Sanaa picture catch.

Try for free

Developed by

Arab chat

0.0 (0)

Pricing

Pay per usage

Monthly users

Runs succeeded

>99%

Last modified

8 months ago

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# Copy just package.json and package-lock.json
7# to speed up the build using Docker layer cache.
8COPY package*.json ./
9
10# Install all dependencies. Don't audit to speed up the installation.
11RUN npm install --include=dev --audit=false
12
13# Next, copy the source files using the user set
14# in the base image.
15COPY . ./
16
17# Install all dependencies and build the project.
18# Don't audit to speed up the installation.
19RUN npm run build
20
21# Create final image
22FROM apify/actor-node:20
23
24# Copy just package.json and package-lock.json
25# to speed up the build using Docker layer cache.
26COPY package*.json ./
27
28# Install NPM packages, skip optional and development dependencies to
29# keep the image small. Avoid logging too much and print the dependency
30# tree for debugging
31RUN npm --quiet set progress=false \
32    && npm install --omit=dev --omit=optional \
33    && echo "Installed NPM packages:" \
34    && (npm list --omit=dev --all || true) \
35    && echo "Node.js version:" \
36    && node --version \
37    && echo "NPM version:" \
38    && npm --version \
39    && rm -r ~/.npm
40
41# Copy built JS files from builder image
42COPY --from=builder /usr/src/app/dist ./dist
43
44# Next, copy the remaining files and directories with the source code.
45# Since we do this after NPM install, quick build will be really fast
46# for most source file changes.
47COPY . ./
48
49
50# Run the image.
51CMD npm run start:prod --silent

.actor/actor.json

1{
2    "actorSpecification": 1,
3    "name": "my-actor-1",
4    "title": "Scrape single page in TypeScript",
5    "description": "Scrape data from single page with provided URL.",
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 a web page",
3    "type": "object",
4    "schemaVersion": 1,
5    "properties": {
6        "url": {
7        "title": "URL of the page",
8        "type": "string",
9        "description": "The URL of website you want to get the data from.",
10        "editor": "textfield",
11        "prefill": "https://www.apify.com"
12        }
13    },
14    "required": ["url"]
15}

.dockerignore

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

.gitignore

1storage
2apify_storage
3crawlee_storage
4node_modules
5dist
6tsconfig.tsbuildinfo
7storage/*
8!storage/key_value_stores
9storage/key_value_stores/*
10!storage/key_value_stores/default
11storage/key_value_stores/default/*
12!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": "^3.1.10",
11        "axios": "^1.5.0",
12        "cheerio": "^1.0.0-rc.12"
13    },
14    "devDependencies": {
15        "@apify/tsconfig": "^0.1.0",
16        "tsx": "^4.6.2",
17        "typescript": "^5.3.3"
18    },
19    "scripts": {
20        "start": "npm run start:dev",
21        "start:prod": "node dist/main.js",
22        "start:dev": "tsx src/main.ts",
23        "build": "tsc",
24        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
25    },
26    "author": "It's not you it's me",
27    "license": "ISC"
28}

src/main.ts

1// Axios - Promise based HTTP client for the browser and node.js (Read more at https://axios-http.com/docs/intro).
2import axios from 'axios';
3// Cheerio - The fast, flexible & elegant library for parsing and manipulating HTML and XML (Read more at https://cheerio.js.org/).
4import * as cheerio from 'cheerio';
5// Apify SDK - toolkit for building Apify Actors (Read more at https://docs.apify.com/sdk/js/).
6import { Actor } from 'apify';
7
8// this is ESM project, and as such, it requires you to specify extensions in your relative imports
9// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
10// note that we need to use `.js` even when inside TS files
11// import { router } from './routes.js';
12
13// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init().
14await Actor.init();
15
16interface Input {
17    url: string;
18}
19// Structure of input is defined in input_schema.json
20const input = await Actor.getInput<Input>();
21if (!input) throw new Error("Input is missing!");
22const { url } = input;
23
24// Fetch the HTML content of the page.
25const response = await axios.get(url);
26
27// Parse the downloaded HTML with Cheerio to enable data extraction.
28const $ = cheerio.load(response.data);
29
30// Extract all headings from the page (tag name and text).
31const headings: { level: string, text: string }[] = [];
32$("h1, h2, h3, h4, h5, h6").each((_i, element) => {
33    const headingObject = {
34        level: $(element).prop("tagName").toLowerCase(),
35        text: $(element).text(),
36    };
37    console.log("Extracted heading", headingObject);
38    headings.push(headingObject);
39});
40
41// Save headings to Dataset - a table-like storage.
42await Actor.pushData(headings);
43
44// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit().
45await Actor.exit();

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.

Catch Surf® USA Scraper

mshopik/catch-surfr-usa-scraper

Scrape Catch Surf® USA and extract data on swimming from catchsurf.com. Our Catch Surf® USA API lets you crawl product information and pricing. The saved data can be downloaded as HTML, JSON, CSV, Excel, and XML.