Telegram, whatsapp, VK scraper

# 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

# 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

# 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 . ./


# Run the image.
CMD npm start --silent

{
    "actorSpecification": 1,
    "name": "my-actor",
    "title": "Project Cheerio Crawler Javascript",
    "description": "Crawlee and Cheerio project in javascript.",
    "version": "0.0",
    "meta": {
        "templateId": "js-crawlee-cheerio"
    },
    "input": "./input_schema.json",
    "dockerfile": "./Dockerfile"
}

{
    "title": "CheerioCrawler Template",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "startUrls": {
            "title": "Start URLs",
            "type": "array",
            "description": "URLs to start with.",
            "editor": "requestListSources",
            "prefill": [
                {
                    "url": "https://crawlee.dev"
                }
            ]
        },
        "maxRequestsPerCrawl": {
            "title": "Max Requests per Crawl",
            "type": "integer",
            "description": "Maximum number of requests that can be made by this crawler.",
            "default": 100
        }
    }
}

1// Apify SDK - toolkit for building Apify Actors (Read more at https://docs.apify.com/sdk/js/)
2import { Actor } from 'apify';
3import _ from 'lodash';
4// Crawlee - web scraping and browser automation library (Read more at https://crawlee.dev)
5import { CheerioCrawler } from 'crawlee';
6// this is ESM project, and as such, it requires you to specify extensions in your relative imports
7// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
8// import { router } from './routes.js';
9
10// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init()
11await Actor.init();
12
13// Structure of input is defined in input_schema.json
14const {
15    startUrls = ['https://crawlee.dev'],
16    maxRequestsPerCrawl = 100,
17} = await Actor.getInput() ?? {};
18
19const proxyConfiguration = await Actor.createProxyConfiguration();
20
21const crawler = new CheerioCrawler({
22    proxyConfiguration,
23    maxRequestsPerCrawl,
24    async requestHandler({ enqueueLinks, request, $, log }) {
25        // log.info('enqueueing new URLs');
26        // await enqueueLinks();
27
28        // Extract title from the page.
29        const title = $('title').text();
30        log.info(`${title}`, { url: request.loadedUrl });
31
32        const telegramLinks = $('a[href*="t.me"]');
33        const vkLinks = $('a[href*="vk"]');
34        const waLinks = $('a[href*="wa.me"], a[href*="api.whatsapp"]');
35
36        const data = [];
37
38        [telegramLinks, vkLinks, waLinks].forEach((links) => {
39            links.each((idx, link) => {
40                data.push({contact: $(link).attr('href')})
41            })
42        })
43
44        const uniqContacts = _.uniqBy(data, 'contact');
45
46        Actor.pushData({url: request.loadedUrl, contacts: uniqContacts})
47    },
48});
49
50await crawler.run(startUrls);
51
52// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit()
53await Actor.exit();

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

root = true

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

{
    "extends": "@apify",
    "root": true
}

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

.DS_Store
.idea
dist
node_modules
apify_storage
storage

{
    "name": "crawlee-cheerio-javascript",
    "version": "0.0.1",
    "type": "module",
    "description": "This is a boilerplate of an Apify actor.",
    "engines": {
        "node": ">=18.0.0"
    },
    "dependencies": {
        "apify": "^3.2.6",
        "crawlee": "^3.11.5"
    },
    "devDependencies": {
        "@apify/eslint-config": "^0.4.0",
        "eslint": "^8.50.0",
        "lodash": "^4.17.21"
    },
    "scripts": {
        "start": "node src/main.js",
        "lint": "eslint ./src --ext .js,.jsx",
        "lint:fix": "eslint ./src --ext .js,.jsx --fix",
        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
    },
    "author": "It's not you it's me",
    "license": "ISC"
}