Fixed Nubiles base poster query, handling trailing commas in qu source set. Added profile scene scraper to Dogfart. Added tag photo.

src/scrapers/dogfart.js

@@ -6,6 +6,8 @@ const { JSDOM } = require('jsdom');
 const moment = require('moment');
 
 const http = require('../utils/http');
+const slugify = require('../utils/slugify');
+const qu = require('../utils/qu');
 
 async function getPhotos(albumUrl) {
 	const res = await http.get(albumUrl);
@@ -20,51 +22,51 @@ async function getPhotos(albumUrl) {
 
 		return {
 			url: pageUrl,
-			extract: ({ qu }) => qu.q('.scenes-module img', 'src'),
+			extract: ({ query }) => query.img('.scenes-module img'),
 		};
 	});
 
 	return photoUrls;
 }
 
-function scrapeLatest(html, site) {
+function scrapeLatest(html, site, filter = true) {
 	const { document } = new JSDOM(html).window;
 	const sceneElements = Array.from(document.querySelectorAll('.recent-updates'));
 
-	return sceneElements.reduce((acc, element) => {
-		const siteUrl = element.querySelector('.help-block').textContent;
+	return sceneElements.map((element) => {
+		const siteUrl = element.querySelector('.recent-details-title .help-block, .model-details-title .site-name').textContent;
 
-		if (`www.${siteUrl.toLowerCase()}` !== new URL(site.url).host) {
+		if (filter && `www.${siteUrl.toLowerCase()}` !== new URL(site.url).host) {
 			// different dogfart site
-			return acc;
+			return null;
 		}
 
 		const sceneLinkElement = element.querySelector('.thumbnail');
-		const url = `https://dogfartnetwork.com${sceneLinkElement.href}`;
+		const url = qu.prefixUrl(sceneLinkElement.href, 'https://dogfartnetwork.com');
 		const { pathname } = new URL(url);
 		const entryId = `${site.slug}_${pathname.split('/')[4]}`;
 
 		const title = element.querySelector('.scene-title').textContent;
-		const actors = title.split(/[,&]|\band\b/).map(actor => actor.trim());
+		const actors = title.split(/[,&]|\band\b/).map(actor => actor.replace(/BTS/i, '').trim());
 
 		const poster = `https:${element.querySelector('img').src}`;
 		const teaser = sceneLinkElement.dataset.preview_clip_url;
 
-		return [
-			...acc,
-			{
-				url,
-				entryId,
-				title,
-				actors,
-				poster,
-				teaser: {
-					src: teaser,
-				},
-				site,
+		const channel = siteUrl?.match(/(.*).com/)?.[1].toLowerCase();
+
+		return {
+			url,
+			entryId,
+			title,
+			actors,
+			poster,
+			teaser: {
+				src: teaser,
 			},
-		];
-	}, []);
+			site,
+			channel,
+		};
+	}).filter(Boolean);
 }
 
 async function scrapeScene(html, url, site) {
@@ -97,8 +99,8 @@ async function scrapeScene(html, url, site) {
 	const poster = `https:${trailerElement.dataset.poster}`;
 	const { trailer } = trailerElement.dataset;
 
-	const lastPhotosUrl = Array.from(document.querySelectorAll('.pagination a')).slice(-1)[0].href;
-	const photos = await getPhotos(`${origin}${pathname}${lastPhotosUrl}`, site, url);
+	const lastPhotosUrl = Array.from(document.querySelectorAll('.pagination a')).slice(-1)[0]?.href;
+	const photos = lastPhotosUrl ? await getPhotos(`${origin}${pathname}${lastPhotosUrl}`, site, url) : [];
 
 	const stars = Math.floor(Number(document.querySelector('span[itemprop="average"]')?.textContent || document.querySelector('span[itemprop="ratingValue"]')?.textContent) / 2);
 	const tags = Array.from(document.querySelectorAll('.scene-details .categories a')).map(({ textContent }) => textContent);
@@ -137,7 +139,23 @@ async function fetchScene(url, site) {
 	return scrapeScene(res.body.toString(), url, site);
 }
 
+async function fetchProfile(baseActor, entity) {
+	const slug = slugify(baseActor.name, '+');
+	const url = `https://www.dogfartnetwork.com/tour/girls/${slug}/`;
+
+	const res = await http.get(url);
+
+	if (res.ok) {
+		const scenes = scrapeLatest(res.body, entity, false);
+
+		return { scenes };
+	}
+
+	return res.status;
+}
+
 module.exports = {
 	fetchLatest,
 	fetchScene,
+	fetchProfile,
 };

src/scrapers/nubiles.js

@@ -45,8 +45,9 @@ function scrapeAll(scenes, site, origin) {
 		release.date = qu.date('.date', 'MMM D, YYYY');
 		release.actors = qu.all('.models a.model', true);
 
-		const poster = qu.q('img').dataset.original;
-		release.poster = [
+		const poster = qu.sourceSet('img', 'data-srcset')?.[0];
+
+		release.poster = poster && [
 			poster.replace('_640', '_1280'),
 			poster,
 		];

src/scrapers/scrapers.js

@@ -197,6 +197,7 @@ const scrapers = {
 		devilsfilm: famedigital,
 		digitalplayground,
 		dtfsluts: fullpornnetwork,
+		dogfartnetwork: dogfart,
 		dorcelclub: dorcel,
 		doubleviewcasting: firstanalquest,
 		elegantangel,

src/utils/qu.js

@@ -253,7 +253,7 @@ function urls(context, selector = 'a', attr = 'href', { origin, protocol = 'http
 	return attr ? urlEls.map(urlEl => prefixUrl(urlEl, origin, protocol)) : urlEls;
 }
 
-function sourceSet(context, selector, attr, options = {}) {
+function sourceSet(context, selector, attr = 'srcset', options = {}) {
 	const srcset = q(context, selector, attr);
 
 	if (!srcset) {
@@ -265,11 +265,16 @@ function sourceSet(context, selector, attr, options = {}) {
 		.map((source) => {
 			const [link, descriptor] = source.split(' ');
 
-			return {
-				descriptor: descriptor || 'fallback',
-				url: prefixUrl(link, options.origin, options.protocol),
-			};
+			if (link) {
+				return {
+					descriptor: descriptor || 'fallback',
+					url: prefixUrl(link, options.origin, options.protocol),
+				};
+			}
+
+			return null;
 		})
+		.filter(Boolean)
 		.sort((sourceA, sourceB) => {
 			if (sourceB.descriptor === 'fallback' || parseInt(sourceA.descriptor, 10) > parseInt(sourceB.descriptor, 10)) {
 				return -1;