Open Source Actors Scraper

# 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

{
    "root": true,
    "env": {
        "browser": true,
        "es2020": true,
        "node": true
    },
    "extends": [
        "@apify/eslint-config-ts"
    ],
    "parserOptions": {
        "project": "./tsconfig.json",
        "ecmaVersion": 2020
    },
    "ignorePatterns": [
        "node_modules",
        "dist",
        "**/*.d.ts"
    ]
}

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

.DS_Store
.idea
dist
node_modules
apify_storage
storage

# Added by Apify CLI
.venv

{
	"name": "apify-store-open-source",
	"version": "0.0.1",
	"type": "module",
	"description": "This is a boilerplate of an Apify actor.",
	"engines": {
		"node": ">=18.0.0"
	},
	"dependencies": {
		"apify": "^3.1.10",
		"crawlee": "^3.5.4"
	},
	"devDependencies": {
		"@apify/eslint-config-ts": "^0.3.0",
		"@apify/tsconfig": "^0.1.0",
		"@typescript-eslint/eslint-plugin": "^6.7.2",
		"@typescript-eslint/parser": "^6.7.2",
		"eslint": "^8.50.0",
		"tsx": "^4.6.2",
		"typescript": "^5.3.3"
	},
	"scripts": {
		"start": "npm run start:dev",
		"start:prod": "node dist/main.js",
		"start:dev": "tsx src/main.ts",
		"build": "tsc",
		"lint": "eslint ./src --ext .ts",
		"lint:fix": "eslint ./src --ext .ts --fix",
		"test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
	},
	"author": "It's not you it's me",
	"license": "ISC"
}

{
    "extends": "@apify/tsconfig",
    "compilerOptions": {
        "module": "NodeNext",
        "moduleResolution": "NodeNext",
        "target": "ES2022",
        "outDir": "dist",
        "noUnusedLocals": false,
        "skipLibCheck": true,
        "lib": ["DOM"]
    },
    "include": [
        "./src/**/*"
    ]
}

# Specify the base Docker image. You can read more about
# the available images at https://crawlee.dev/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node:20 AS builder

# 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 all dependencies. Don't audit to speed up the installation.
RUN npm install --include=dev --audit=false

# Next, copy the source files using the user set
# in the base image.
COPY . ./

# Install all dependencies and build the project.
# Don't audit to speed up the installation.
RUN npm run build

# Create final image
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

# Copy built JS files from builder image
COPY --from=builder /usr/src/app/dist ./dist

# 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 run start:prod --silent

{
	"actorSpecification": 1,
	"name": "open-source-actors-scraper",
	"title": "Project Cheerio Crawler Typescript",
	"description": "Crawlee and Cheerio project in typescript.",
	"version": "0.0",
	"meta": {
		"templateId": "ts-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, log } from 'apify';
3// Crawlee - web scraping and browser automation library (Read more at https://crawlee.dev)
4import { CheerioCrawler } 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// note that we need to use `.js` even when inside TS files
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
13const proxyConfiguration = await Actor.createProxyConfiguration();
14
15const firstReq = {
16    url: `https://api.apify.com/v2/store?&limit=1000`,
17    label: 'PAGINATION',
18    userData: { offset: 0 },
19};
20
21interface ActorStore {
22    name: string;
23    url: string;
24}
25
26const crawler = new CheerioCrawler({
27    proxyConfiguration,
28    requestHandler: async ({ request, $, json }) => {
29        if (request.label === 'PAGINATION') {
30            const { items } = json.data;
31
32            log.info(`Loaded ${items.length} Actors from page ${request.url}`);
33
34            const toEnqueue = items.map((item: ActorStore) => {
35                return {
36                    url: item.url,
37                    label: 'DETAIL',
38                    userData: { item },
39                };
40            });
41            await crawler.addRequests(toEnqueue);
42
43            if (items.length >= 1000) {
44                const offset = request.userData.offset + 1000;
45                await crawler.addRequests([{
46                    url: `https://api.apify.com/v2/store?limit=1000&offset=${offset}`,
47                    label: 'PAGINATION',
48                    userData: { offset },
49                }]);
50            }
51        } else if (request.label === 'DETAIL') {
52            const { item } = request.userData;
53            const isOpenSource = $('[data-test-url="source-code"]').length > 0;
54
55            if (isOpenSource) {
56                await Actor.pushData({
57                    ...item,
58                    isOpenSource,
59                });
60            }
61
62            log.info(`${item.name} is open source: ${isOpenSource}`);
63        }
64    },
65});
66
67await crawler.run([firstReq]);
68
69// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit()
70await Actor.exit();