traxxx/src/scrapers/bradmontana.js

'use strict';

const qu = require('../utils/q');
const slugify = require('../utils/slugify');

function genderFromUrl(url) {
	const { pathname } = new URL(url);

	if (/atores/.test(pathname)) {
		return 'male';
	}

	if (/atrizes/.test(pathname)) {
		return 'female';
	}

	return null;
}

function scrapeAll(scenes) {
	return scenes.map(({ query }) => {
		const release = {};
		const subtitle = query.cnt('.subtitle');

		release.url = query.url('a');
		release.entryId = new URL(release.url).pathname.match(/\/videos\/([\w-]+)/)[1];

		release.title = query.cnt('.title') || query.q('img', 'title');
		release.actors = subtitle.slice(subtitle.indexOf(':') + 1).split(',').map((actor) => actor.trim()).filter(Boolean);

		release.poster = query.img('.thumb img');

		if (release.poster) {
			const match = release.poster.match(/\/uploads\/(\d{4})\/(\d{2})/);

			if (match) {
				release.date = new Date(match[1], match[2] - 1, 1);
				release.datePrecision = 'month';
			}
		}

		return release;
	});
}

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

	const dataString = query.html('.yoast-schema-graph');
	const data = dataString && JSON.parse(dataString)['@graph'];
	const pageData = data.find((item) => item['@type'] === 'WebPage');
	const imageData = data.find((item) => item['@type'] === 'ImageObject');

	release.entryId = new URL(url).pathname.match(/\/videos\/([\w-]+)/)[1];

	release.title = query.cnt('.video .title h1')
		|| data.find((item) => item['@type'] === 'BreadcrumbList')?.itemListElement.slice(-1)[0].item.name
		|| pageData?.name.slice(0, pageData.name.lastIndexOf('-')).trim();

	release.description = query.cnt('.video .descript');

	release.date = pageData.datePublished && new Date(pageData.datePublished);

	release.actors = query.all('.video .elenco a').map((el) => {
		const actorUrl = query.url(el, null);

		return {
			name: query.cnt(el),
			url: actorUrl,
			gender: genderFromUrl(actorUrl),
		};
	});

	release.poster = imageData?.url
		|| query.meta('property="og:image"')
		|| html.match(/poster: '(http.*\.jpg)'/)?.[1];

	release.photos = query.imgs('.listPostSm a', 'href');
	release.trailer = query.video('source', 'src', { origin: channel.url });

	release.likes = query.number('.vortex-p-like-counter');
	release.dislikes = query.number('.vortex-p-dislike-counter');

	if (!release.date && release.poster) {
		const match = release.poster.match(/\/uploads\/(\d{4})\/(\d{2})/);

		if (match) {
			release.date = new Date(match[1], match[2] - 1, 1);
			release.datePrecision = 'month';
		}
	}

	return release;
}

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

	profile.gender = genderFromUrl(url);

	profile.description = query.cnt('.about')?.replace(/sobre a atriz:/i, '').trim();
	profile.avatar = query.img('.left .thumb img');

	profile.scenes = scrapeAll(qu.initAll(el, '.listPostLg .post'));

	return profile;
}

async function fetchLatest(channel, page = 1) {
	const url = `${channel.url}/videos/page/${page}`;
	const res = await qu.getAll(url, '.listPostLg .post');

	if (res.ok) {
		return scrapeAll(res.items, channel);
	}

	return res.status;
}

async function fetchProfilePage({ name, gender }, entity, secondAttempt) {
	const url = `${entity.url}/${gender === 'male' || secondAttempt ? 'atores' : 'atrizes'}/${slugify(name, '-')}`;
	const res = await qu.get(url);

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

	if (secondAttempt) {
		return res.status;
	}

	return fetchProfilePage({ name, gender }, entity, true);
}

async function fetchProfile(baseActor, entity, options) {
	const { res, url } = await fetchProfilePage(baseActor, entity, false);

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

	return res.status;
}

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