Obchodni Rejstrik Downloader
Pricing
Pay per usage
Downloads data from Czech company registry https://or.justice.cz/
Pricing
Pay per usage
Rating
5.0
(1)
Developer
Josef Válek
Actor stats
0
Bookmarked
35
Total users
1
Monthly active users
2 months ago
Last modified
Categories
Share
# 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:24 AS builder
# Check preinstalled packagesRUN 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 imageFROM apify/actor-node:24
# Check preinstalled packagesRUN 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 debuggingRUN 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 imageCOPY /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": "my-actor-25", "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": "Obchodni rejstrik downloader", "type": "object", "schemaVersion": 1, "properties": { "companyIco": { "title": "ICO of the company you want to scrape", "type": "string", "editor": "textfield", "description": "ICO of the company you want to scrape", "prefill": "04788290" } }, "required": ["companyIco"]}1import { Actor, log } from 'apify';2import { CheerioCrawler, Dataset } from 'crawlee';3import * as cheerio from 'cheerio';4
5interface Input {6 companyIco: string,7}8
9await Actor.init();10
11const getHeaderValue = (rawHeaders: string[], name: string): string | null | undefined => {12 return rawHeaders[rawHeaders.findIndex((h) => h.toLowerCase() === name) + 1];13};14
15const getFileMetadata = (prefix: string, rawHeaders: string[]) => {16 const contentType = getHeaderValue(rawHeaders, 'content-type') ?? 'text/plain';17 const filename = getHeaderValue(rawHeaders, 'content-disposition')?.match(/filename="(.*)"/)?.[1] || 'unknown';18
19 return {20 contentType,21 filename: `${prefix}-${filename.replace(/[^a-zA-Z0-9_.-]/g, '-')}`,22 };23};24
25const downloadPdf = async (26 fileIdentifier: string,27 downloadUrl: string,28 fileCategory: string,29 documentUrl: string,30 { sendRequest }: Record<string, any>,31) => {32 log.info('Downloading document', { downloadUrl, fileCategory });33 const response = await sendRequest({ url: downloadUrl });34 // For some reason, we can only access raw headers35 const { contentType, filename } = getFileMetadata(fileIdentifier, response.rawHeaders);36
37 if (contentType.startsWith('text/html')) {38 const $res = cheerio.load(response.rawBody);39 if ($res('h2').text().includes("časová platnost")) {40
41 throw new Error('Failed to get the document in time. Will retry');42 }43 }44
45 // Do not save the document if it was alredy scraped46 const doc = await Actor.getValue(filename);47 if (doc) {48 return;49 }50
51 await Actor.setValue(filename, response.rawBody, { contentType });52 await Actor.pushData({53 url: documentUrl,54 filename,55 fileUrl: kvs.getPublicUrl(filename),56 fileCategory,57 });58}59
60
61const {62 companyIco,63} = await Actor.getInput<Input>() ?? {} as Input;64
65const kvs = await Actor.openKeyValueStore();66
67const LABELS = {68 START: 'START',69 SBIRKA_LISTIN: 'SBIRKA_LISTIN',70 DOKUMENT: 'DOKUMENT',71} as const;72
73const DOCUMENT_CATEGORY = {74 LISTINA: 'LISTINA',75 UPLNY_VYPIS: 'UPLNY_VYPIS',76 VYPIS_PLATNYCH: 'VYPIS_PLATNYCH',77} as const;78
79// Open the default request queue associated with the actor run80const requestQueue = await Actor.openRequestQueue();81
82// TODO: What to do about expiring signatures83const crawler = new CheerioCrawler({84 // TODO: Is this using proxy properly?85 proxyConfiguration: await Actor.createProxyConfiguration(),86 maxConcurrency: 10,87 maxRequestRetries: 7,88 requestHandler: async ({ request, $, sendRequest }) => {89 if (request.label === LABELS.START) {90 log.info('Determining subjectId of the organization...');91
92 // Get subjektId - internal identifier in the database93 const [ link ] = $('a[href*="PLATNY"]').toArray();94 const subjektId = new URLSearchParams(link.attribs.href.split('?')[1]).get('subjektId')!;95
96 if (!subjektId) {97 log.error('Subjekt id not found, cannot continue.');98 return;99 }100
101 log.info('Found subjektId', { subjektId });102
103 // Enqueue the list of urls104 const documentsUrl = new URL('https://or.justice.cz/ias/ui/vypis-sl-firma'); 105 documentsUrl.searchParams.set('subjektId', subjektId);106 await requestQueue.addRequests([{ url: documentsUrl.toString(), label: LABELS.SBIRKA_LISTIN }]);107
108 // Add the URLs to the two main documents109 const baseUrl = new URL('https://or.justice.cz/ias/ui/print-pdf');110 baseUrl.searchParams.set('subjektId', subjektId);111
112 baseUrl.searchParams.set('typVypisu', 'PLATNY');113 await downloadPdf(114 'vypis-platnych',115 baseUrl.toString(),116 DOCUMENT_CATEGORY.VYPIS_PLATNYCH,117 request.url,118 { sendRequest },119 );120
121 baseUrl.searchParams.set('typVypisu', 'UPLNY');122
123 await downloadPdf(124 'uplny-vypis',125 baseUrl.toString(),126 DOCUMENT_CATEGORY.UPLNY_VYPIS,127 request.url,128 { sendRequest },129 );130
131
132 } else if (request.label === LABELS.SBIRKA_LISTIN) {133 // Construct links to the documents134 const documentsLinks = $('a[href^="./vypis-sl-detail"]').toArray().map(link => {135 const params = new URLSearchParams(link.attribs.href.split('?')[1]);136 const url = new URL('https://or.justice.cz/ias/ui/vypis-sl-detail');137 const dokumentId = params.get('dokument')!;138 url.searchParams.set('dokument', dokumentId);139 url.searchParams.set('subjektId', params.get('subjektId')!);140 url.searchParams.set('spis', params.get('spis')!);141 return {142 url: url.toString(),143 userData: {144 label: LABELS.DOKUMENT,145 dokumentId,146 }147 }148 });149
150 log.info('Found documents', { count: documentsLinks.length });151
152 await requestQueue.addRequests(documentsLinks);153 154 } else if (request.label === LABELS.DOKUMENT) {155 const links = $('a[href^=/ias/content/download]').toArray();156 log.info(`Found document links`, { count: links.length });157
158 const dokumentId = request.userData.dokumentId;159
160 await Promise.all(links.map(async (link, idx) => {161 const downloadUrl = `https://or.justice.cz${link.attribs.href}`;162 await downloadPdf(163 `doc-${dokumentId}-part-${idx}`,164 downloadUrl,165 DOCUMENT_CATEGORY.LISTINA,166 request.url,167 { sendRequest },168 );169 }));170 }171 },172});173
174const startUrl = new URL('https://or.justice.cz/ias/ui/rejstrik-$firma');175startUrl.searchParams.set('ico', companyIco.replace(/[^0-9]/, ''));176
177await crawler.run([178 { url: startUrl.toString(), label: LABELS.START },179]);180
181// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit()182await Actor.exit();# configurations.idea.vscode
# crawlee and apify storage foldersapify_storagecrawlee_storagestorage
# installed filesnode_modules
# git folder.gitroot = true
[*]indent_style = spaceindent_size = 4charset = utf-8trim_trailing_whitespace = trueinsert_final_newline = trueend_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.vscodedistnode_modulesapify_storagestorage{ "name": "crawlee-cheerio-typescript", "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-ts": "^0.3.0", "@apify/tsconfig": "^0.1.0", "@typescript-eslint/eslint-plugin": "^7.18.0", "@typescript-eslint/parser": "^7.18.0", "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/**/*" ]}