traxxx/src/scrapers/acam.js

'use strict';

const unprint = require('unprint');

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

function extractEntryId(poster) {
	try {
		return slugify(new URL(poster).pathname.match(/\/images\/(.*?)\.[a-z]{3,4}/i)?.[1]?.replace(/smak.*/i, ''), '');
	} catch (error) {
		return null;
	}
}

function extractTags(title, titleComment) {
	if (!title && !titleComment) {
		return [];
	}

	if (titleComment?.includes('<i>')) {
		const tagsMatch = titleComment.match(/<i>(.*?)<\/i>/)?.[1];

		if (tagsMatch) {
			return tagsMatch.split('-').map((tag) => tag.trim().toLowerCase());
		}
	}

	const firstTagIndex = title.match(/[A-Z]{2}/)?.index;

	if (firstTagIndex) {
		const tagSection = title
			.slice(firstTagIndex)
			.match(/([A-Z0-9\s]{2,})/g);

		if (tagSection) {
			return tagSection
				.map((tag) => tag.trim().toLowerCase())
				.filter(Boolean) || [];
		}
	}

	return [];
}

// derived photo is usually uncensored and preferred as poster, but not guaranteed to exist, so fall back to original image
function getPhotos(poster) {
	const photo = poster?.replace(/(s[ma]{2}kprov\d*)|([._]preview)/i, ''); // sic

	if (photo === poster) {
		return {
			poster,
			photos: [],
		};
	}

	return {
		poster: [photo, poster],
		photos: [poster],
	};
}

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

		// Vilde URLs are temporary tokens for some reason, seem to be handled entirely back-end
		const url = query.url('a[href*="/show-video"]');

		release.token = new URL(url).pathname.match(/\/show-video\/([a-z0-9]+)/)?.[1];
		release.forceDeep = true;

		release.title = query.content('a h5, .product-content p, .video_text');
		release.tags = extractTags(release.title, query.content('//a/comment()'));

		const { poster, photos } = getPhotos(query.img('img[src*="/videos/images"], img[src*="/uploads/images"]'));

		release.poster = poster;
		release.photos = photos;

		if (parameters.staticUrl) {
			release.url = url;
			release.entryId = release.token;
		} else {
			release.entryId = extractEntryId(release.poster);
		}

		return release;
	});
}

async function setLanguage(parameters) {
	if (parameters.languageUrl) {
		const langRes = await unprint.post(parameters.languageUrl, {
			[parameters.languageKey || 'select_language']: parameters.language || 'english',
		}, {
			form: true,
		});

		return langRes.cookies;
	}

	return null;
}

async function fetchLatest(channel, page = 1, { parameters }) {
	const cookies = await setLanguage(parameters);

	const res = await unprint.post(`${channel.origin}/pagination`, {
		i: page,
		status: true,
	}, {
		selectAll: '.movi-area',
		form: true,
		cookies,
	});

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

	return res.status;
}

async function fetchLatestHooked(channel, page = 1, { parameters }) {
	const cookies = await setLanguage(parameters);

	const res = await unprint.get(`${channel.origin}/Welcome/index/${(page - 1) * 9}`, {
		selectAll: '.product-main',
		cookies,
	});

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

	return res.status;
}

async function fetchLatestKanal(channel, page = 1, { parameters }) {
	const cookies = await setLanguage(parameters);

	const res = await unprint.post(`${channel.origin}/pagination`, {
		k: page,
		hidden_page_no: page - 1,
		status: true,
	}, {
		selectAll: '.video_bx',
		form: true,
		cookies,
	});

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

	return res.status;
}

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

	// URL is temporary token
	if (!query.exists('.login-sec.for-browser, .video-description, .video_co_title')) {
		// URL likely expired, still returns 200
		return null;
	}

	if (query.exists('.video-description')) {
		const descriptions = query.contents('.video-description p').filter(Boolean);

		release.title = descriptions[0];
		release.description = descriptions.slice(1).join(' ') || null;
	} else {
		release.title = query.content('.login-sec.for-browser h3, .video_co_title h3');
		release.description = query.contents('.login-sec.for-browser h3 ~ *').join(' ') || null;
	}

	release.tags = extractTags(release.title);

	const { poster, photos } = getPhotos(query.poster('.play_video_cont video'));

	release.poster = poster;
	release.photos = photos;

	release.trailer = query.all('.play_video_cont source')
		.map((videoEl) => ({
			src: unprint.query.url(videoEl, null, { attribute: 'src' }),
			quality: unprint.query.number(videoEl, null, { attribute: 'size' }),
			referer: url,
		}))
		.toSorted((videoA, videoB) => videoB.quality - videoA.quality);

	if (parameters.staticUrl) {
		release.url = url;
		release.entryId = baseRelease?.token || new URL(url).pathname.match(/\/show-video\/([a-z0-9]+)/)?.[1];
	} else {
		release.entryId = extractEntryId(release.poster);
	}

	return release;
}

async function fetchScene(baseUrl, entity, baseRelease, { parameters }) {
	const url = baseUrl || (baseRelease?.token && `${entity.origin}/show-video/${baseRelease.token}`) || null;

	if (!url) {
		return null;
	}

	const cookies = await setLanguage(parameters);

	const res = await unprint.get(url, {
		headers: {
			'accept-language': 'en-US,en',
		},
		cookies,
	});

	if (res.ok || res.status === 500) { // Anal Hooked returns 500 for valid scene pages
		return scrapeScene(res.context, { url, baseRelease, parameters });
	}

	return res.status;
}

module.exports = {
	fetchLatest,
	fetchScene,
	hooked: {
		fetchLatest: fetchLatestHooked,
		fetchScene,
	},
	kanal: {
		fetchLatest: fetchLatestKanal,
		fetchScene,
	},
};