Zillow Property Data Scrape

# Specify the base Docker image. You can read more about
# the available images at https://docs.apify.com/sdk/js/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node:20 AS builder

# Check preinstalled packages
RUN npm ls crawlee apify puppeteer playwright

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY package*.json ./

# Install all dependencies. Don't audit to speed up the installation.
RUN npm install --include=dev --audit=false

# Next, copy the source files using the user set
# in the base image.
COPY . ./

# Install all dependencies and build the project.
# Don't audit to speed up the installation.
RUN npm run build

# Create final image
FROM apify/actor-node:20

# Check preinstalled packages
RUN npm ls crawlee apify puppeteer playwright

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY package*.json ./

# Install NPM packages, skip optional and development dependencies to
# keep the image small. Avoid logging too much and print the dependency
# tree for debugging
RUN npm --quiet set progress=false \
    && npm install --omit=dev --omit=optional \
    && echo "Installed NPM packages:" \
    && (npm list --omit=dev --all || true) \
    && echo "Node.js version:" \
    && node --version \
    && echo "NPM version:" \
    && npm --version \
    && rm -r ~/.npm

# Copy built JS files from builder image
COPY --from=builder /usr/src/app/dist ./dist

# Next, copy the remaining files and directories with the source code.
# Since we do this after NPM install, quick build will be really fast
# for most source file changes.
COPY . ./

# Create and run as a non-root user.
RUN adduser -h /home/apify -D apify && \
    chown -R apify:apify ./
USER apify

# Run the image.
CMD npm run start:prod --silent

{
    "actorSpecification": 1,
    "name": "my-actor",
    "title": "Scrape single page in TypeScript",
    "description": "Scrape data from single page with provided URL.",
    "version": "0.0",
    "meta": {
        "templateId": "ts-start"
    },
    "input": "./input_schema.json",
    "dockerfile": "./Dockerfile"
}

{
  "title": "Zillow Scraper Input",
  "description": "Input for scraping Zillow property by address.",
  "type": "object",
  "schemaVersion": 1,
  "properties": {
    "address": {
      "title": "Property Address",
      "type": "string",
      "description": "Enter the full property address (e.g., '17 Zelma Dr, Greenville, SC 29617').",
      "editor": "textfield",
      "minLength": 5
    }
  },
  "required": ["address"]
}

1import { Actor, Dataset } from 'apify';
2
3await Actor.init();
4
5interface Input {
6    address: string;
7}
8
9const input = await Actor.getInput<Input>();
10if (!input?.address) throw new Error("Missing input!");
11
12const { address } = input;
13
14const zpidScraperInput = {
15    multiple_input_box: address,
16    scrape_type: "property_addresses",
17};
18
19const zpidRun = await Actor.call('sorower/zillow-scrape-address-url-zpid', zpidScraperInput);
20if (!zpidRun.defaultDatasetId) throw new Error('No default dataset ID from the ZPID scraper.');
21
22const zpidDataset = await Dataset.open(zpidRun.defaultDatasetId);
23const { items } = await zpidDataset.getData();
24
25if (!items.length || !items[0].PropertyZillowURL) {
26    throw new Error('PropertyZillowURL not found');
27}
28
29const originalUrl = items[0].PropertyZillowURL;
30const zpidMatch = originalUrl.match(/(\d+)_zpid/);
31if (!zpidMatch) throw new Error('ZPID not found');
32const zpid = zpidMatch[1];
33
34function formatAddress(address: string): string {
35    return address.replace(/,/g, '').replace(/\s+/g, '-').replace(/-{2,}/g, '-').trim();
36}
37
38const formattedAddress = formatAddress(address);
39const finalUrl = `https://www.zillow.com/homedetails/${formattedAddress}/${zpid}_zpid/`;
40
41const detailScraperInput = {
42    extractBuildingUnits: 'all',
43    propertyStatus: 'FOR_SALE',
44    startUrls: [
45        {
46            url: finalUrl,
47            method: 'GET',
48        },
49    ],
50};
51
52const detailRun = await Actor.call('maxcopell/zillow-detail-scraper', detailScraperInput);
53if (!detailRun.defaultDatasetId) throw new Error('No default dataset ID from the detail scraper.');
54
55const detailDataset = await Dataset.open(detailRun.defaultDatasetId);
56const detailItems = await detailDataset.getData();
57
58await Actor.pushData({
59    inputAddress: address,
60    detailData: detailItems.items[0],
61});
62
63await Actor.exit();

# configurations
.idea
.vscode

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

# dist folder
dist

root = true

[*]
indent_style = space
indent_size = 4
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
end_of_line = lf

{
    "root": true,
    "env": {
        "browser": true,
        "es2020": true,
        "node": true
    },
    "extends": [
        "@apify/eslint-config-ts"
    ],
    "parserOptions": {
        "project": "./tsconfig.json",
        "ecmaVersion": 2020
    },
    "ignorePatterns": [
        "node_modules",
        "dist",
        "**/*.d.ts"
    ]
}

# This file tells Git which files shouldn't be added to source control

.idea
.vscode
.zed
storage
apify_storage
crawlee_storage
node_modules
dist
tsconfig.tsbuildinfo
storage/*
!storage/key_value_stores
storage/key_value_stores/*
!storage/key_value_stores/default
storage/key_value_stores/default/*
!storage/key_value_stores/default/INPUT.json

{
    "name": "ts-start",
    "version": "0.0.1",
    "type": "module",
    "description": "This is an example of an Apify actor.",
    "engines": {
        "node": ">=18.0.0"
    },
    "dependencies": {
        "apify": "^3.2.6",
        "axios": "^1.5.0",
        "cheerio": "^1.0.0-rc.12"
    },
    "devDependencies": {
        "@apify/eslint-config-ts": "^0.3.0",
        "@apify/tsconfig": "^0.1.0",
        "@typescript-eslint/eslint-plugin": "^7.18.0",
        "@typescript-eslint/parser": "^7.18.0",
        "eslint": "^8.50.0",
        "tsx": "^4.6.2",
        "typescript": "^5.3.3"
    },
    "scripts": {
        "start": "npm run start:dev",
        "start:prod": "node dist/main.js",
        "start:dev": "tsx src/main.ts",
        "build": "tsc",
        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
    },
    "author": "It's not you it's me",
    "license": "ISC"
}

{
    "extends": "@apify/tsconfig",
    "compilerOptions": {
        "module": "NodeNext",
        "moduleResolution": "NodeNext",
        "target": "ES2022",
        "outDir": "dist",
        "noUnusedLocals": false,
        "skipLibCheck": true,
        "lib": ["DOM"]
    },
    "include": [
        "./src/**/*"
    ]
}