The readFacebookProfileInfo function automates the process of extracting a Facebook profile's name, description, and URL from a given profile page. It uses web scraping techniques to locate and interact with elements on the page, ultimately returning a structured object containing the extracted data.

Run example

npm run import -- "Scrape facebook profile"

Scrape facebook profile

var importer = require('../Core');
// TODO: pass profile path in as parameter becomes readFacebookProfileInfo
function readFacebookProfileInfo() {
    var profile = {};
    // TODO: check for profile path
    return client
        .getAllXPath('//*[contains(@class, "scrollable")]//h4[contains(., "Profile")]/parent::*//a/@href')
        .then(r => r != ''
            ? client.clickSpa(r)
                .pause(2000)
                .then(() => importer.runAllPromises([
                    client.getText('[role="main"] h1'),
                    client.isExisting('#intro_container_id li').then(is => is
                        ? client.getText('#intro_container_id li')
                        : Promise.resolve('')),
                    client.getUrl()
                ]))
                .then(r => (profile = ({
                    name: r[0],
                    description: r[1],
                    url: r[2]
                })))
            : client)
        .then(() => profile)
        .catch(e => console.log(e))
};
module.exports = readFacebookProfileInfo;

const { Client } = require('../Core');

/**
 * Reads Facebook profile information from the browser.
 *
 * @returns {Object} Profile information (name, description, url)
 */
async function readFacebookProfileInfo(profilePath) {
    try {
        // Check if profile path is provided
        if (!profilePath) {
            throw new Error('Profile path is required');
        }

        // Get all relevant profile links
        const profileLinks = await Client.getAllXPath(`//*[contains(@class, "scrollable")]//h4[contains(., "Profile")]/parent::*//a/@href`);

        // If no links are found, return an empty profile
        if (profileLinks.length === 0) {
            return {};
        }

        // Click on the first profile link
        const profileUrl = profileLinks[0];
        await Client.clickSpa(profileUrl);
        await Client.pause(2000);

        // Get profile information
        const promises = [
            Client.getText('[role="main"] h1'),
            Client.isExisting('#intro_container_id li')
               .then(isExisting => isExisting
                   ? Client.getText('#intro_container_id li')
                    : Promise.resolve('')),
            Client.getUrl()
        ];
        const profileInfo = await Client.runAllPromises(promises);

        // Create profile object
        const profile = {
            name: profileInfo[0],
            description: profileInfo[1],
            url: profileInfo[2]
        };

        return profile;
    } catch (error) {
        console.log(error);
        return {};
    }
}

module.exports = readFacebookProfileInfo;

This code snippet defines a function called readFacebookProfileInfo that aims to extract information from a Facebook profile.

Here's a breakdown:

1. Initialization:

   • It initializes an empty object profile to store the extracted data.

2. Finding the Profile Link:

   • It uses client.getAllXPath to locate the link to the profile page. The XPath expression targets elements containing "Profile" within a scrollable container and extracts the href attribute of the link.

3. Navigating to the Profile:

   • If a profile link is found, it clicks on the link using client.clickSpa and waits for 2 seconds using pause(2000).

4. Extracting Profile Data:

   • It then uses importer.runAllPromises to execute multiple asynchronous operations:
     • client.getText('[role="main"] h1'): Extracts the profile name from the main heading.
     • client.isExisting('#intro_container_id li').then(is => is ? client.getText('#intro_container_id li') : Promise.resolve('')): Checks if an element with the ID intro_container_id exists and contains list items. If it does, it extracts the text content of those list items (likely the profile description). Otherwise, it resolves with an empty string.
     • client.getUrl(): Gets the current URL of the profile page.

5. Storing Profile Data:

   • The extracted data is then combined into the profile object, which includes name, description, and url properties.

6. Returning Profile Data:

   • Finally, the function returns the profile object containing the extracted information.