Pricing
Pay per usage
Downloads data from Czech company registry https://or.justice.cz/
0.0 (0)
Pricing
Pay per usage
0
Monthly users
1
Runs succeeded
>99%
Last modified
a month ago
Pricing model
Pay per usageThis Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage.
1# Specify the base Docker image. You can read more about
2# the available images at https://crawlee.dev/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 --silent1{
2 "actorSpecification": 1,
3 "name": "my-actor-25",
4 "title": "Project Cheerio Crawler Typescript",
5 "description": "Crawlee and Cheerio project in typescript.",
6 "version": "0.0",
7 "meta": {
8 "templateId": "ts-crawlee-cheerio"
9 },
10 "input": "./input_schema.json",
11 "dockerfile": "./Dockerfile"
12}1{
2 "title": "Obchodni rejstrik downloader",
3 "type": "object",
4 "schemaVersion": 1,
5 "properties": {
6 "companyIco": {
7 "title": "ICO of the company you want to scrape",
8 "type": "string",
9 "editor": "textfield",
10 "description": "ICO of the company you want to scrape",
11 "prefill": "04788290"
12 }
13 },
14 "required": ["companyIco"]
15}1import { Actor, log } from 'apify';
2import { CheerioCrawler, Dataset } from 'crawlee';
3
4interface Input {
5 companyIco: string,
6}
7
8await Actor.init();
9
10const getHeaderValue = (rawHeaders: string[], name: string): string | null | undefined => {
11 return rawHeaders[rawHeaders.findIndex((h) => h.toLowerCase() === name) + 1];
12};
13
14const getFileMetadata = (prefix: string, rawHeaders: string[]) => {
15 const contentType = getHeaderValue(rawHeaders, 'content-type') ?? 'text/plain';
16 const filename = getHeaderValue(rawHeaders, 'content-disposition')?.match(/filename="(.*)"/)?.[1] || 'unknown';
17
18 return {
19 contentType,
20 filename: `${prefix}-${+new Date()}-${filename.replace(/[^a-zA-Z0-9_.-]/g, '-')}`,
21 };
22};
23
24
25const {
26 companyIco,
27} = await Actor.getInput<Input>() ?? {} as Input;
28
29const kvs = await Actor.openKeyValueStore();
30
31const LABELS = {
32 START: 'START',
33 SBIRKA_LISTIN: 'SBIRKA_LISTIN',
34 LISTINA: 'LISTINA',
35} as const;
36
37const crawler = new CheerioCrawler({
38 // TODO: Is this using proxy properly?
39 proxyConfiguration: await Actor.createProxyConfiguration(),
40 maxConcurrency: 10,
41 requestHandler: async ({ enqueueLinks, request, $, sendRequest }) => {
42 if (request.label === LABELS.START) {
43 log.info('Enqueuing urls from search page...');
44 await enqueueLinks({
45 selector: 'a[href^="./vypis-sl"]',
46 label: LABELS.SBIRKA_LISTIN,
47 });
48 } else if (request.label === LABELS.SBIRKA_LISTIN) {
49 log.info('Enqueuing URLs from document list...');
50 await enqueueLinks({
51 selector: 'a[href^="./vypis-sl-detail"]',
52 label: LABELS.LISTINA,
53 });
54 } else if (request.label === LABELS.LISTINA) {
55 const links = $('a[href^=/ias/content/download]').toArray();
56 log.info(`Found ${links.length} links`);
57
58 await Promise.allSettled(links.map(async (link) => {
59 log.info('Downloading document...');
60 const downloadUrl = `https://or.justice.cz${link.attribs.href}`;
61 const response = await sendRequest({ url: downloadUrl });
62 // For some reason, we can only access raw headers
63 const { contentType, filename } = getFileMetadata('file', response.rawHeaders);
64 await Actor.setValue(filename, response.rawBody, { contentType });
65 await Actor.pushData({
66 url: request.url,
67 filename,
68 fileUrl: kvs.getPublicUrl(filename),
69 });
70
71 }));
72 }
73 },
74});
75
76const startUrl = new URL('https://or.justice.cz/ias/ui/rejstrik-$firma');
77startUrl.searchParams.set('ico', companyIco.replace(/[^0-9]/, ''));
78
79await crawler.run([
80 { url: startUrl.toString(), label: LABELS.START },
81]);
82
83// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit()
84await Actor.exit();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.git1root = true
2
3[*]
4indent_style = space
5indent_size = 4
6charset = utf-8
7trim_trailing_whitespace = true
8insert_final_newline = true
9end_of_line = lf1{
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}1# This file tells Git which files shouldn't be added to source control
2
3.DS_Store
4.idea
5.vscode
6dist
7node_modules
8apify_storage
9storage1{
2 "name": "crawlee-cheerio-typescript",
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": "^3.2.6",
11 "crawlee": "^3.11.5"
12 },
13 "devDependencies": {
14 "@apify/eslint-config-ts": "^0.3.0",
15 "@apify/tsconfig": "^0.1.0",
16 "@typescript-eslint/eslint-plugin": "^7.18.0",
17 "@typescript-eslint/parser": "^7.18.0",
18 "eslint": "^8.50.0",
19 "tsx": "^4.6.2",
20 "typescript": "^5.3.3"
21 },
22 "scripts": {
23 "start": "npm run start:dev",
24 "start:prod": "node dist/main.js",
25 "start:dev": "tsx src/main.ts",
26 "build": "tsc",
27 "lint": "eslint ./src --ext .ts",
28 "lint:fix": "eslint ./src --ext .ts --fix",
29 "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
30 },
31 "author": "It's not you it's me",
32 "license": "ISC"
33}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}