Xplate

Try for free

Developed by

DevFlexi

0.0 (0)

Pricing

Pay per usage

Monthly users

Runs succeeded

>99%

Last modified

a month ago

Automation

Open source

.actor/Dockerfile

1# Specify the base Docker image. You can read more about
2# the available images at https://docs.apify.com/sdk/js/docs/guides/docker-images
3# You can also use any other image from Docker Hub.
4FROM apify/actor-node:20 AS builder
5
6# Check preinstalled packages
7RUN npm ls crawlee apify puppeteer playwright
8
9# Copy just package.json and package-lock.json
10# to speed up the build using Docker layer cache.
11COPY package*.json ./
12
13# Install all dependencies. Don't audit to speed up the installation.
14RUN npm install --include=dev --audit=false
15
16# Next, copy the source files using the user set
17# in the base image.
18COPY . ./
19
20# Install all dependencies and build the project.
21# Don't audit to speed up the installation.
22RUN npm run build
23
24# Create final image
25FROM apify/actor-node:20
26
27# Check preinstalled packages
28RUN npm ls crawlee apify puppeteer playwright
29
30# Copy just package.json and package-lock.json
31# to speed up the build using Docker layer cache.
32COPY package*.json ./
33
34# Install NPM packages, skip optional and development dependencies to
35# keep the image small. Avoid logging too much and print the dependency
36# tree for debugging
37RUN npm --quiet set progress=false \
38    && npm install --omit=dev --omit=optional \
39    && echo "Installed NPM packages:" \
40    && (npm list --omit=dev --all || true) \
41    && echo "Node.js version:" \
42    && node --version \
43    && echo "NPM version:" \
44    && npm --version \
45    && rm -r ~/.npm
46
47# Copy built JS files from builder image
48COPY --from=builder /usr/src/app/dist ./dist
49
50# Next, copy the remaining files and directories with the source code.
51# Since we do this after NPM install, quick build will be really fast
52# for most source file changes.
53COPY . ./
54
55# Create and run as a non-root user.
56RUN adduser -h /home/apify -D apify && \
57    chown -R apify:apify ./
58USER apify
59
60# Run the image.
61CMD npm run start:prod --silent

.actor/actor.json

1{
2    "actorSpecification": 1,
3    "name": "xplate-license-plate-scraper",
4    "title": "Xplate License Plate Scraper",
5    "description": "An Apify Actor that scrapes license plate data from Xplate using a provided page number input. It extracts images, prices, durations, and details (emirate, character, number) from the specified page.",
6    "version": "0.0",
7    "meta": {
8        "templateId": "ts-start"
9    },
10    "input": "./input_schema.json",
11    "dockerfile": "./Dockerfile"
12}

.actor/input_schema.json

1{
2  "title": "Scrape data from Xplate",
3  "type": "object",
4  "schemaVersion": 1,
5  "properties": {
6    "pageNumber": {
7      "title": "Page Number",
8      "type": "integer",
9      "description": "The page number to scrape from Xplate.",
10      "editor": "number",
11      "default": 1
12    }
13  },
14  "required": ["pageNumber"]
15}

src/main.ts

1import axios from 'axios';
2import * as cheerio from 'cheerio';
3import { Actor } from 'apify';
4
5await Actor.init();
6
7interface Input {
8    pageNumber: number;
9}
10
11// Get input (expecting a JSON object like: { "pageNumber": 3 })
12const input = await Actor.getInput<Input>();
13if (!input) throw new Error("Input is missing! Please provide a JSON object with a 'pageNumber' property.");
14const pageNumber: number = input.pageNumber || 1;
15console.log(`Scraping page number: ${pageNumber}`);
16
17// Construct the URL using the provided page number.
18const targetUrl = `https://xplate.com/en/numbers/license-plates?page=${pageNumber}`;
19
20// Define your selectors configuration.
21const XPLATES_SELECTORS = {
22    SOURCE_NAME: 'xplate',
23    ERROR_MESSAGE_SELECTOR: 'div.alert.alert-warning.text-center.m-0.rounded-3',
24    ALL_PLATES: 'div[class="number-card"]',
25    PLATE_PRICE: 'span.custom-red.dm-white',
26    PLATE_DURATION: 'div.d-flex.align-items-center.meta > div > span',
27    PLATE_LINK: 'a[class="p-0 m-0 lower-part default-dark-btn px-1 text-center bordered dm-bordered"]',
28    URL: targetUrl,
29    SKIP_CONFIGURATION: {
30        CALL_FOR_PRICE: 'Call For Price',
31        FEATURED: 'featured',
32        CHARACTER_HAS_NOC: 'noc',
33    },
34};
35
36interface Plate {
37    image: string;
38    price: string;
39    duration: string;
40    emirate: string;
41    character: string;
42    number: string;
43    source: string;
44}
45
46// Fetch the HTML content of the page using axios.
47const response = await axios.get(targetUrl, {
48    headers: {
49        // Include cookies if required by the site.
50        'Cookie': 'XSRF-TOKEN=...; xplate_session=...'
51    }
52});
53const html = response.data;
54const $ = cheerio.load(html);
55
56// Check for an error message on the page.
57if ($(XPLATES_SELECTORS.ERROR_MESSAGE_SELECTOR).length) {
58    console.error('Error message found on the page, aborting.');
59    await Actor.exit();
60}
61
62// Select all plate elements (skipping the first element if necessary).
63const plateElements = Array.from($(XPLATES_SELECTORS.ALL_PLATES)).slice(1);
64console.log(`Found ${plateElements.length} plate elements.`);
65
66const plates: Plate[] = [];
67
68// Extract information for each plate element.
69for (const plateEl of plateElements) {
70    const plateElement = $(plateEl);
71    const imgSrc = plateElement.find('img').attr('data-src') || '';
72    const price = plateElement.find(XPLATES_SELECTORS.PLATE_PRICE).text().trim() || '';
73    const duration = plateElement.find(XPLATES_SELECTORS.PLATE_DURATION).text().trim() || '';
74    const url = plateElement.find(XPLATES_SELECTORS.PLATE_LINK).attr('href') || '';
75
76    // Use regex to extract additional details from the URL.
77    const emirateMatch = url.match(/\/(\d+)-(.+?)-code-/);
78    const characterMatch = url.match(/-code-(.+?)-plate-number-/);
79    const numberMatch = url.match(/plate-number-(\d+)/);
80    const emirate = emirateMatch ? emirateMatch[2] : '';
81    const character = characterMatch ? characterMatch[1] : '';
82    const number = numberMatch ? numberMatch[1] : '';
83
84    const newPlate: Plate = {
85        image: imgSrc,
86        price,
87        duration,
88        emirate,
89        character,
90        number,
91        source: XPLATES_SELECTORS.SOURCE_NAME,
92    };
93
94    plates.push(newPlate);
95}
96
97// Log the extracted plates.
98console.log(JSON.stringify(plates, null, 2));
99
100// Save the results to the default dataset.
101await Actor.pushData(plates);
102
103await Actor.exit();

.dockerignore

1# configurations
2.idea
3.vscode
4
5# crawlee and apify storage folders
6apify_storage
7crawlee_storage
8storage
9
10# installed files
11node_modules
12
13# git folder
14.git
15
16# dist folder
17dist

.editorconfig

1root = true
2
3[*]
4indent_style = space
5indent_size = 4
6charset = utf-8
7trim_trailing_whitespace = true
8insert_final_newline = true
9end_of_line = lf

.eslintrc

1{
2    "root": true,
3    "env": {
4        "browser": true,
5        "es2020": true,
6        "node": true
7    },
8    "extends": [
9        "@apify/eslint-config-ts"
10    ],
11    "parserOptions": {
12        "project": "./tsconfig.json",
13        "ecmaVersion": 2020
14    },
15    "ignorePatterns": [
16        "node_modules",
17        "dist",
18        "**/*.d.ts"
19    ]
20}

.gitignore

1# This file tells Git which files shouldn't be added to source control
2
3.idea
4.vscode
5storage
6apify_storage
7crawlee_storage
8node_modules
9dist
10tsconfig.tsbuildinfo
11storage/*
12!storage/key_value_stores
13storage/key_value_stores/*
14!storage/key_value_stores/default
15storage/key_value_stores/default/*
16!storage/key_value_stores/default/INPUT.json

package.json

1{
2    "name": "ts-start",
3    "version": "0.0.1",
4    "type": "module",
5    "description": "This is an example of an Apify actor.",
6    "engines": {
7        "node": ">=18.0.0"
8    },
9    "dependencies": {
10        "apify": "^3.2.6",
11        "axios": "^1.5.0",
12        "cheerio": "^1.0.0-rc.12"
13    },
14    "devDependencies": {
15        "@apify/eslint-config-ts": "^0.3.0",
16        "@apify/tsconfig": "^0.1.0",
17        "@typescript-eslint/eslint-plugin": "^7.18.0",
18        "@typescript-eslint/parser": "^7.18.0",
19        "eslint": "^8.50.0",
20        "tsx": "^4.6.2",
21        "typescript": "^5.3.3"
22    },
23    "scripts": {
24        "start": "npm run start:dev",
25        "start:prod": "node dist/main.js",
26        "start:dev": "tsx src/main.ts",
27        "build": "tsc",
28        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
29    },
30    "author": "It's not you it's me",
31    "license": "ISC"
32}

tsconfig.json

1{
2    "extends": "@apify/tsconfig",
3    "compilerOptions": {
4        "module": "NodeNext",
5        "moduleResolution": "NodeNext",
6        "target": "ES2022",
7        "outDir": "dist",
8        "noUnusedLocals": false,
9        "skipLibCheck": true,
10        "lib": ["DOM"]
11    },
12    "include": [
13        "./src/**/*"
14    ]
15}

Pricing

Pricing model

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage.

Email

contact2353/my-actor-2

TML

Xplate

yousef-alsakkaf/DevFlexi

An Apify Actor that scrapes license plate data from Xplate using axios and cheerio. It extracts images, prices, durations, and details (emirate, character, number) from the site. Provide JSON input with a "pageNumber" property to specify the page to scrape.