traxxx/src/scrapers/naughtyamerica.js

'use strict';

const unprint = require('unprint');

const slugify = require('../utils/slugify');
const { stripQuery } = require('../utils/url');

const channelMap = {
	spa: 'thespa',
	gym: 'thegym',
	dormroom: 'thedormroom',
	dressingroom: 'thedressingroom',
	psepornstarexperience: 'pornstarexperience',
	office: 'theoffice',
	ta: 'tanda',
};

function scrapeLatest(scenes, channel) {
	return scenes.map(({ query }) => {
		const release = {};
		const url = query.url('a');

		release.entryId = query.attribute('a', 'data-scene-id') || (url && new URL(url).pathname.match(/-(\d+)$/)?.[1]) || null;

		release.date = query.date('.entry-date, .scene-date', 'MMM D, YYYY');
		release.duration = query.duration('.scene-runtime');

		release.actors = query.all('.contain-actors a, .scene-actors a').map((actorEl) => ({
			name: unprint.query.content(actorEl),
			url: channel.parameters?.useActorUrl === false
				? null // actor URL is scene link in native layout
				: unprint.query.url(actorEl, null),
		}));

		release.poster = [
			...(query
				.sourceSet('source[data-srcset*="scenes/"][type="image/jpeg"]', 'data-srcset', { includeDescriptor: true })
				?.toSorted((sourceA, sourceB) => sourceB.density - sourceA.density)
				.map((source) => source.url) || []),
			query.img('.main-scene-img', { attribute: 'srcset' }),
			query.img('.scene-thumb'),
		].filter(Boolean);

		release.teaser = query.video('a[data-desktop-video]', { attribute: 'data-desktop-video' });

		release.tags = query.contents('.flag-bg');

		release.qualities = [
			query.exists('//a[contains(@class, "label-four-k") and contains(text(), "4K")] | //span[contains(@class, "bug-4k")]') && 2160, // label-four-k is also used for non-4K tags
			query.exists('//a[contains(@class, "label-hd") and contains(text(), "HD")]') && 720,
		].filter(Boolean);

		const channelSlug = slugify(query.content('.site-title'), '');

		release.channel = channelMap[channelSlug] || channelSlug;

		// NA affiliate prefers to push more traffic to Naughty America VR, all scenes labeled VR seem to be available on NAVR
		release.url = release.tags?.some((tag) => tag.toLowerCase() === 'vr')
			? url.replace('naughtyamerica.com', 'naughtyamericavr.com')
			: url;

		return release;
	});
}

async function fetchLatest(channel, page = 1, { parameters }) {
	const url = parameters.latest || `${channel.url}${parameters?.scenes || ''}`;

	const res = await unprint.browserRequest(`${url}?page=${page}`, {
		selectAll: '.site-list .scene-item, .panel-body',
		async control(ctx) {
			await ctx.locator('.site-list, .grid-three').hover({ trial: true, timeout: 10000 }); // wait for overview to initialize
		},
	});

	if (res.ok) {
		const scenes = scrapeLatest(res.context, channel, parameters);

		return scenes;
	}

	return res.status;
}

function scrapeScene({ query }, { url }) {
	const release = {};

	release.entryId = new URL(url).pathname.match(/-(\d+)$/)?.[1];

	// release.title = query.content('.breadcrumb-item.active') || query.content('.scene-title, .grey-title'); // main title has performer name instead of scene title in live scenes
	release.title = query.content('.scene-title, .grey-title'); // breadcrumb as used before often doesn't have title
	release.description = query.text('.synopsis, .scene-description');

	release.date = query.date('.entry-date, .released-date', ['MMM D, YYYY', 'MM/DD/YY']);
	release.duration = query.duration('.duration');

	release.actors = query.exists('.performer-list') || query.exists('.scene-info a[href*="/pornstar"].scene-title') // title links to performer in live scenes
		? query.all('.performer-list a, .grey-performers a, .scene-info a[href*="/pornstar"].scene-title').map((actorEl) => ({
			name: unprint.query.content(actorEl),
			url: stripQuery(unprint.query.url(actorEl, null)),
		}))
		: query.content('.grey-performers')?.split(',').map((actorName) => actorName.trim()); // not all performers are linked

	release.poster = [
		...(query.sourceSet('.play-trailer source[data-srcset*="scenes/"][type="image/jpeg"]', 'data-srcset') || []),
		...(query.sourceSet('.scenepage-video source[srcset*="scenes/"][type="image/jpeg"]', 'srcset') || []),
		query.img('.play-trailer img[data-srcset*="scenes/"]', { attribute: 'data-srcset' }),
		query.img('.scenepage-video .playcard'),
		query.img('.scene-page .start-card'),
		query.poster('dl8-video[poster]'),
	].filter(Boolean);

	release.photos = query.els('.contain-scene-images.desktop-only .scene-image').map((imgEl) => [
		unprint.query.url(imgEl, null),
		unprint.query.img(imgEl, 'img', { attribute: 'srcset' }),
	]);

	const trailer = query.video('#triggerPlay video source');

	if (trailer) {
		release.trailer = [
			{
				source: trailer.replace(/_\d+\.mp4/, '_1080.mp4'),
				quality: 1080,
			},
			trailer,
		];
	}

	const channelSlug = slugify(query.content('.site-title'), '');

	release.channel = channelMap[channelSlug] || channelSlug;

	release.tags = query.contents('.categories a, .category a');

	release.qualities = [
		query.exists('//a[contains(@class, "label-four-k") and contains(text(), "4K")]') && 2160, // label-four-k is also used for non-4K tags
		query.exists('img.icon-1080') && 1080,
		query.exists('//a[contains(@class, "label-hd") and contains(text(), "HD")]') && 720,
	].filter(Boolean);

	return release;
}

async function fetchScene(url, _channel) {
	// latest set NaughtyAmericaVR URL, but try deep scrape from regular NA website
	const res = await unprint.browserRequest(url.replace('naughtyamericavr.com', 'naughtyamerica.com'), {
		async control(ctx) {
			await ctx.locator('.scene-info, .scene').first().hover({ trial: true, timeout: 30000 }); // wait for trailer to initialize
		},
	});

	if (res.ok) {
		const scene = scrapeScene(res.context, { url });

		return scene;
	}

	return res.controlError || res.status;
}

async function scrapeProfile({ query }) {
	const profile = {};

	profile.description = query.content('.bio_about_text, .performer-description');
	profile.avatar = query.img('img.performer-pic, img.performer-img, img.peformer-img'); // sic peformer

	return profile;
}

async function fetchProfile({ slug }, { channel }) {
	const url = unprint.prefixUrl(`/pornstar/${slug}`, channel.url);

	const res = await unprint.browserRequest(url, {
		select: '.bio-info, .performer-details',
		async control(ctx) {
			await ctx.locator('.bio-info, .performer-details').hover({ trial: true, timeout: 30000 }); // wait for bio to initialize
		},
	});

	if (res.ok) {
		const profile = scrapeProfile(res.context, { url });

		return profile;
	}

	return res.status;
}

module.exports = {
	fetchLatest,
	fetchScene,
	fetchProfile,
};