Added deciated ExploitedX scraper.

src/scrapers/exploitedx.js

@@ -0,0 +1,131 @@
+'use strict';
+
+const unprint = require('unprint');
+
+const slugify = require('../utils/slugify');
+const { convert } = require('../utils/convert');
+
+function scrapeAll(scenes) {
+	return scenes.map(({ query }) => {
+		const release = {};
+
+		release.url = query.url('.img-div a[href*="/trailers"], .content-div h4 a[href*="/trailers"]'); // empty anchor in markup for some reason
+		release.entryId = new URL(release.url).pathname.match(/\/trailers\/(.*)\.html/)[1].toLowerCase();
+
+		release.title = query.content('.content-div h4 a[href]');
+
+		release.date = query.date('.more-info-div', 'MMM DD, YYYY');
+		release.duration = query.duration('.more-info-div');
+
+		release.photoCount = query.number('.more-info-div', { match: /(\d+) photos/i, matchIndex: 1 })
+			|| query.number('//i[contains(@class, "fa-camera")]//following-sibling::text()[1]');
+
+		const poster = query.img('.video_placeholder') || query.poster();
+
+		if (poster) {
+			release.poster = [
+				poster.replace('-1x', '-2x'),
+				poster.replace('-1x', '-3x'),
+				poster,
+				poster.replace('-1x', '-4x'), // too big, only use as fallback
+			];
+		}
+
+		release.teaser = query.video();
+
+		return release;
+	});
+}
+
+function scrapeScene({ query }, { url }) {
+	const release = {};
+
+	release.entryId = new URL(url).pathname.match(/\/trailers\/(.*)\.html/)[1].toLowerCase();
+
+	// ExGoGiGirls deviates most from the other sites
+	release.title = query.content('.video-player .section-title, #scene-info h1') || query.content('.bio-article .section-title'); // model-name class not on all sites
+	release.description = (query.content('.descriptionFull') || query.content('.description'))?.replace(/(read more)|(read less)/i, '').trim(); // querying text nodes breaks a lot of descriptions
+
+	release.date = query.date('//*[strong[contains(text(), "Released")]]', 'MMMM D, YYYY');
+	release.duration = query.duration('//*[strong[contains(text(), "Runtime")]]');
+	release.photoCount = query.number('//*[strong[contains(text(), "Runtime")]]', { match: /(\d+) photos/i, matchIndex: 1 });
+
+	release.actors = query.all('.models-list-thumbs li, [id="model bio"] .card').map((actorEl) => { // not all actors have links
+		const actorUrl = unprint.query.url(actorEl);
+
+		return {
+			name: unprint.query.content(actorEl, 'span, .model-name'),
+			url: actorUrl,
+			entryId: actorUrl && new URL(actorUrl).pathname.match(/\/models\/(.*)\.html/)?.[1].toLowerCase(),
+			avatar: [
+				unprint.query.img(actorEl, 'img', { attribute: 'src0_2x' }),
+				unprint.query.img(actorEl, 'img', { attribute: 'src0_1x' }),
+				unprint.query.img(actorEl, 'img', { attribute: 'src0_3x' }), // too big
+			],
+		};
+	});
+
+	release.tags = query.contents('.tags a[href]');
+
+	release.poster = query.img('.update_thumb', { attribute: 'src0_1x' });
+
+	return release;
+}
+
+function scrapeProfile({ query }, _entity) {
+	const profile = {};
+
+	const bio = Object.fromEntries(query.all('.detail-div p').map((detailEl) => [
+		slugify(unprint.query.content(detailEl, 'strong'), '_'),
+		unprint.query.text(detailEl),
+	]));
+
+	profile.age = Number(bio.age) || null;
+	profile.height = convert(bio.height, 'cm');
+	profile.measurements = bio.measurements;
+
+	profile.description = [
+		bio.favorite_position && `Favorite position: ${bio.favorite_position}`,
+		bio.likes && `Likes: ${bio.likes}`,
+	].filter(Boolean).join('\n');
+
+	profile.avatar = [
+		query.img('.model_bio_thumb', { attribute: 'src0_2x' }),
+		query.img('.model_bio_thumb', { attribute: 'src0_1x' }),
+		query.img('.model_bio_thumb', { attribute: 'src0_3x' }), // too big
+	];
+
+	return profile;
+}
+
+async function fetchLatest(channel, page = 1) {
+	const url = `${channel.url}/categories/movies_${page}_d.html`;
+	const res = await unprint.get(url, { selectAll: '.main-article .item-update' });
+
+	if (res.ok) {
+		return scrapeAll(res.context, channel);
+	}
+
+	return res.status;
+}
+
+async function fetchProfile({ url }, entity) {
+	if (!url) {
+		// ExploitedX has loads of performers with the same name, don't search for the name, only use known URLs
+		return null;
+	}
+
+	const res = await unprint.get(url);
+
+	if (res.ok) {
+		return scrapeProfile(res.context, entity);
+	}
+
+	return res.status;
+}
+
+module.exports = {
+	fetchLatest,
+	fetchProfile,
+	scrapeScene,
+};