Pages Checker

# 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": {
        "startUrls": {
            "title": "Start URLs",
            "type": "array",
            "description": "URLs to start with.",
            "editor": "requestListSources",
            "prefill": [
                {
                    "url": "https://apify.com"
                }
            ]
        },
        "checkFunction": {
            "title": "Check function",
            "type": "string",
            "description": "Function applied to each page",
            "editor": "javascript",
            "prefill": "async ({ $, request, log }) => { return $('title').text() === 'Hi' ; }"
        },
        "proxyConfiguration": {
            "title": "Proxy configuration",
            "type": "object",
            "description": "Select proxies to be used by your crawler.",
            "prefill": { "useApifyProxy": true },
            "editor": "proxy"
        }
    }
}

1import { Actor } from 'apify';
2import { CheerioCrawler } from 'crawlee';
3
4import { Dataset, createCheerioRouter } from 'crawlee';
5
6// Parses given string to js function
7const parseCheckFunction = (fnStr) => {
8    try {
9        const checkFunction = eval(fnStr);
10        if (typeof checkFunction !== 'function') {
11            throw new Error('Check function is not a function');
12        }
13        return checkFunction;
14    } catch(err) {
15        console.error(err);
16        throw new Error('Cannot parse check function');
17    }
18}
19
20// Initialize the Apify SDK
21await Actor.init();
22
23// Get input
24const {
25    startUrls,
26    checkFunction: checkFunctionString,
27    proxyConfiguration: proxyConfigurationOptions,
28} = await Actor.getInput();
29
30// Parse check function
31const checkFunction = parseCheckFunction(checkFunctionString);
32
33// Generate proxy config
34const proxyConfiguration = await Actor.createProxyConfiguration(proxyConfigurationOptions);
35
36// Number of failed checks is kept in state, we need to base the exit code of actor on that
37let { failedChecksCount } = await Actor.getValue('my-crawling-state') || { failedChecksCount: 0 };
38Actor.on('migrating', () => {
39    Actor.setValue('my-crawling-state', { failedChecksCount });
40});
41
42const router = createCheerioRouter();
43
44router.addDefaultHandler(async (arg, ...rest) => {
45    const isOk = await checkFunction(arg, ...rest);
46    if (!isOk) failedChecksCount++;
47    await Dataset.pushData({
48        url: arg.request.loadedUrl,
49        isOk,
50    });
51});
52
53const crawler = new CheerioCrawler({
54    proxyConfiguration,
55    requestHandler: router,
56});
57
58await crawler.run(startUrls);
59
60if (failedChecksCount > 0) {
61    await Actor.fail('Check failed on some of the pages');
62} else {
63    await Actor.exit();
64}

# 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"
}