traxxx/src/scrapers/killergram.js

'use strict';

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

function scrapeAll({ query }) {
	const urls = query.urls('td > a:not([href*=joinnow])').map((pathname) => `http://killergram.com/${encodeURI(pathname)}`);
	const posters = query.imgs('td > a img');
	const titles = query.all('.episodeheadertext', true);
	const actors = query.all('.episodetextinfo:nth-child(3)').map((el) => query.all(el, 'a', true));
	const channels = query.all('.episodetextinfo:nth-child(2) a', true).map((channel) => slugify(channel, ''));

	if ([urls.length, posters.length, titles.length, actors.length, channels.length].every((value, index, array) => value === array[0])) { // make sure every set has the same number of items
		const releases = urls.map((url, index) => ({
			url,
			entryId: new URL(url).searchParams.get('id'),
			title: titles[index],
			actors: actors[index],
			channel: channels[index],
			poster: posters[index],
		}));

		return releases;
	}

	return [];
}

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

	release.entryId = new URL(url).searchParams.get('id');
	release.date = query.date('.episodetext', 'DD MMMM YYYY', /\d{2} \w+ \d{4}/);

	release.description = query.q('.episodetext tr:nth-child(5) td:nth-child(2)', true);
	release.actors = query.all('.modelstarring a', true);

	const duration = html.match(/(\d+) minutes/)?.[1];
	const channelUrl = query.url('a[href*="ct=site"]');

	if (duration) release.duration = Number(duration) * 60;

	if (channelUrl) {
		const siteName = new URL(`https://killergram.com/${channelUrl}`).searchParams.get('site');
		release.channel = slugify(siteName, '');
	}

	[release.poster, ...release.photos] = query.imgs('img[src*="/models"]');

	return release;
}

async function fetchActorReleases({ query }, url, remainingPages, actorName, accReleases = []) {
	const releases = scrapeAll({ query }).filter((release) => release.actors.includes(actorName));

	if (remainingPages.length > 0) {
		const { origin, pathname, searchParams } = new URL(url);
		searchParams.set('p', remainingPages[0]);

		const nextPage = `${origin}${pathname}?${searchParams}`;
		const res = await qu.get(nextPage, '#episodes > table');

		if (res.ok) {
			return fetchActorReleases(res.item, url, remainingPages.slice(1), actorName, accReleases.concat(releases));
		}
	}

	return accReleases.concat(releases);
}

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

	profile.avatar = {
		src: `http://thumbs.killergram.com/models/${encodeURI(actorName)}/modelprofilethumb.jpg`,
		process: {
			crop: {
				top: 4,
				left: 4,
				width: 289,
				height: 125,
			},
		},
	};

	if (include.releases) {
		const availablePages = query.all('.pageboxdropdown option', 'value');
		profile.releases = await fetchActorReleases(qu.init(query.q('#episodes > table')), url, availablePages.slice(1), actorName);
	}

	return profile;
}

async function fetchLatest(channel, page = 1) {
	const res = await qu.get(`${channel.url}&p=${((page - 1) * 15) + 1}`, '#episodes > table');

	return res.ok ? scrapeAll(res.item, channel) : res.status;
}

async function fetchScene(url, channel) {
	const res = await qu.get(url, '#episodes > table');

	return res.ok ? scrapeScene(res.item, url, channel) : res.status;
}

async function fetchProfile({ name: actorName }, entity, include) {
	const url = `http://killergram.com/episodes.asp?page=episodes&model=${encodeURI(actorName)}&ct=model`;
	const res = await qu.get(url, '#content', null, {
		followRedirects: false,
	});

	return res.ok ? scrapeProfile(res.item, actorName, url, include) : res.status;
}

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