Arab chat all
Try for free
No credit card required
View all Actors
Arab chat all
alhemaqani111/arab-chat-all
Try for free
No credit card required
Arab chat Free for everyone
.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
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 NPM packages, skip optional and development dependencies to
11# keep the image small. Avoid logging too much and print the dependency
12# tree for debugging
13RUN npm --quiet set progress=false \
14 && npm install --omit=dev --omit=optional \
15 && echo "Installed NPM packages:" \
16 && (npm list --omit=dev --all || true) \
17 && echo "Node.js version:" \
18 && node --version \
19 && echo "NPM version:" \
20 && npm --version \
21 && rm -r ~/.npm
22
23# Next, copy the remaining files and directories with the source code.
24# Since we do this after NPM install, quick build will be really fast
25# for most source file changes.
26COPY . ./
27
28
29# Run the image.
30CMD npm start --silent
.actor/actor.json
1{
2 "actorSpecification": 1,
3 "name": "my-actor",
4 "title": "Project Cheerio Crawler Javascript",
5 "description": "Crawlee and Cheerio project in javascript.",
6 "version": "0.0",
7 "meta": {
8 "templateId": "js-crawlee-cheerio"
9 },
10 "input": "./input_schema.json",
11 "dockerfile": "./Dockerfile"
12}
.actor/input_schema.json
1{
2 "title": "CheerioCrawler Template",
3 "type": "object",
4 "schemaVersion": 1,
5 "properties": {
6 "startUrls": {
7 "title": "Start URLs",
8 "type": "array",
9 "description": "URLs to start with.",
10 "editor": "requestListSources",
11 "prefill": [
12 {
13 "url": "https://crawlee.dev"
14 }
15 ]
16 },
17 "maxRequestsPerCrawl": {
18 "title": "Max Requests per Crawl",
19 "type": "integer",
20 "description": "Maximum number of requests that can be made by this crawler.",
21 "default": 100
22 }
23 }
24}
.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
.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 "extends": "@apify",
3 "root": true
4}
.gitignore
1# This file tells Git which files shouldn't be added to source control
2
3.DS_Store
4.idea
5dist
6node_modules
7apify_storage
8storage
package.json
1{
2 "name": "crawlee-cheerio-javascript",
3 "version": "0.0.1",
4 "type": "module",
5 "description": "This is a boilerplate of an Apify actor.",
6 "engines": {
7 "node": ">=18.0.0"
8 },
9 "dependencies": {
10 "apify": "^3.1.10",
11 "crawlee": "^3.5.4"
12 },
13 "devDependencies": {
14 "@apify/eslint-config": "^0.4.0",
15 "eslint": "^8.50.0"
16 },
17 "scripts": {
18 "start": "node src/main.js",
19 "lint": "eslint ./src --ext .js,.jsx",
20 "lint:fix": "eslint ./src --ext .js,.jsx --fix",
21 "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
22 },
23 "author": "It's not you it's me",
24 "license": "ISC"
25}
src/main.js
1// Apify SDK - toolkit for building Apify Actors (Read more at https://docs.apify.com/sdk/js/)
2import { Actor } from 'apify';
3// Crawlee - web scraping and browser automation library (Read more at https://crawlee.dev)
4import { CheerioCrawler, Dataset } from 'crawlee';
5// this is ESM project, and as such, it requires you to specify extensions in your relative imports
6// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
7// import { router } from './routes.js';
8
9// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init()
10await Actor.init();
11
12// Structure of input is defined in input_schema.json
13const {
14 startUrls = ['https://crawlee.dev'],
15 maxRequestsPerCrawl = 100,
16} = await Actor.getInput() ?? {};
17
18const proxyConfiguration = await Actor.createProxyConfiguration();
19
20const crawler = new CheerioCrawler({
21 proxyConfiguration,
22 maxRequestsPerCrawl,
23 async requestHandler({ enqueueLinks, request, $, log }) {
24 log.info('enqueueing new URLs');
25 await enqueueLinks();
26
27 // Extract title from the page.
28 const title = $('title').text();
29 log.info(`${title}`, { url: request.loadedUrl });
30
31 // Save url and title to Dataset - a table-like storage.
32 await Dataset.pushData({ url: request.loadedUrl, title });
33 },
34});
35
36await crawler.run(startUrls);
37
38// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit()
39await Actor.exit();