Product Hunt User Finder (2023)

# 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:16

# 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": "project-cheerio-crawler-javascript",
    "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": {
        "usernames": {
            "title": "Usernames",
            "type": "string",
            "description": "Product Hunt usernames",
            "editor": "textarea"
        }
    },
    "required": ["usernames"]
}

1export const collectUsernamesArray = (usernamesInput) => {
2    const matches = [...usernamesInput.matchAll(/[^ \n\t,]+/g)];
3    
4    if (matches.length === 0) {
5        throw new Error('There are no usernames to process');
6    }
7
8    return matches.map((match) => match[0]);
9};
10
11export const getColumnName = (() => {
12    let index = 1;
13
14    return (prefix, name) => {
15        const formattedIndex = index.toString().padStart(2, '0');
16
17        index++;
18
19        return `${formattedIndex}_${prefix}_${name}`;
20    };
21})();

1import { collectUsernamesArray } from './helpers.js';
2
3const getProfileUrl = (username) => {
4    return `https://www.producthunt.com/@${username}`;
5};
6
7const getUsernameFromUrl = (url) => {
8    const regex = /@(.+)/;
9    const match = url.match(regex);
10   
11    return match[1];
12};
13
14const collectProfileUrls = (usernamesInput) => {
15    const usernames = collectUsernamesArray(usernamesInput);
16    const profileUrls = [];
17
18    for (const username of usernames) {
19        profileUrls.push(getProfileUrl(username));
20    }
21
22    if (profileUrls.length === 0) {
23        throw new Error('There are no links to crawl');
24    }
25
26    return profileUrls;
27};
28
29const getProfileName = ($) => {
30    return $('h1').text();
31};
32
33const getProfileAbout = ($) => {
34    return $('h2:contains("About") + p').text();
35};
36
37const getProfileFollowersCount = ($) => {
38    const followersText = $('header a:contains("followers")').text();
39
40    return parseInt(followersText.replace(',', ''));
41};
42
43export default {
44    getProfileUrl,
45    getUsernameFromUrl,
46    collectProfileUrls,
47    getProfileName,
48    getProfileAbout,
49    getProfileFollowersCount
50};

1import { Actor } from 'apify';
2import { CheerioCrawler } from 'crawlee';
3import { router } from './routes.js';
4import productHunt from './modules/product-hunt.js';
5
6await Actor.init();
7
8const { usernames } = await Actor.getInput();
9const profileUrls = productHunt.collectProfileUrls(usernames);
10
11const proxyConfiguration = await Actor.createProxyConfiguration();
12const crawler = new CheerioCrawler({
13    proxyConfiguration,
14    requestHandler: router
15});
16
17await crawler.run(profileUrls);
18
19await Actor.exit();

1import { Dataset, createCheerioRouter } from 'crawlee';
2import productHunt from './modules/product-hunt.js';
3
4export const router = createCheerioRouter();
5
6router.addDefaultHandler(async ({ request: { loadedUrl }, response: { statusCode }, $ }) => {
7    let urlData = {
8        '01_ph_url': loadedUrl,
9        '02_ph_status': statusCode,
10    };
11
12    if (statusCode !== 404) {
13        const name = productHunt.getProfileName($);
14        const about = productHunt.getProfileAbout($);
15        const followers = productHunt.getProfileFollowersCount($);
16
17        urlData = {
18            ...urlData,
19            '03_ph_name': name,
20            '04_ph_followers': followers,
21            '05_ph_about': about
22        };
23    }
24
25    await Dataset.pushData(urlData);
26
27    console.log(`${loadedUrl} parsed`);
28});

# 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": ">=16.0.0"
    },
    "dependencies": {
        "apify": "^3.0.0",
        "crawlee": "^3.0.0"
    },
    "devDependencies": {
        "@apify/eslint-config": "^0.3.1",
        "eslint": "^8.36.0"
    },
    "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"
}