如何使用Scrapeless Browserless构建Google Maps爬虫：2026年的终极AI准备指南

mkdir google-maps-pro && cd google-maps-pro
npm init -y
npm install puppeteer-core dotenv
npm install -D tsx typescript @types/node

SCRAPELESS_API_KEY=your_key_here

import "dotenv/config";
import puppeteer from "puppeteer-core";

function connectionURL(sessionName: string, proxyCountry = "US", sessionTTL = 600) {
  const qs = new URLSearchParams({
    token: process.env.SCRAPELESS_API_KEY!,
    proxyCountry,
    sessionTTL: String(sessionTTL),
    sessionName,
  });
  return `wss://browser.scrapeless.com/api/v2/browser?${qs.toString()}`;
}

async function openBrowser(sessionName: string) {
  return puppeteer.connect({
    browserWSEndpoint: connectionURL(sessionName),
    defaultViewport: null,
  });
}

function kmPerDegLng(lat: number) { return 111.32 * Math.cos((lat * Math.PI) / 180); }
function kmPerDegLat() { return 111.32; }

function buildGrid(centerLat: number, centerLng: number, cellRadiusKm: number, maxCells: number) {
  const side = Math.max(1, Math.floor(Math.sqrt(maxCells)));
  const cells: { lat: number; lng: number }[] = [];
  const stepLat = (cellRadiusKm * 2) / kmPerDegLat();
  const stepLng = (cellRadiusKm * 2) / kmPerDegLng(centerLat);
  const offset = (side - 1) / 2;
  for (let i = 0; i < side; i++) {
    for (let j = 0; j < side; j++) {
      cells.push({
        lat: centerLat + (i - offset) * stepLat,
        lng: centerLng + (j - offset) * stepLng,
      });
      if (cells.length >= maxCells) return cells;
    }
  }
  return cells;
}

function searchUrlForCell(query: string, lat: number, lng: number) {
  const q = encodeURIComponent(query).replace(/%20/g, "+");
  return `https://www.google.com/maps/search/${q}/@${lat.toFixed(6)},${lng.toFixed(6)},15z`;
}

async function collectSearchResults(page: Page, searchUrl: string, target: number) {
  await page.goto(searchUrl, { waitUntil: "domcontentloaded", timeout: 60000 });
  await page.waitForSelector('div[role="feed"], h1.DUwDvf', { timeout: 25000 });

  let last = 0, stable = 0;
  for (let i = 0; i < 40; i++) {
    const n = await page.$$eval(".Nv2PK", (els) => els.length);
    if (n >= target) break;

**稳定计数器模式**（三次滚动没有新结果意味着信息流结束）每次都优于固定休眠。如果信息流真的停止加载，等待更长时间没有帮助。

`placeId` 嵌入在每个 URL 中，位于 `!1s0x...:0x....` 后面。这是去重的键。

---

## 第四步 — 奇怪的谷歌地图渲染问题

这一点让我花了大部分时间来理清。

如果你直接导航到一个地方的 URL，比如 `https://www.google.com/maps/place/Haraz+Coffee+House/...`，谷歌地图会渲染出一个简化版的信息面板。`h1` 标题在。这有评分。 但是评论数、开放时间表、服务属性、照片 — 一半的内容缺失或为空。整页的 DOM 大约有三千个字符。

如果你改为导航到搜索结果，并点击同一个地方的卡片，你会得到完整的丰富面板。相同的 URL，完全不同的渲染。

解决方法是：**总是通过搜索 URL 进入，点击你想要的地方卡片，并等待面板。**

```typescript
const clicked = await page.evaluate((placeName) => {
  const cards = document.querySelectorAll(".Nv2PK a.hfpxzc");
  for (const c of Array.from(cards)) {
    if (c.getAttribute("aria-label") === placeName) {
      (c as HTMLElement).click();
      return true;
    }
  }
  return false;
}, hit.name);

await page.waitForSelector("h1.DUwDvf", { timeout: 15000 });

const overview = await page.evaluate(() => {
  const $ = (s: string) => document.querySelector(s) as HTMLElement | null;
  const txt = (s: string) => $(s)?.textContent?.trim() || null;

  return {
    title: txt("h1.DUwDvf"),
    totalScore: parseFloat(txt('div.F7nice span[aria-hidden="true"]') || "") || null,
    categoryName: txt("button.DkEaL"),
    address: txt('button[data-item-id="address"] .Io6YTe'),
    phone: txt('button[data-item-id*="phone"] .Io6YTe'),
    website: txt('a[data-item-id="authority"] .Io6YTe'),
    plusCode: txt('button[data-item-id="oloc"] .Io6YTe'),
  };
});

const at = page.url().match(/@(-?\d+\.\d+),(-?\d+\.\d+)/);
const location = at ? { lat: parseFloat(at[1]), lng: parseFloat(at[2]) } : null;
const placeId = page.url().match(/!1s(0x[0-9a-f]+:0x[0-9a-f]+)/i)?.[1] ?? null;

const reviews = await page.evaluate((max) => {
  const cards = Array.from(document.querySelectorAll(".Nv2PK"));
  return cards.slice(0, max).map((c) => ({
    name: c.querySelector(".d4r55")?.textContent?.trim() || null,
    text: c.querySelector(".wiI7pd")?.textContent?.trim() || null,
    publishedAtDate: c.querySelector(".rsqaWe")?.textContent?.trim() || null,
    stars: (() => {
      const m = (c.querySelector(".kvMYJc")?.getAttribute("aria-label") || "").match(/(\d)/);
      return m ? parseInt(m[1], 10) : null;
    })(),
    responseFromOwnerText: c.querySelector(".CDe7pd .wiI7pd")?.textContent?.trim() || null,
  }));
}, 30);

for (let attempt = 1; attempt <= 3; attempt++) {
  const eb = await openBrowser(`gmp-enrich-${attempt}`);
  const ep = await eb.newPage();
  try {
    await ep.goto(searchUrl, { waitUntil: "domcontentloaded", timeout: 60000 });
    await ep.waitForSelector('div[role="feed"]', { timeout: 20000 });
    const place = await enrichPlaceOnSearchPage(ep, hit, cfg);
    if (place.title) return place;
  } finally {
    await ep.close();
    await eb.close();
  }
  await new Promise(r => setTimeout(r, 2000));
}

{
  "title": "Haraz Coffee House",
  "placeId": "0x8644b52f8462f95f:0xa572bbcb1887b9bb",
  "cid": "11921797644567427515",
  "url": "https://www.google.com/maps/place/Haraz+Coffee+House/...",
  "rank": 2,
  "address": "500 W Martin Luther King Jr Blvd Suite A, Austin, TX 78701",
  "plusCode": "77J4+WJ Austin, Texas",
  "location": { "lat": 30.2823385, "lng": -97.7434096 },
  "phone": "(512) 243-5667",
  "phoneUnformatted": "5122435667",
  "website": "harazcoffeehouse.com",
  "domain": "harazcoffeehouse.com",
  "categoryName": "咖啡店",
  "categories": ["咖啡店"],
  "totalScore": 4.7,
  "reviewsCount": 47239,
  "openingHours": [
    { "day": "星期一", "hours": "早上7点到晚上10点" },
    { "day": "星期二", "hours": "早上7点到晚上10点" },
    "... 还有5天"
  ],
  "additionalInfo": {
    "服务选项": [
      { "name": "堂食", "value": true },
      { "name": "外卖", "value": true }
    ],
    "无障碍设施": [
      { "name": "轮椅可进入的入口", "value": true }
    ],
    "亮点": [{ "name": "绝佳的咖啡", "value": true }],
    "... 还有10个部分": {}
  },
  "images": [
    "https://lh3.googleusercontent.com/.../=w1600-h1600",
    "... 还有4个URLs"
  ],
  "reviews": [
    {
      "name": "Maria T",
      "text": "奥斯汀最好的拿铁，毋庸置疑...",
      "publishedAtDate": "14小时前",
      "stars": 5,
      "reviewerPhotoUrl": "https://lh3.googleusercontent.com/...",
      "responseFromOwnerText": "谢谢，Maria!"
    },
    "... 还有9条评论"
  ],
  "menu": [],
  "questionsAndAnswers": [],
  "popularTimesLiveText": null,
  "scrapedAt": "2026-04-13T13:23:18.450Z"
}