traxxx/src/scrapers/loveherfilms.js

'use strict';

const unprint = require('unprint');

const slugify = require('../utils/slugify');
const { convert } = require('../utils/convert');
// const { getImageWithFallbacks } = require('./elevatedx');

function curateSources(item) {
	if (!item) {
		return null;
	}

	if (item.sources) {
		return item.sources
			.toSorted((sourceA, sourceB) => sourceB.resolution - sourceA.resolution)
			.map((source) => source.path);
	}

	return item.previewImage;
}

function scrapeScene(data, channel) {
	const release = {};

	release.entryId = data.slug?.toLowerCase(); // _id can't be used for API lookup
	release.url = data.slug && `${channel.origin}/tour/trailers/${data.slug}.html`;

	release.title = data.title;
	release.description = data.description;

	release.date = new Date(data.releaseDateVideo);

	release.actors = data.models?.map((actor) => ({
		name: actor.modelName,
		url: actor.slug && `${channel.origin}/tour/models/${actor.slug}.html`,
		entryId: actor._id,
	}));

	release.tags = data.categories?.map((category) => category.title);

	if (data.type?.toLowerCase() === 'bts') {
		release.tags = release.tags.concat('bts');
	}

	release.poster = curateSources(data.thumb);
	release.photos = [...data.photos?.map((photo) => curateSources(photo)) || []].filter(Boolean);

	if (data.thumbHover && data.thumbHover.baseName !== '849') { // placeholder image
		release.photos = release.photos.concat([curateSources(data.thumbHover)]);
	}

	const trailerType = data.trailer?.type === 'previewTrailer'
		? 'teaser'
		: 'trailer';

	release[trailerType] = data.trailer?.sources?.map((source) => ({
		src: source.path,
		quality: source.quality || source.height || null, // only available on teaser
		expectType: {
			'application/octet-stream': 'video/mp4',
		},
	}));

	return release;
}

async function fetchLatest(channel, page = 1, { parameters }) {
	// bonus-type scenes are third-party, don't include
	const url = `${channel.origin.replace('www.', 'api.')}/v1/content-sets?types[]=Content&types[]=Tease&types[]=BTS&sort=latest&limit=27&offset=${(page - 1) * 27}`;

	const res = await unprint.get(url, {
		interface: 'request',
		headers: {
			'X-Site-Id': parameters.xSiteId,
		},
	});

	if (res.ok && res.data?.items) {
		return res.data.items.map((item) => scrapeScene(item, channel));
	}

	return res.status;
}

/* no entry ID, enable when two entry IDs are supported
async function fetchUpcoming(channel, _page, { parameters }) {
	// unsure if site ID parameter is necessary when the header is present, but the site uses it
	const url = `${channel.origin.replace('www.', 'api.')}/v1/content-sets/upcoming?siteId${parameters.xSiteId}`;

	const res = await unprint.get(url, {
		interface: 'request',
		headers: {
			'X-Site-Id': parameters.xSiteId,
		},
	});

	if (res.ok && res.data) {
		return res.data.map((item) => scrapeScene(item, channel));
	}

	return res.status;
}
*/

async function fetchScene(sceneUrl, entity, _baseRelease, { parameters }) {
	// deep data not identical, contains photoset and full trailer
	const slug = new URL(sceneUrl).pathname.match(/\/trailers\/(.*?)\.html/)[1];
	const url = `${entity.origin.replace('www.', 'api.')}/v1/content-sets/${slug}`;

	const res = await unprint.get(url, {
		interface: 'request',
		headers: {
			'X-Site-Id': parameters.xSiteId,
		},
	});

	if (res.ok && res.data) {
		return scrapeScene(res.data, entity);
	}

	return res.status;
}

function scrapeProfile({ query }, url) {
	const profile = { url };

	const bio = Object.fromEntries(query.all('ul[class*="HeroModel_list"] li').map((bioEl) => [
		slugify(unprint.query.content(bioEl, 'p:first-child'), '_'),
		unprint.query.content(bioEl, 'p:last-child'),
	]));

	profile.description = query.content('p[class*="HeroModel_text"]');
	profile.birthPlace = bio.place_of_birth;

	profile.dateOfBirth = unprint.extractDate(bio.date_of_birth, ['MMMM DD, YYYY', 'MM/DD/YYYY']);
	profile.ethnicity = bio.ethnicity;

	profile.measurements = bio.measurements;
	profile.height = convert(bio.height, 'cm');
	profile.weight = convert(bio.weight, 'lb', 'kg');

	profile.hairColor = bio.hair_color;
	profile.eyes = bio.eye_color;

	profile.foot = unprint.extractNumber(bio.feet_size, { match: /\((\d+(.\d+)?) eur\)/i, matchIndex: 1 });

	if (/(natural)|(real)/i.test(bio.boob_type || bio.tits_type)) {
		profile.naturalBoobs = true;
	}

	if (/(enhanced)|(fake)/i.test(bio.boob_type || bio.tits_type)) {
		profile.naturalBoobs = false;
	}

	if (bio.tattoos) {
		profile.hasTattoos = !/none/i.test(bio.tattoos);
		profile.tattoos = profile.hasTattoos ? bio.tattoos : null;
	}

	if (bio.piercings) {
		profile.hasPiercings = !/none/i.test(bio.piercings);
		profile.piercings = profile.hasPiercings ? bio.piercings : null;
	}

	profile.avatar = query.sourceSet('picture[class*="modelImage"] img');

	return profile;
}

async function getActorUrl(actor, { entity, parameters }) {
	if (actor.url) {
		return actor.url;
	}

	const url = `${entity.origin.replace('www.', 'api.')}/v1/models?limit=12&offset=0&query=&sort=latest&modelsNames[]=${slugify(actor.name, '+')}`;

	const res = await unprint.get(url, {
		interface: 'request',
		headers: {
			'X-Site-Id': parameters.xSiteId,
		},
	});

	if (res.ok) {
		const actorSlug = res.data.items?.find((item) => slugify(item.modelName) === actor.slug)?.slug;

		if (actorSlug) {
			return `${entity.origin}/tour/models/${actorSlug}.html`;
		}
	}

	return null;
}

async function fetchProfile(actor, context) {
	const actorUrl = await getActorUrl(actor, context);

	if (!actorUrl) {
		return null;
	}

	const res = await unprint.get(actorUrl);

	if (res.ok) {
		return scrapeProfile(res.context, actorUrl, context);
	}

	return res.status;
}

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