# First, specify the base Docker image. You can read more about
# the available images at https://sdk.apify.com/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node:16

# Second, copy just package.json and package-lock.json since those are the only
# files that affect "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 || true) \
 && echo "Node.js version:" \
 && node --version \
 && echo "NPM version:" \
 && npm --version

# 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 . ./

# Optionally, specify how to launch the source code of your actor.
# By default, Apify's base Docker images define the CMD instruction
# that runs the Node.js source code using the command specified
# in the "scripts.start" section of the package.json file.
# In short, the instruction looks something like this:
#
# CMD npm start


Dockerfile

Please paste here the URL of the petition you want to crawl signature from.

Petition URL (it should look like this https://www.petitions.lu/voir-les-signatures/xxxx-xxxx)

Petition Crawling Input Schema

INPUT_SCHEMA.json

// This is the main Node.js source code file of your actor.
// It is referenced from the "scripts" section of the package.json file.

const Apify = require('apify');

Apify.main(async () => {
    // Get input of the actor. Input fields can be modified in INPUT_SCHEMA.json file.
    // For more information, see https://docs.apify.com/actor/input-schema
    const input = await Apify.getInput();
    console.log('Input:');
    console.dir(input);

    // Here you can prepare your input for actor apify/web-scraper this input is based on a actor
    // task you used as the starting point.
    const metamorphInput = {
        "runMode": "DEVELOPMENT",
        "startUrls": [
            {
                "url": input.petitionUrl,
                "method": "GET"
            }
        ],
        "keepUrlFragments": false,
        "linkSelector": "a[href]",
        "pseudoUrls": [
            {
                "purl": input.petitionUrl+"?tx_petition_singlepetitionsignatures%5Bpagenumber%5D=[(\\d)+]&cHash=[(\\w)+]",
                "method": "GET"
            }
        ],
        "pageFunction": // The function accepts a single argument: the "context" object.
        // For a complete list of its properties and functions,
        // see https://apify.com/apify/web-scraper#page-function 
        async function pageFunction(context) {
            // This statement works as a breakpoint when you're trying to debug your code. Works only with Run mode: DEVELOPMENT!
            // debugger; 
        
            // jQuery is handy for finding DOM elements and extracting data from them.
            // To use it, make sure to enable the "Inject jQuery" option.
            const $ = context.jQuery;
            const signatures = [];
             $('.petition-signatures div p').each(function(){
                 var obj = {};
                 var split = $(this).text().split(',');
                 if (split.length == 2){
                     obj.name = split[0];
                     obj.city = split[1].trim();
                 } else {
                     obj.name = split.subarray(0,split.length-2).join(" ");
                     obj.city = split[split.length-1].trim();
                 }
                 signatures.push(obj);
             });
        
            // Print some information to actor log
            context.log.info(`URL: ${context.request.url}, SIGNATURES: ${signatures}`);
        
            // Manually add a new page to the queue for scraping.
            // context.enqueueRequest({ url: 'http://www.example.com' });
        
            // Return an object with the data extracted from the page.
            // It will be stored to the resulting dataset.
            return signatures;
        },
        "preNavigationHooks": `// We need to return array of (possibly async) functions here.
            // The functions accept two arguments: the "crawlingContext" object
            // and "gotoOptions".
            [
                async (crawlingContext, gotoOptions) => {
                    // ...
                },
            ]`,
        "postNavigationHooks": `// We need to return array of (possibly async) functions here.
            // The functions accept a single argument: the "crawlingContext" object.
            [
                async (crawlingContext) => {
                    // ...
                },
            ]`,
        "injectJQuery": true,
        "injectUnderscore": false,
        "proxyConfiguration": {
            "useApifyProxy": false
        },
        "proxyRotation": "RECOMMENDED",
        "useChrome": false,
        "useStealth": false,
        "ignoreSslErrors": false,
        "ignoreCorsAndCsp": false,
        "downloadMedia": false,
        "downloadCss": false,
        "waitUntil": [
            "networkidle2"
        ],
        "breakpointLocation": "NONE",
        "debugLog": false,
        "browserLog": false
    };

    // Now let's metamorph into actor apify/web-scraper using the created input.
    await Apify.metamorph('apify/web-scraper', metamorphInput);
});

main.js

extract-signatures-chambre-depute-luxembourg

package.json

This Actor let you extract signatures from Luxembourgish official petition website petitions.lu. You'll get firstname(s), lastname(s), and city.

Petition.lu signature extractor.

Where next?