LinkedIn Profile URL Scrapper (from Google)

# 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:20

# 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": "my-actor",
    "title": "Project Cheerio Crawler Javascript",
    "description": "Crawlee and Cheerio project in javascript.",
    "version": "0.0",
    "meta": {
        "templateId": "js-crawlee-cheerio"
    },
    "input": "./input_schema.json",
    "storages": {
        "dataset": "./dataset_schema.json"
    },
    "dockerfile": "./Dockerfile"
}

{
    "actorSpecification": 1,
    "fields": {
        "LinkedIn URL": {
            "type": "string",
            "description": "The URL of the LinkedIn profile."
        }
    },
    "views": {
        "overview": {
            "title": "Overview",
            "transformation": {
                "fields": ["LinkedIn URL"]
            },
            "display": {
                "component": "table",
                "properties": {
                    "LinkedIn URL": {
                        "label": "LinkedIn Profile URL",
                        "format": "link"
                    }
                }
            }
        }
    }
}

{
    "title": "Scrape LinkedIn profiles based on keywords",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "keywords": {
            "title": "Search Keywords",
            "type": "array",
            "description": "Enter the keywords to search for LinkedIn profiles, e.g., job titles, and locations.",
            "editor": "stringList",
            "items": {
                "type": "string"
            },
            "prefill": ["chief product officer", "united states"]
        },
        "numPages": {
            "title": "Number of Pages",
            "type": "integer",
            "description": "The number of pages to scrape (each page corresponds to a set of search results).",
            "editor": "number",
            "minimum": 1,
            "default": 1
        }
    },
    "required": ["keywords", "numPages"]
}

{
    "title": "LinkedIn Profile URLs",
    "type": "array",
    "items": {
        "type": "object",
        "properties": {
            "LinkedIn URL": {
                "type": "string",
                "description": "The URL of the LinkedIn profile."
            }
        },
        "required": ["LinkedIn URL"]
    }
}

1import { Actor, log } from 'apify';
2import { CheerioCrawler } from 'crawlee';
3
4await Actor.init();
5
6try {
7    const input = await Actor.getInput();
8    const keywords = input.keywords ? input.keywords.slice(0, 2) : ["chief product officer", "united states"];
9    const numPages = input.numPages || 1;
10
11    const baseUrl = 'https://www.google.com/search?q=site%3Alinkedin.com%2Fin%2F+';
12    const formattedKeywords = keywords.map(keyword => `%22${keyword.replace(/ /g, "+")}%22`).join('+');
13    const headers = {
14        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
15    };
16
17    const linkedinUrlsSet = new Set();
18
19    // Generate URLs for the number of pages specified
20    const urls = [];
21    for (let page = 0; page < numPages; page++) {
22        const start = page * 10;
23        urls.push(`${baseUrl}${formattedKeywords}&start=${start}`);
24    }
25
26    const requestQueue = await Actor.openRequestQueue();
27    for (const url of urls) {
28        await requestQueue.addRequest({ url, headers });
29    }
30
31    const crawler = new CheerioCrawler({
32        requestQueue,
33        requestHandler: async ({ request, $ }) => {
34            console.log(`Processing ${request.url}...`);
35
36            $('a').each((index, element) => {
37                const href = $(element).attr('href');
38                const match = href && href.match(/(https?:\/\/www\.linkedin\.com\/in\/[^&]+)/);
39                if (match) {
40                    const linkedinUrl = match[1];
41                    linkedinUrlsSet.add(linkedinUrl); // Add to set to ensure uniqueness
42                }
43            });
44        },
45    });
46
47    await crawler.run();
48
49    // Convert set to array for pushing to dataset
50    const linkedinUrlsArray = Array.from(linkedinUrlsSet);
51
52    // Push unique results to dataset
53    const results = linkedinUrlsArray.map(url => ({ "LinkedIn URL": url }));
54    await Actor.pushData(results);
55
56    log.info(`Found and saved ${linkedinUrlsSet.size} unique LinkedIn URLs based on the keywords across ${numPages} pages.`);
57} catch (error) {
58    console.error('Error during actor run:', error);
59    throw error;
60}
61
62await Actor.exit();

# 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": ">=18.0.0"
    },
    "dependencies": {
        "apify": "^3.1.10",
        "crawlee": "^3.5.4",
        "googleapis": "^118.0.0"
    },
    "devDependencies": {
        "@apify/eslint-config": "^0.4.0",
        "eslint": "^8.50.0"
    },
    "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"
}