traxxx/src/scrapers/julesjordan.js

'use strict';

const util = require('util');
const unprint = require('unprint');

const argv = require('../argv');
const { heightToCm } = require('../utils/convert');
const slugify = require('../utils/slugify');
const tryUrls = require('../utils/try-urls');

function getEntryId(url) {
	if (!url) {
		return null;
	}

	const entryId = new URL(url).pathname.split('/').at(-1).match('(.*?)_vids.html');

	if (entryId) {
		return slugify(entryId[1]);
	}

	return null;
}

function scrapeAll(scenes, site) {
	return scenes.map(({ query }) => {
		const release = {};
		const title = query.content('.jj-card-title, .content_img div, .dvd_info > a, a.update_title, .update_title a, a[title] + a[title], .overlay-text')
			|| query.content('a[title*=" "]');

		release.title = title?.slice(0, title.match(/starring:/i)?.index || Infinity).trim();
		release.url = query.url('.jj-card-thumb, .content_img a, .dvd_info > a, a.update_title, .update_title a, a[title]');
		release.date = query.date('.jj-card-date, .update_date', ['MM/DD/YYYY', 'YYYY-MM-DD', 'MMMM D, YYYY']);

		release.entryId = getEntryId(release.url);

		release.actors = query.all('.content_img .update_models a, .update_models a').map((actorEl) => ({
			name: unprint.query.content(actorEl),
			url: unprint.query.url(actorEl, null),
		}));

		const dvdPhotos = query.imgs('.dvd_preview_thumb');
		const photoCount = Number(query.attribute('a img.thumbs', 'cnt')) || 1;

		[release.poster, ...release.photos] = dvdPhotos.length
			? dvdPhotos
			: Array.from({ length: photoCount }).map((_value, index) => {
				const src = query.img('a img.thumbs', { attribute: `src${index}_1x` }) || query.img('a img.thumbs', { attribute: `src${index}` }) || query.img('a img.thumbs');
				const prefixedSrc = unprint.prefixUrl(src, site.url);

				if (src) {
					return Array.from(new Set([
						prefixedSrc.replace(/.jpg$/, '-full.jpg'),
						prefixedSrc.replace(/-1x.jpg$/, '-4x.jpg'),
						prefixedSrc.replace(/-1x.jpg$/, '-2x.jpg'),
						prefixedSrc,
					])).map((source) => ({
						src: source,
						referer: site.url,
						verifyType: 'image',
					}));
				}

				return null;
			}).filter(Boolean);

		release.teaser = query.video('.jj-card-video', { attribute: 'data-src' });

		if (!release.teaser) {
			const teaserScript = query.html('script');

			if (teaserScript) {
				release.teaser = teaserScript.slice(teaserScript.indexOf('http'), teaserScript.indexOf('.mp4') + 4);
			}
		}

		return release;
	});
}

async function fetchLatest(site, page = 1, include, preData, entryIdFromTitle = false) {
	const url = site.parameters?.latest
		? util.format(site.parameters.latest, page)
		: `${site.url}/trial/categories/movies_${page}_d.html`;

	// const res = await http.get(url);
	const res = await unprint.get(url, { selectAll: '.scenes-listing-grid .jj-content-card' });

	if (res.ok) {
		return scrapeAll(res.context, site, typeof site.parameters?.entryIdFromTitle === 'boolean' ? site.parameters.entryIdFromTitle : entryIdFromTitle);
	}

	return res.status;
}

/* disable until we have entryId solution
function scrapeUpcoming(scenes, _channel) {
	return scenes.map(({ query, html }) => {
		const release = {};

		release.title = query.text('.overlay-text', { join: false })?.[0];
		release.date = query.date('.overlay-text', ['MM/DD/YYYY', 'YYYY-MM-DD']);

		release.actors = query.all('.update_models a').map((actorEl) => ({
			name: unprint.query.content(actorEl),
			url: unprint.query.url(actorEl, null),
		}));

		release.poster = query.img('img') || query.img('img', { attribute: 'src0_1x' });
		release.teaser = html.match(/src=['"](https:\/\/.*\.mp4)['"]/)?.[1];

		release.entryId = channel.parameters?.entryIdFromTitle
			? getEntryIdFromTitle(release)
			: getEntryId(html);

		return release;
	});
}

async function fetchUpcoming(site) {
	if (site.parameters?.upcoming === false) return null;

	const url = site.parameters?.upcoming ? util.format(site.parameters.upcoming) : `${site.url}/trial/index.php`;
	const res = await unprint.get(url, { selectAll: '//img[contains(@alt, "Coming Soon")]/ancestor::div' });

	if (res.ok) {
		return scrapeUpcoming(res.context, site);
	}

	return res.status;
}
*/

function extractLegacyTrailer(html, context) {
	const trailerLines = html.split('\n').filter((line) => /movie\["trailer\w*"\]\[/i.test(line));

	if (trailerLines.length) {
		return trailerLines.map((trailerLine) => {
			// const src = trailerLine.match(/path:"([\w-:/.&=?%]+)"/)?.[1];
			const src = trailerLine.match(/path:"(.+)"/)?.[1];
			const quality = trailerLine.match(/movie_height:'(\d+)/)?.[1];

			return src && {
				src: /^http/.test(src) ? src : `${context.entity.url}${src}`,
				quality: quality && Number(quality.replace('558', '540')),
			};
		}).filter(Boolean);
	}

	return null;
}

const qualities = [
	'photos',
	'1600watermarked',
	'1280watermarked',
	'1024watermarked',
	'thumbs',
];

function getPhotos(query, release, context) {
	// https://thumbs.julesjordan.com/members/content//upload/dl03/julesjordan/whitney_wright_dredd/1024watermarked/whitney_wright_julesjordan.com-20.jpg
	// https://thumbs.julesjordan.com/members/content//upload/dl03/julesjordan/bambi_barton_manuel_ferrara/1024watermarked/bambi_barton_julesjordan_com-13.jpg
	if (!release.actors?.length > 0) {
		return null;
	}

	const photoCount = query.number('//div[contains(@class, "title-heading-content")][contains(text(), "Photos")]');

	if (photoCount) {
		// slug actor order is not always the same as actor list order, prefer trailer slug if available
		const path = query.dataset('.movieformat_button', 'src')?.match(/:(.*)_trailer/)?.[1] || release.actors.map((actor) => slugify(actor.name || actor, '_')).join('_');

		const derivedActorSlug = path.replace(`_${release.actors.slice(1).map(({ name }) => slugify(name, '_'))}`, '');
		const actorSlug = derivedActorSlug === path // no replacement took place, so the slug is likely invalid
			? slugify(release.actors[0].name || release.actors[0], '_')
			: derivedActorSlug;

		return Array.from({ length: photoCount }, (value, index) => qualities
			.flatMap((quality) => [
				`https://thumbs.${context.entity.slug}.com/trial/content//upload/dl03/${context.entity.slug}/${path}/${quality}/${actorSlug}_${context.entity.slug}_com-${index + 1}.jpg`,
				`https://thumbs.${context.entity.slug}.com/trial/content//upload/dl03/${context.entity.slug}/${path}/${quality}/${actorSlug}_${context.entity.slug}.com-${index + 1}.jpg`, // .com instead of _com
			]).map((src) => ({ src, attempts: 1 })));
	}

	return null;
}

async function scrapeScene({ html, query }, context) {
	const release = {};

	release.entryId = getEntryId(context.url);

	release.title = query.content('.scene-title, .title_bar_hilite, .movie_title');
	release.description = query.content('.scene-desc, .update_description') || query.text('//div[./span[contains(text(), "Description")]]');

	release.date = query.date(['.meta-item:nth-child(2) .val, .update_date', '//div[./span[contains(text(), "Date")]]'], ['MM/DD/YYYY', 'YYYY-MM-DD', 'MMMM D, YYYY']);

	release.actors = query.all('.meta-item .update_models a, .backgroundcolor_info > .update_models a, .item .update_models a, .player-scene-description .update_models a').map((actorEl) => ({
		name: unprint.query.content(actorEl),
		url: unprint.query.url(actorEl, null),
	}));

	release.tags = query.contents('.scene-cats a, .update_tags a, .player-scene-description a[href*="/categories"]');
	release.director = release.tags?.find((tag) => ['mike john', 'van styles'].includes(tag?.trim().toLowerCase()));

	const posterPath = query.poster('#video-player', { forceGetAttribute: true }) // without getAttribute, missing poster is returned as page URL
		|| html.match(/useimage = "(.*)"/)?.[1];

	if (posterPath) {
		const poster = /^http/.test(posterPath) ? posterPath : `${context.entity.url}${posterPath}`;

		if (poster) {
			release.poster = {
				src: poster,
				referer: context.entity.url,
			};
		}
	}

	if (query.exists('source[data-bitrate="trailer"]')) {
		release.trailer = [
			query.video('source[data-bitrate="trailer_1080" i]'),
			query.video('source[data-bitrate="trailer_720" i]'),
			query.video('source[data-bitrate="trailer" i]'), // also seems to be 720p
			query.video('source[data-bitrate="trailer_mobile" i]'), // also seems to be 720p
		].filter(Boolean);
	} else if (context.include.trailers && context.entity.slug !== 'manuelferrara') {
		release.trailer = extractLegacyTrailer(html, context);
	}

	if (release.trailer?.includes('_sfw')) {
		release.trailer = null;
	}

	// release.photos = async () => await getPhotos(release.entryId, context.entity); // probably no longer works on any site
	if (argv.jjFullPhotos) {
		release.photos = getPhotos(query, release, context);
	} else {
		// base release photos are usually better, but deep photos have additional thumbs
		// the filenames are not chronological, so sorting after appending only worsens the mix.
		// #images img selects a list of images that is present on every page; the JJ website removes the ones that failed to load with JS (lol)
		release.photos = [
			...context.baseRelease?.photos?.map((sources) => sources.at(-1).src) || [],
			...query.imgs('.tp-photos-strip img, #images img'),
			...query.imgs('img.update_thumb', { attribute: 'src0_1x' }),
		].filter(Boolean).map((source) => Array.from(new Set([
			source.replace(/.jpg$/, '-full.jpg'),
			source.replace(/-1x.jpg$/, '-4x.jpg'),
			source.replace(/-1x.jpg$/, '-2x.jpg'),
			source,
		])).map((fallbackSource) => ({
			src: fallbackSource,
			referer: context.entity.url,
			verifyType: 'image',
		})));
	}

	if (query.exists('.player-scene-description a[href*="/dvd"]')) {
		release.movie = {
			url: query.url('.player-scene-description a[href*="/dvd"]'),
			title: query.content('.player-scene-description a[href*="/dvd"]'),
		};

		release.movie.entryId = new URL(release.movie.url).pathname.split('/').slice(-1)[0]?.replace('.html', '').toLowerCase();
	}

	release.stars = query.number('.avg_rating');

	release.qualities = query.contents('.res-item .res-lbl').map((resolution) => Number(resolution.match(/\d+$/)?.[0])).filter(Boolean);

	return release;
}

function scrapeMovie({ query }, { url }) {
	const movie = {};

	movie.entryId = new URL(url).pathname.split('/').slice(-1)[0]?.replace('.html', '').toLowerCase();
	movie.title = query.attribute('meta[property="og:title"]', 'content');

	movie.covers = [query.img('img.dvd_box')]; // -2x etc is likely upscaled

	const sceneTitles = query.contents('.title-heading-content-black-dvd');

	const scenes = query.all('.grid-container-scene').map((sceneEl, index) => {
		const scene = {};

		scene.url = unprint.query.url(sceneEl, 'a[href*="/scenes"]');
		scene.title = sceneTitles[index];

		scene.date = unprint.query.date(sceneEl, '//span[contains(@class, "dvd-scene-description") and span[contains(text(), "Date")]]', 'MM/DD/YYYY');
		scene.actors = unprint.query.contents(sceneEl, '.update_models a');

		scene.entryId = getEntryId(scene.url);

		return scene;
	});

	movie.scenes = scenes?.sort((sceneA, sceneB) => sceneA.date - sceneB.date);

	movie.date = movie.scenes?.[0]?.date;
	movie.datePrecision = 'month';

	return movie;
}

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

	profile.description = query.content('//comment()[contains(., " Bio Extra Field ")]/following-sibling::span') // the spaces are important to avoid selecting a similar comment
		|| query.content('//comment()[contains(., " Bio Extra Field ")]/following-sibling::text()');

	profile.height = heightToCm(query.content('//span[contains(text(), "Height")]/following-sibling::span'));
	profile.measurements = query.content('//span[contains(text(), "Measurements")]/following-sibling::span');

	const age = query.content('//span[contains(text(), "Age")]/following-sibling::span')?.trim();

	if (age && /\w+ \d+, \d{4}/.test(age)) {
		profile.dateOfBirth = unprint.extractDate(age, 'MMMM D, YYYY');
	} else {
		profile.age = Number(age) || null;
	}

	profile.avatar = [
		query.img('.model_bio_pic img, .model_bio_thumb', { attribute: 'src0_3x' }),
		query.img('.model_bio_pic img, .model_bio_thumb', { attribute: 'src0_2x' }),
		query.img('.model_bio_pic img, .model_bio_thumb', { attribute: 'src0_1x' }),
		query.img('.model_bio_pic img, .model_bio_thumb', { attribute: 'src0' }),
		query.img('.model_bio_pic img, .model_bio_thumb', { attribute: 'src' }),
		// ...query.sourceSet('.model_bio_pic img, .model_bio_thumb', { origin: entity.url }),
	].filter(Boolean).map((src) => ({
		src,
		referer: entity.url,
		verifyType: 'image',
	}));

	profile.scenes = scrapeAll(unprint.initAll(query.all('.mbp-scenes-grid .jj-content-card, .grid-item')), entity, true);

	return profile;
}

async function fetchProfile({ name: actorName, url: actorUrl }, entity) {
	const actorSlugA = slugify(actorName, '');
	const actorSlugB = slugify(actorName, '-');

	const urls = [
		actorUrl,
		`${entity.parameters?.profile || `${entity.url}/trial/models`}/${actorSlugA}.html`,
		`${entity.parameters?.profile || `${entity.url}/trial/models`}/${actorSlugB}.html`,
	];

	const { res, url } = await tryUrls(urls);

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

	return res.status;
}

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