISData(html) {
    return {
      parcelId: html.match(/parcel.?id[^>]*>([^<]+)/i)?.[1]?.trim(),
      zoning: html.match(/zon(?:e|ing)[^>]*>([^<]+)/i)?.[1]?.trim(),
      acreage: html.match(/acreage|area[^>]*>([^<]+)/i)?.[1]?.trim(),
      landUse: html.match(/land.?use[^>]*>([^<]+)/i)?.[1]?.trim()
    };
  }
}

// Usage
const gis = new GISExtractor('YOUR_API_KEY');

// Single coordinate lookup
const data = await gis.extractByCoordinates(
  'https://gis.county.example.gov',
  34.0522, -118.2437
);

// Extract entire region
const region = await gis.extractRegion('https://gis.county.example.gov', {
  north: 34.10, south: 34.00, east: -118.20, west: -118.30
});

CAPTCHA Parameters for GIS Portals

Troubleshooting

FAQ

Why do GIS portals use old-style image CAPTCHAs?

Government GIS systems are often built on legacy platforms that predate modern CAPTCHA services. Budget constraints and long procurement cycles mean these older CAPTCHAs persist.

How should I handle county-specific CAPTCHA formats?

Each county may use different CAPTCHA implementations. Use CaptchaAI's textinstructions parameter to describe the specific format — for example, "5 uppercase letters" or "solve the math equation."

Can I extract shapefile or GeoJSON data behind CAPTCHAs?

If the portal offers downloadable spatial data behind a CAPTCHA, solve the CAPTCHA to access the download link. CaptchaAI handles the CAPTCHA; then download the file normally.

Next Steps

Extract GIS data reliably — get your CaptchaAI API key and handle government portal CAPTCHAs automatically.