Bloxy Tokens Info

# This is a template for a Dockerfile used to run acts in Actor system.
# The base image name below is set during the act build, based on user settings.
# IMPORTANT: The base image must set a correct working directory, such as /usr/src/app or /home/user
FROM apify/actor-node-puppeteer-chrome

# Second, copy just package.json and package-lock.json since it should be
# the only file that affects "npm install" in the next step, to speed up the build
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 --only=prod --no-optional \
 && echo "Installed NPM packages:" \
 && (npm list --all || true) \
 && echo "Node.js version:" \
 && node --version \
 && echo "NPM version:" \
 && npm --version

# Copy source code to container
# Do this in the last step, to have fast build if only the source code changed
COPY --chown=myuser:myuser . ./

# NOTE: The CMD is already defined by the base image.
# Uncomment this for local node inspector debugging:
# CMD [ "node", "--inspect=0.0.0.0:9229", "main.js" ]

{
    "name": "apify-project",
    "version": "0.0.1",
    "description": "",
    "author": "It's not you it's me",
    "license": "ISC",
    "dependencies": {
        "apify": "latest"
    },
    "scripts": {
        "start": "node main.js"
    }
}

1const Apify = require('apify');
2
3Apify.main(async () => {
4    // Apify.openRequestQueue() creates a preconfigured RequestQueue instance.
5    // We add our first request to it - the initial page the crawler will visit.
6    const requestQueue = await Apify.openRequestQueue();
7    await requestQueue.addRequest({ url: 'https://bloxy.info/list_tokens/ERC20?page=1' });
8    // Create an instance of the PlaywrightCrawler class - a crawler
9    // that automatically loads the URLs in headless Chrome / Playwright.
10    const input = await Apify.getInput();
11    const crawler = new Apify.PuppeteerCrawler({
12        requestQueue,
13        launchContext: {
14            // Here you can set options that are passed to the playwright .launch() function.
15            launchOptions: {
16                headless: true,
17            },
18        },
19
20        // Stop crawling after several pages
21        maxRequestsPerCrawl: input.maxPage || 50,
22        handlePageTimeoutSecs: 30,
23
24        handlePageFunction: async ({ request, page }) => {
25            console.log(`Processing ${request.url}...`);
26
27            // A function to be evaluated by Playwright within the browser context.
28            const data = await page.$$eval('tbody tr', $posts => {
29                const scrapedData = [];
30                // // We're getting the title, rank and URL of each post on Hacker News.
31                $posts.forEach($post => {
32                    let linkContract = $post.querySelector('td:nth-child(1) a').href
33                    let contract = linkContract.split('token_holders/')[1]
34                    scrapedData.push({
35                        title: $post.querySelector('td:nth-child(1)').textContent.trim(),
36                        contract,
37                        type: $post.querySelector('td:nth-child(2)').textContent.trim(),
38                        senders_receivers: $post.querySelector('td:nth-child(3)').textContent.trim(),
39                        transfers7days: $post.querySelector('td:nth-child(4)').textContent.trim(),
40                        volume7days: $post.querySelector('td:nth-child(5)').textContent.trim(),
41                        topTransferTx: $post.querySelector('td:nth-child(6)').textContent.trim(),
42                    });
43                });
44
45                return scrapedData;
46            });
47            console.log(data);
48            // Store the results to the default dataset.
49            await Apify.pushData(data);
50
51            // Find a link to the next page and enqueue it if it exists.
52            const infos = await Apify.utils.enqueueLinks({
53                page,
54                requestQueue,
55                selector: '.next_page a',
56            });
57
58            if (infos.length === 0) console.log(`${request.url} is the last page!`);
59        },
60
61        // This function is called if the page processing failed more than maxRequestRetries+1 times.
62        handleFailedRequestFunction: async ({ request }) => {
63            console.log(`Request ${request.url} failed too many times.`);
64        },
65    });
66
67    // Run the crawler and wait for it to finish.
68    await crawler.run();
69
70    console.log('Crawler finished.');
71});