Obchodni Rejstrik Downloader

# 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": "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';
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();

# configurations
.idea
.vscode

# 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
.vscode
dist
node_modules
apify_storage
storage

{
    "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/**/*"
    ]
}