traxxx/src/scrapers/mikeadriano.js

'use strict';

const unprint = require('unprint');

const http = require('../utils/http');
const { convert } = require('../utils/convert');

function scrapeAll(scenes, channel) {
	return scenes.map(({ query }) => {
		const release = {};

		release.title = query.content('h3.title a, .content-title-wrap a');
		release.url = query.url('h3.title a, h1.title a, .content-title-wrap a', { origin: channel.url });

		const pathname = new URL(release.url).pathname;

		release.entryId = pathname.match(/\/scenes\/([\w-]+)/)?.[1];

		release.description = query.content('.desc, .content-description');
		release.date = query.date('.date, time, .hide', 'Do MMM YYYY', { match: null });

		release.actors = query.contents('h4.models a, .content-models a');
		release.duration = query.duration('//span[contains(@class, "total-time") and text()[contains(., ":")]]'); // total-time is also used for photo counts on True Anal

		const [poster, ...primaryPhotos] = query.imgs('a img');
		const secondaryPhotos = query.styles('.thumb-top, .thumb-bottom, .thumb-mouseover', { styleAttribute: 'background-image' }).map((style) => style.match(/url\((.*)\)/)?.[1]);

		release.poster = [
			poster.replace(/-c\d+x\d+/, ''),
			poster,
		];

		release.photos = primaryPhotos.concat(secondaryPhotos);

		return release;
	});
}

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

	const pathname = new URL(url).pathname;
	const data = query.json('#__NEXT_DATA__')?.props?.pageProps?.content;

	release.entryId = data?.slug || pathname.match(/\/scenes\/([\w-]+)/)?.[1];

	release.title = data?.title || query.content('.content-page-info .title');
	release.description = data?.description || query.content('.content-page-info .desc');
	release.date = data?.formatted_date
		? unprint.extractDate(data.formatted_date, 'Do MMM YYYY', { match: null })
		: query.date('.content-page-info .date, .content-page-info .hide, .post-date', 'Do MMM YYYY', { match: null });

	release.actors = data?.models_thumbs?.map((actor) => ({
		name: actor.name,
		url: actor.slug && `${channel.url}/models/${actor.slug}`,
		avatar: actor.thumb,
	}))
		|| query.elements('.content-page-info .models a').map((actorEl) => ({
			name: unprint.query(actorEl),
			url: unprint.url(actorEl, null),
		}));

	release.duration = data?.seconds_duration || query.duration('.content-page-info .total-time:last-child');

	release.poster = [data?.trailer_screencap, data?.thumb, data?.extra_thumbails?.[0]].filter(Boolean);
	release.photos = data?.extra_thumbnails?.slice(1); // first photo is poster

	release.trailer = data?.trailer_url || null;
	release.caps = data?.thumbs;

	release.tags = data?.tags;

	release.qualities = data?.videos && Object.values(data.videos).map((video) => video.height);

	return release;
}

async function fetchLatestContent(url, parameters) {
	if (parameters.useBrowser) {
		const res = await http.get(url, {
			bypassBrowser: 'shared',
			bypass: {
				evaluate: async () => {
					// images lazy loaded by JS, gradually scroll through page
					return Array.from(document.querySelectorAll('.content-item ')).reduce(async (chain, el) => {
						await chain;

						return new Promise((resolve) => {
							el.scrollIntoView();
							setTimeout(resolve, 20);
						});
					}, Promise.resolve());
				},
			},
		});

		if (res.statusCode !== 200) {
			return {
				ok: false,
				status: res.statusCode,
			};
		}

		const context = unprint.init(res.body);

		return {
			ok: true,
			status: res.statusCode,
			context,
		};
	}

	const res = await unprint.get(url);

	return res;
}

async function fetchLatest(channel, page = 1, { parameters }) {
	const url = `${channel.url}/scenes?page=${page}`;
	const res = await fetchLatestContent(url, parameters);

	if (res.ok) {
		if (res.context.query.exists('a[href*="stackpath.com"]')) {
			throw new Error('URL blocked by StackPath');
		}

		return scrapeAll(unprint.initAll(res.context.query.all('.content-item-large, .content-item, .content-border')), channel);
	}

	return res.status;
}

async function fetchScene(url, channel) {
	const cookieJar = http.cookieJar();
	const session = http.session({ cookieJar });

	const res = await http.get(url, {
		session,
	});

	if (res.ok) {
		const context = unprint.init(res.body);

		if (context.query.exists('a[href*="stackpath.com"]')) {
			throw new Error('URL blocked by StackPath');
		}

		return scrapeScene(context, url, channel);
	}

	return res.status;
}

async function scrapeProfile(data) {
	const profile = {};
	// unreliable key case, lowercase all
	const bio = Object.fromEntries(Object.entries(data).map(([key, value]) => [key.toLowerCase(), value]));

	profile.entryId = bio.id;

	profile.gender = bio.gender;
	profile.description = bio.bio;

	profile.birthPlace = bio.born;
	profile.dateOfBirth = unprint.extractDate(bio.birthdate, 'YYYY-MM-DD');
	profile.age = bio.age;

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

	profile.eyes = bio.eyes;
	profile.hairColor = bio.hair;

	profile.avatar = bio.thumb;

	const tags = bio.tags?.split(',') || [];

	if (tags.includes('tattoos')) profile.hasTattoos = true;
	if (tags.includes('piercing')) profile.hasPiercings = true;

	return profile;
}

async function fetchProfile(actor, context) {
	const url = `${context.channel.url}/models/${actor.slug}`;

	const res = await unprint.get(url, {
		parser: {
			runScripts: 'dangerously',
		},
	});

	if (res.ok) {
		const data = res.context.query.json('#__NEXT_DATA__');

		if (data.props.pageProps.model) {
			return scrapeProfile(data.props.pageProps.model, context.channel);
		}

		return null;
	}

	return res.status;
}

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