Refactored New Sensations scraper.

package-lock.json

@@ -78,7 +78,7 @@
                 "tunnel": "0.0.6",
                 "ua-parser-js": "^1.0.32",
                 "undici": "^4.13.0",
-                "unprint": "^0.8.2",
+                "unprint": "^0.9.1",
                 "url-pattern": "^1.0.3",
                 "v-tooltip": "^2.0.3",
                 "video.js": "^7.11.4",
@@ -17004,9 +17004,9 @@
             }
         },
         "node_modules/unprint": {
-            "version": "0.8.2",
-            "resolved": "https://registry.npmjs.org/unprint/-/unprint-0.8.2.tgz",
-            "integrity": "sha512-mCKPDPwtuECbXJJLQbDn2FFbydr6fLKytyS3pymbxcTh2dkk7NFypMjR7qjU2Uv9Fl91hSE48SjYMsWHNKpp4w==",
+            "version": "0.9.1",
+            "resolved": "https://registry.npmjs.org/unprint/-/unprint-0.9.1.tgz",
+            "integrity": "sha512-TEdPfly6qOST3Vessa9gNFFkJsSsdWe04k0FCU5XuvdpCSb8eVRrAvLouuyJI/GkIhrn6ZHc9VgX/gRW/R5UcQ==",
             "dependencies": {
                 "axios": "^0.27.2",
                 "bottleneck": "^2.19.5",
@@ -31449,9 +31449,9 @@
             "integrity": "sha1-sr9O6FFKrmFltIF4KdIbLvSZBOw="
         },
         "unprint": {
-            "version": "0.8.2",
-            "resolved": "https://registry.npmjs.org/unprint/-/unprint-0.8.2.tgz",
-            "integrity": "sha512-mCKPDPwtuECbXJJLQbDn2FFbydr6fLKytyS3pymbxcTh2dkk7NFypMjR7qjU2Uv9Fl91hSE48SjYMsWHNKpp4w==",
+            "version": "0.9.1",
+            "resolved": "https://registry.npmjs.org/unprint/-/unprint-0.9.1.tgz",
+            "integrity": "sha512-TEdPfly6qOST3Vessa9gNFFkJsSsdWe04k0FCU5XuvdpCSb8eVRrAvLouuyJI/GkIhrn6ZHc9VgX/gRW/R5UcQ==",
             "requires": {
                 "axios": "^0.27.2",
                 "bottleneck": "^2.19.5",

package.json

@@ -137,7 +137,7 @@
         "tunnel": "0.0.6",
         "ua-parser-js": "^1.0.32",
         "undici": "^4.13.0",
-        "unprint": "^0.8.2",
+        "unprint": "^0.9.1",
         "url-pattern": "^1.0.3",
         "v-tooltip": "^2.0.3",
         "video.js": "^7.11.4",

seeds/02_sites.js

@@ -6856,16 +6856,9 @@ const sites = [
 		parent: 'newsensations',
 		parameters: {
 			siteId: 'hwxxx',
-			block: true,
+			layout: 'block',
 		},
 	},
-	{
-		slug: 'tabutales',
-		name: 'Tabu Tales',
-		url: 'https://www.thetabutales.com',
-		parent: 'newsensations',
-		parameters: { siteId: 'tt' },
-	},
 	{
 		slug: 'nsfamilyxxx',
 		name: 'Family XXX',
@@ -6874,7 +6867,7 @@ const sites = [
 		tags: ['family'],
 		parameters: {
 			siteId: 'famxxx',
-			block: true,
+			layout: 'block',
 		},
 	},
 	{
@@ -6883,7 +6876,10 @@ const sites = [
 		url: 'https://www.thelesbianexperience.com',
 		parent: 'newsensations',
 		tags: ['lesbian'],
-		parameters: { siteId: 'tle' },
+		parameters: {
+			siteId: 'tle',
+			layout: 'block',
+		},
 	},
 	{
 		slug: 'theromanceseries',
@@ -6892,13 +6888,6 @@ const sites = [
 		parent: 'newsensations',
 		parameters: { siteId: 'rs' },
 	},
-	{
-		slug: 'talesfromtheedge',
-		name: 'Tales From The Edge',
-		url: 'thetalesfromtheedge',
-		parent: 'newsensations',
-		parameters: { siteId: 'ttfte' },
-	},
 	{
 		slug: 'parodypass',
 		name: 'Parody Pass',
@@ -6907,11 +6896,15 @@ const sites = [
 		parameters: { siteId: 'pp' },
 	},
 	{
-		slug: 'shanedieselsbangingbabes',
-		name: 'Shane Diesel\'s Banging Babes',
-		url: 'http://shanedieselsbangingbabes.com',
+		slug: 'shanedieselxxx',
+		name: 'Shane Diesel XXX',
+		alias: ['shane diesel\'s banging babes', 'sdbb'],
+		url: 'https://shanedieselxxx.com',
 		parent: 'newsensations',
-		parameters: { siteId: 'sdbb' },
+		parameters: {
+			siteId: 'sdxxx',
+			layout: 'block',
+		},
 	},
 	{
 		slug: 'unlimitedmilfs',
@@ -6961,7 +6954,25 @@ const sites = [
 		name: 'Fresh Outta High School',
 		url: 'https://www.freshouttahighschool.com',
 		parent: 'newsensations',
-		parameters: { siteId: 'fohs' },
+		parameters: {
+			siteId: 'fohs',
+			layout: 'block',
+		},
+	},
+	// merged with Family XXX or main site
+	{
+		slug: 'tabutales',
+		name: 'Tabu Tales',
+		url: 'https://www.thetabutales.com',
+		parent: 'newsensations',
+		parameters: { siteId: 'tt' },
+	},
+	{
+		slug: 'talesfromtheedge',
+		name: 'Tales From The Edge',
+		url: 'https://www.thetalesfromtheedge.com',
+		parent: 'newsensations',
+		parameters: { siteId: 'ttfte' },
 	},
 	// NUBILES
 	{

src/deep.js

@@ -113,9 +113,6 @@ function fetchMovie(scraper, url, entity, baseRelease, options) {
 async function scrapeRelease(baseRelease, entitiesByHostname, type = 'scene') {
 	const entity = baseRelease.entity || entitiesByHostname[urlToHostname(baseRelease.url)];
 
-	console.log(entitiesByHostname);
-	console.log(entity);
-
 	if (!entity) {
 		logger.warn(`No entity available for ${baseRelease.url}`);
 		return baseRelease;

src/entities.js

@@ -103,7 +103,7 @@ function urlToHostname(url) {
 	try {
 		const hostname = new URL(url)
 			.hostname
-			.match(/(www\.)(.*)/)?.at(-1);
+			.match(/(www\.)?(.*)/)?.at(-1);
 
 		return hostname;
 	} catch (error) {

src/scrapers/newsensations.js

@@ -1,90 +1,165 @@
 'use strict';
 
-const { geta, ed } = require('../utils/q');
+const unprint = require('unprint');
+const slugify = require('../utils/slugify');
 
-function scrapeBlockLatest(scenes) {
-	return scenes.map(({ html, qu }) => {
+function scrapeLatestBlock(scenes) {
+	return scenes.map(({ html, query }) => {
 		const release = {};
 
-		const entryId = qu.q('div[class*="videothumb"]', 'class').match(/videothumb_(\d+)/)
-            || qu.q('div[id*="videothumb"]', 'id').match(/videothumb_(\d+)/);
+		release.title = query.content('h4 a');
+		release.url = query.url('h4 a');
+		release.date = unprint.extractDate(html, 'MM/DD/YYYY', { match: /\d{2}\/\d{2}\/\d{4}/ });
 
-		release.entryId = entryId[1];
+		release.actors = query.contents('.tour_update_models a');
 
-		release.title = qu.q('h4 a', true);
-		release.url = qu.url('h4 a');
-		release.date = ed(html, 'MM/DD/YYYY', /\d{2}\/\d{2}\/\d{4}/);
+		// native videothumb entry ID does not occur on scene page, date is not available on all sites
+		release.entryId = slugify([...release.actors.sort(), release.title]);
 
-		release.actors = qu.all('.tour_update_models a', true);
-
-		release.poster = qu.q('div img').dataset.src;
-		release.photos = [qu.q('div img', 'src0_4x') || qu.q('div img', 'src0_3x') || qu.q('div img', 'src0_2x')];
-
-		release.teaser = qu.video();
-
-		console.log(release);
+		release.poster = query.dataset('.video_placeholder', 'src');
+		release.teaser = query.video();
 
 		return release;
 	});
 }
 
-function scrapeClassicLatest(scenes) {
-	return scenes.map(({ el, qu }) => {
+function scrapeLatestClassic(scenes) {
+	return scenes.map(({ query }) => {
 		const release = {};
 
-		release.entryId = el.dataset.setid;
-		release.url = qu.url('a');
+		release.url = query.url('a');
 
-		release.title = qu.q('.update_title_small', true) || qu.q('a:nth-child(2)', true);
+		release.title = query.content('.update_title_small') || query.content('a:nth-child(2)');
+		release.description = query.attribute('a', 'title');
 
-		const description = qu.q('a', 'title');
-		if (description) release.description = description;
+		release.date = query.date('.date_small, .update_date', 'MM/DD/YYYY');
 
-		const date = qu.date('.date_small, .update_date', 'MM/DD/YYYY');
-		if (date) release.date = date;
+		release.duration = query.number('.update_counts') * 60;
 
-		const durationLine = qu.q('.update_counts', true);
-		if (durationLine) release.duration = Number(durationLine.match(/(\d+) min/i)[1]) * 60;
+		const actors = query.contents('.update_models a');
 
-		const actors = qu.all('.update_models a', true);
-		release.actors = actors.length > 0 ? actors : qu.q('.update_models', true).split(/,\s*/);
+		release.actors = actors.length === 0
+			? query.content('.update_models').split(/,\s*/)
+			: actors;
+
+		// native videothumb entry ID does not occur on scene page, date is not available on all sites
+		release.entryId = slugify([...release.actors.sort(), release.title]);
+
+		const photoCount = query.number('.update_thumb', { attribute: 'cnt' });
 
-		const photoCount = qu.q('.update_thumb', 'cnt');
 		[release.poster, ...release.photos] = Array.from({ length: photoCount })
-			.map((value, index) => qu.q('.update_thumb', `src${index}_3x`)
-                || qu.q('.update_thumb', `src${index}_2x`)
-                || qu.q('.update_thumb', `src${index}_1x`));
+			.map((value, index) => query.attribute('.update_thumb', `src${index}_3x`)
+                || query.attribute('.update_thumb', `src${index}_2x`)
+                || query.attribute('.update_thumb', `src${index}_1x`));
 
 		return release;
 	});
 }
 
-function scrapeScene({ query }) {
+function scrapeSceneBlock({ query }) {
 	const release = {};
 
 	release.title = query.content('.indScene h2');
+	release.description = query.content('.description');
+	release.date = query.date('.sceneDateP span', 'MM/DD/YYYY');
+
+	release.actors = query.all('.sceneTextLink .tour_update_models a').map((actorEl) => ({
+		name: unprint.query.content(actorEl),
+		url: unprint.query.url(actorEl, null),
+	}));
+
+	release.duration = query.number('.sceneDateP', { match: /(\d+)\s+min/i, matchIndex: 1 }) * 60;
+	release.entryId = slugify([...release.actors.map((actor) => actor.name).sort(), release.title]);
+
+	release.stars = query.number('.sceneRating');
+
+	release.poster = query.img('#trailer_thumb img[src*=content]');
+	release.trailer = query.video('#trailerVideo source');
+
+	return release;
+}
+
+async function fetchPhotos(url) {
+	const res = await unprint.get(url);
+
+	if (res.ok) {
+		return res.context.query.imgs('.grid-gallery img');
+	}
+
+	return [];
+}
+
+async function scrapeSceneClassic({ query }, context, options) {
+	const release = {};
+
+	release.title = query.content('.update_title');
+	release.description = query.content('.update_description');
+	release.date = query.date('.update_date', 'MM/DD/YYYY');
+
+	release.actors = query.all('.update_models a').map((actorEl) => ({
+		name: unprint.query.content(actorEl),
+		url: unprint.query.url(actorEl, null),
+	}));
+
+	release.entryId = slugify([...release.actors.map((actor) => actor.name).sort(), release.title]);
+
+	release.tags = query.contents('.update_tags a');
+	release.stars = query.number('.gallery_info', { match: /average\s+rating:\s+(\d+\.\d+)/i, matchIndex: 1 });
+
+	release.poster = query.img('#vidplayer', { attribute: 'poster' });
+	release.trailer = query.video('#vidplayer source');
+
+	const gallery = query.url('//a[img[contains(@src, "gallery.gif")]]');
+
+	if (gallery && options.includePhotos) {
+		release.photos = await fetchPhotos(gallery);
+	}
 
-	console.log(release);
 	return release;
 }
 
 async function fetchLatest(site, page = 1) {
+	const url = `${site.url}/tour_${site.parameters.siteId}/categories/movies_${page}_d.html`;
+	const res = await unprint.get(url, { selectAll: '.movieBlock, .videoBlock, .update_details, .update_details' });
+
+	return res;
+}
+
+async function fetchLatestClassic(site, page) {
 	if (!site.parameters) {
 		return null;
 	}
 
-	const url = `${site.url}/tour_${site.parameters.siteId}/categories/movies_${page}_d.html`;
-	const res = await geta(url, '.updatesBlock .movieBlock, .updatesBlock .videoBlock, .latest_updates_block .update_details, .category_listing_block .update_details');
+	const res = await fetchLatest(site, page);
 
-	if (res.ok && site.parameters.block) {
-		return scrapeBlockLatest(res.items, site);
+	if (res.ok) {
+		return scrapeLatestClassic(res.context, site);
 	}
 
-	return res.ok ? scrapeClassicLatest(res.items, site) : res.status;
+	return res.status;
+}
+
+async function fetchLatestBlock(site, page) {
+	if (!site.parameters) {
+		return null;
+	}
+
+	const res = await fetchLatest(site, page);
+
+	if (res.ok) {
+		return scrapeLatestBlock(res.context, site);
+	}
+
+	return res.status;
 }
 
 module.exports = {
-	fetchLatest,
-	scrapeScene,
+	fetchLatest: fetchLatestClassic,
+	scrapeScene: scrapeSceneClassic,
 	useUnprint: true,
+	block: {
+		scrapeScene: scrapeSceneBlock,
+		fetchLatest: fetchLatestBlock,
+		useUnprint: true,
+	},
 };

src/store-releases.js

@@ -36,6 +36,7 @@ async function curateReleaseEntry(release, batchId, existingRelease, type = 'sce
 		url: release.url,
 		date: Number(release.date) ? release.date : null,
 		date_precision: release.datePrecision,
+		duration: Number(release.duration) || null,
 		slug,
 		description: release.description,
 		comment: release.comment,

src/utils/slugify.js

@@ -36,21 +36,24 @@ const substitutes = {
 	ỹ: 'y',
 };
 
-function slugify(string, delimiter = '-', {
+function slugify(strings, delimiter = '-', {
 	encode = false,
 	removeAccents = true,
 	removePunctuation = false,
 	limit = 1000,
 } = {}) {
-	if (!string || typeof string !== 'string') {
-		return string;
+	if (!strings || (typeof strings !== 'string' && !Array.isArray(strings))) {
+		return strings;
 	}
 
-	const slugComponents = string
+	const slugComponents = []
+		.concat(strings)
+		.filter(Boolean)
+		.flatMap((string) => string
 			.trim()
 			.toLowerCase()
 			.replace(removePunctuation && /[.,:;'"_-]/g, '')
-		.match(/[A-Za-zÀ-ÖØ-öø-ÿ0-9]+/g);
+			.match(/[A-Za-zÀ-ÖØ-öø-ÿ0-9]+/g));
 
 	if (!slugComponents) {
 		return '';