traxxx/src/scrapers/bangbros.js

'use strict';

/* eslint-disable newline-per-chained-call */
const bhttp = require('bhttp');
const cheerio = require('cheerio');
const moment = require('moment');

const slugify = require('../utils/slugify');
const { ex } = require('../utils/q');

function scrape(html, site) {
    const $ = cheerio.load(html, { normalizeWhitespace: true });
    const sceneElements = $('.echThumb').toArray();

    return sceneElements.map((element) => {
        const sceneLinkElement = $(element).find('.thmb_lnk');
        const title = sceneLinkElement.attr('title');
        const url = `https://bangbros.com${sceneLinkElement.attr('href')}`;
        const shootId = sceneLinkElement.attr('id') && sceneLinkElement.attr('id').split('-')[1];
        const entryId = url.split('/')[3].slice(5);

        const date = moment.utc($(element).find('.thmb_mr_2 span.faTxt').text(), 'MMM D, YYYY').toDate();
        const actors = $(element).find('.cast-wrapper a.cast').map((actorIndex, actorElement) => $(actorElement).text().trim()).toArray();

        const photoElement = $(element).find('.rollover-image');
        const poster = `https:${photoElement.attr('data-original')}`;

        const photosUrl = photoElement.attr('data-rollover-url');
        const photosMaxIndex = photoElement.attr('data-rollover-max-index');
        const photos = Array.from({ length: photosMaxIndex }, (val, index) => `https:${photosUrl}big${index + 1}.jpg`);

        const duration = moment.duration(`0:${$(element).find('.thmb_pic b.tTm').text()}`).asSeconds();
        const channel = $(element).find('a[href*="/websites"]').attr('href').split('/').slice(-1)[0];

        return {
            url,
            entryId,
            shootId,
            title,
            actors,
            date,
            duration,
            poster,
            photos,
            rating: null,
            site,
            channel,
        };
    });
}

/* no dates available, breaks database
function scrapeUpcoming(html, site) {
    const { document } = ex(html);

    return ctxa(document, 'a[id*="upcoming-videos"]').map(({ element, q }) => {
        const release = {};
        [release.shootId] = element.id.split('-').slice(-1);
        const siteCode = release.shootId.match(/[a-z]+/)[0];

        if (siteCode !== site.parameters.code) {
            return null;
        }

        const posterEl = q('img');

        [release.entryId] = element.href.split('/')[1].match(/\d+/);
        release.url = `https://bangbros.com${element.href}`;
        release.title = posterEl.alt;
        release.poster = `https:${posterEl.src}`;

        release.actors = q('.castName', true).split(/ in/g).slice(0, -1).map(actorName => actorName.trim());

        console.log(release);

        return release;
    }).filter(Boolean);
}
*/

function scrapeScene(html, url, _site) {
    const { qu } = ex(html, '.playerSection');
    const release = {};

    [release.shootId] = qu.q('.vdoTags + .vdoCast', true).match(/\w+$/);
    [release.entryId] = url.split('/')[3].match(/\d+$/);
    release.title = qu.q('.ps-vdoHdd h1', true);
    release.description = qu.q('.vdoDesc', true);

    release.actors = qu.all('a[href*="/model"]', true);
    release.tags = qu.all('.vdoTags a', true);

    release.stars = Number(qu.q('div[class*="like"]', true).match(/^\d+/)[0]) / 20;

    const poster = qu.img('img#player-overlay-image');
    release.poster = [
        poster,
        poster.replace('/big_trailer', '/members/450x340'), // load error fallback
    ];

    release.trailer = { src: qu.trailer() };

    // all scenes seem to have 12 album photos available, not always included on the page
    const firstPhotoUrl = ex(html).qu.img('img[data-slider-index="1"]');
    release.photos = Array.from({ length: 12 }, (val, index) => firstPhotoUrl.replace(/big\d+/, `big${index + 1}`));

    const [channel] = qu.url('a[href*="/websites"]').match(/\w+$/);
    release.channel = channel === 'bangcasting' ? 'bangbroscasting' : channel;

    return release;
}

function scrapeProfile(html) {
    const { q } = ex(html);
    const profile = {};

    const avatar = q('.profilePic img', 'src');
    if (avatar) profile.avatar = `https:${avatar}`;

    profile.releases = scrape(html);

    return profile;
}

function scrapeProfileSearch(html, actorName) {
    const { q } = ex(html);
    const actorLink = q(`a[title="${actorName}"]`, 'href');

    return actorLink ? `https://bangbros.com${actorLink}` : null;
}

async function fetchLatest(site, page = 1) {
    const res = await bhttp.get(`${site.url}/${page}`);

    return scrape(res.body.toString(), site);
}

/*
async function fetchUpcoming(site) {
    const res = await bhttp.get('https://www.bangbros.com');

    return scrapeUpcoming(res.body.toString(), site);
}
*/

async function fetchScene(url, site, release) {
    if (!release?.date) {
        throw new Error(`Cannot fetch Bang Bros scenes from argument URL, as scene pages do not have release dates: ${url}`);
    }

    const { origin } = new URL(url);
    const res = await bhttp.get(url);

    if (!/https?:\/\/(www.)?bangbros.com\/?$/.test(origin)) {
        throw new Error('Cannot fetch from this URL. Please find the scene on https://bangbros.com and try again.');
    }

    return scrapeScene(res.body.toString(), url, site);
}

async function fetchProfile(actorName) {
    const actorSlug = slugify(actorName);
    const url = `https://bangbros.com/search/${actorSlug}`;
    const res = await bhttp.get(url);

    if (res.statusCode === 200) {
        const actorUrl = scrapeProfileSearch(res.body.toString(), actorName);

        if (actorUrl) {
            const actorRes = await bhttp.get(actorUrl);

            if (actorRes.statusCode === 200) {
                return scrapeProfile(actorRes.body.toString());
            }
        }
    }

    return null;
}

module.exports = {
    fetchLatest,
    fetchScene,
    fetchProfile,
    // fetchUpcoming, no dates available
};