traxxx/src/scrapers/bang.js

'use strict';

const unprint = require('unprint');

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

/*
function encodeId(id) {
	if (!id) {
		return id;
	}

	return Buffer
		.from(id, 'hex')
		.toString('base64')
		.replace(/\+/g, '-')
		.replace(/\//g, '_')
		.replace(/=/g, ',');
}
*/

function decodeId(id) {
	if (!id) {
		return id;
	}

	const restoredId = id
		.replace(/-/g, '+')
		.replace(/_/g, '/')
		.replace(/,/g, '=');

	return Buffer
		.from(restoredId, 'base64')
		.toString('hex');
}

function getAvatarFallback(url) {
	try {
		const { origin, pathname } = new URL(url);

		return [
			`${origin}${pathname}`,
			url,
		];
	} catch (error) {
		return null;
	}
}

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

		release.url = query.url('a', { origin: entity.url });
		release.entryId = query.dataset('a', 'videopreview-id-value') || decodeId(new URL(release.url).pathname.match(/\/video\/([\w-]+)\//)?.[1]);

		release.title = query.content('a > span.block');
		release.date = query.date('a + div', 'MMM DD, YYYY');

		release.duration = query.duration('[data-videopreview-target="duration"]', { attribute: 'data-content' });

		release.actors = query.elements('a + div a[href*="/pornstar"]').map((el) => ({
			name: unprint.query.content(el),
			url: unprint.query.url(el, null, { origin: 'https://www.bang.com' }),
		}));

		const poster = query.img('img[data-videopreview-target="image"]');
		const posterUrl = new URL(poster);

		if (poster) {
			release.poster = [
				`${posterUrl.origin}${posterUrl.pathname}`,
				posterUrl.href,
			];
		}

		const videoData = query.json('a', { attribute: 'data-videopreview-sources-value' });

		if (videoData) {
			release.teaser = [
				videoData.mp4_large,
				videoData.webm_large,
				videoData.mp4,
				videoData.webm,
			];
		}

		return release;
	});
}

async function scrapeScene({ query }, { url, entity }) {
	const release = {};
	const data = query.json('//script[contains(text(), "VideoObject")]');

	release.entryId = data?.['@id'] || decodeId(new URL(url).pathname.match(/\/video\/([\w-]+)\//)?.[1]);

	// data title is not capitalized, prefer markup
	release.title = query.attribute('meta[property="og:title"]', 'content') || query.content('.video-container + div h1') || data?.name;
	release.description = data?.description || query.attribute('meta[property="og:description"]', 'content') || query.content('//div[contains(@class, "actions")]/preceding-sibling::p');

	release.date = unprint.extractDate(data?.datePublished, 'YYYY-MM-DD') || query.date('//p[contains(text(), "Date:")]', 'MMM DD, YYYY');
	release.duration = unprint.extractTimestamp(data?.duration) || query.duration('//p[contains(text(), "Playtime:")]//span');

	if (data?.actor) {
		release.actors = data.actor.map((actor) => ({
			name: actor.name,
			url: actor.url,
			avatar: getAvatarFallback(query.img(`a[href*="/pornstar"] img[alt="${actor.name}"]`)),
		}));
	} else {
		release.actors = query.elements('//div[contains(@class, "video-actors")]//a[img|picture]').map((element) => ({
			name: unprint.query.attribute(element, 'img', 'alt'),
			url: unprint.query.url(element, null, { origin: entity.url }),
			avatar: getAvatarFallback(unprint.query.img(element, 'img')),
		}));
	}

	release.tags = query.contents('.actions .genres');

	const sourcesData = query.json('.video-container [data-videopreview-sources-value]', { attribute: 'data-videopreview-sources-value' });

	release.poster = data?.thumbnailUrl || query.attribute('meta[property="og:image"]', 'content');
	release.teaser = (sourcesData && [
			sourcesData.mp4_large,
			sourcesData.webm_large,
			sourcesData.mp4,
			sourcesData.webm,
		])
		|| data?.contentUrl
		|| query.attribute('meta[property="og:video"]')
		|| query.video('video[data-videocontainer-target] source');

	release.photos = query.sourceSets('.photo-set img');
	release.photoCount = query.number('//h2[contains(text(), "Photos")]/following-sibling::span');

	const channelName = query.content('.video-container + div a[href*="?in="]')?.trim();

	if (channelName) {
		release.channel = entity.children?.find((channel) => new RegExp(channel.name, 'i').test(channelName) || slugify(channelName) === channel.slug)?.slug;
	}

	return release;
}

async function fetchActorScenes(element, url, entity, page = 1, acc = []) {
	const scenes = scrapeAll(unprint.initAll(element, '.video_container'), entity);

	if (scenes.length) {
		const nextPageRes = await unprint.post(url, { page: page + 1 });

		if (nextPageRes.ok) {
			return fetchActorScenes(nextPageRes.context.element, url, entity, page + 1, acc.concat(scenes));
		}
	}

	return acc.concat(scenes);
}

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

	profile.dateOfBirth = query.date('//text()[contains(., "Born")]/following-sibling::span[contains(@class, "font-bold")][1]', 'MMMM D, YYYY');
	profile.birthPlace = query.content('//text()[contains(., "From")]/following-sibling::span[contains(@class, "font-bold")][1]');

	profile.ethnicity = query.content('//text()[contains(., "Ethnicity")]/following-sibling::span[contains(@class, "font-bold")][1]');

	profile.hairColor = query.content('//text()[contains(., "Hair Color")]/following-sibling::span[contains(@class, "font-bold")][1]');
	profile.eyes = query.content('//text()[contains(., "Eye Color")]/following-sibling::span[contains(@class, "font-bold")][1]');

	profile.avatar = getAvatarFallback(query.img('img[alt*="profile"][src*="https://i.bang.com/pornstars/"]'));

	if (include.scenes) {
		profile.scenes = await fetchActorScenes(element, url, entity);
	}

	return profile;
}

async function fetchLatest(channel, page = 1) {
	const url = `${channel.url}&by=date.desc&page=${page}`;
	const res = await unprint.get(url, { selectAll: '.video_container' });

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

	return res.status;
}
async function fetchUpcoming(channel) {
	const url = `${channel.url}&by=date.desc&early-access=true`;
	const res = await unprint.get(url, { selectAll: '.video_container' });

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

	return res.status;
}

async function fetchProfile({ name: actorName }, { entity }, include) {
	const searchRes = await unprint.get(`https://www.bang.com/pornstars?term=${slugify(actorName, '+')}`);

	if (!searchRes.ok) {
		return searchRes.status;
	}

	const url = searchRes.context.query.url(`//a[contains(.//span, "${actorName}")]`);

	if (!url) {
		return null;
	}

	const actorRes = await unprint.get(url);

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

	return actorRes.status;
}

module.exports = {
	fetchLatest,
	fetchUpcoming,
	fetchProfile,
	scrapeScene,
	useUnprint: true,
};