GIS 和地图数据提取的验证码处理 (实用指南)

政府 GIS 门户、县评估系统和地图平台通过图像和 OCR 验证码保护地理空间查询。这些门户提供地块边界、分区指定、洪泛区和财产评估等数据，这些数据对于房地产分析、城市规划和环境研究非常有价值。以下是处理验证码的方法。

GIS 门户上的验证码模式

门户型	验证码类型	扳机
县 GIS/assessor	图片文字验证码	包裹搜索查询
国家地理空间门户	自定义验证码	数据下载请求
美国地质调查局数据门户	reCAPTCHA v2	批量数据访问
市政分区图	图片验证码	重复查找属性
环境数据库	数学验证码	报告生成
洪泛区查找	图片文字验证码	地址查询

地理信息系统数据提取器

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")

        def text_or_none(node):
            return node.text.strip() if node and node.text else None

        return {
            "parcel_id": text_or_none(soup.select_one(".parcel-id, #parcelId")),
            "owner": text_or_none(soup.select_one(".owner, .owner-name")),
            "address": text_or_none(soup.select_one(".address, .situs")),
            "zoning": text_or_none(soup.select_one(".zoning, .zone-code")),
            "acreage": text_or_none(soup.select_one(".acreage, .area")),
            "assessed_value": text_or_none(soup.select_one(".assessed, .value")),
            "land_use": text_or_none(soup.select_one(".land-use, .use-code"))
        }

    def _parse_search_results(self, html):
        from bs4 import BeautifulSoup
        soup = BeautifulSoup(html, "html.parser")

        def text_or_none(node):
            return node.text.strip() if node and node.text else None

        results = []
        for row in soup.select(".result-row, tr.parcel"):
            results.append({
                "parcel_id": text_or_none(row.select_one(".parcel-id")),
                "address": text_or_none(row.select_one(".address")),
                "owner": text_or_none(row.select_one(".owner"))
            })
        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"]
)

基于坐标的提取 (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
});

GIS 门户的验证码参数

范围	价值	使用案例
`method`	`base64`	标准图片验证码
`numeric`	`1`	纯数字验证码
`min_len`	`4`	当字符数已知时
`max_len`	`6`	当字符数已知时
`language`	`0`	英文/Latin字符
`textinstructions`	风俗	数学验证码或格式化代码

预批提取检查表

在开始大型收集运行之前验证地图视口、区域过滤器和分页控件。
存储标准化坐标有效负载和原始目标响应，以便提取错误保持可调试性。
当验证码密度激增时暂停批次，而不是让重试隐藏目标端行为更改。

故障排除

问题	原因	处理方式
验证码图像加载损坏	需要会话 cookie	首先加载搜索页面
已解决的文本被拒绝	区分大小写	添加`case_sensitive=1`参数
门户返回不同的验证码	特定于会话的验证码	在同一会话中下载并解决
验证码后无包裹数据	缺少隐藏表单字段	提交前提取所有隐藏输入

常问问题

为什么 GIS 门户使用旧式图像验证码？

政府 GIS 系统通常构建在现代验证码服务出现之前的遗留平台上。预算限制和漫长的采购周期意味着这些旧的验证码仍然存在。

我应该如何处理特定于县的验证码格式？

每个县可能使用不同的验证码实施方式。使用CaptchaAI的textinstructions参数来描述具体格式——例如“5个大写字母”或“求解数学方程”。

我可以提取验证码后面的 shapefile 或 GeoJSON 数据吗？

如果门户在验证码后面提供可下载的空间数据，请解决验证码以访问下载链接。 CaptchaAI 处理验证码；然后就可以正常下载文件了。

下一步

可靠地提取 GIS 数据 —获取您的 CaptchaAI API 密钥并自动处理政府门户验证码。

后续阅读

CaptchaAI 快速上手：5 分钟解决你的第一个验证码
使用 API 解决 reCAPTCHA v2：分步实战指南
如何使用 API 解决 Cloudflare Turnstile
如何使用 API 解决 GeeTest v3 问题