giris
Try for free
No credit card required
Go to Store
giris
bets10/giris
Try for free
No credit card required
Bets10, en yüksek oranlar ve özel bonuslarla kazanç dolu dünyaya adım atmanızı sağlıyor! Güvenilir altyapısı sayesinde kesintisiz eğlencenin tadını çıkarın!
.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 /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
56# Run the image.
57CMD npm run start:prod --silent
.actor/actor.json
1{
2 "actorSpecification": 1,
3 "name": "my-actor",
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}
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();
.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}
Developer
Maintained by Community
Actor Metrics
1 monthly user
-
0 No stars yet
Created in Feb 2025
Modified 11 hours ago
Categories