Added American Pornstar. Improved Jules Jordan scraper to accomodate for American Pornstar. Changed entity logo mogrify settings to ensure both minimum height and width.

src/scrapers/americanpornstar.js

@@ -0,0 +1,65 @@
+'use strict';
+
+const { fetchLatest, fetchProfile } = require('./julesjordan');
+
+const qu = require('../utils/q');
+const slugify = require('../utils/slugify');
+
+function scrapeScene({ query }, channel) {
+	const release = {};
+	const title = query.cnt('.update_title', false);
+
+	release.title = title.trim();
+	release.description = query.cnt('.latest_update_description');
+
+	release.date = query.date('.update_date', 'MM/DD/YYYY');
+	release.actors = query.all('.tour_update_models a').map(actorEl => ({
+		name: query.cnt(actorEl),
+		url: query.url(actorEl, null),
+	}));
+
+	release.entryId = slugify(release.title);
+
+	release.duration = Number(query.cnt('.update_counts_preview_table').match(/(\d+) min/)[1]) * 60;
+
+	const poster = query.img('.large_update_thumb', 'src', { origin: channel.url });
+	const trailer = query.q('.update_image a', 'onclick')?.match(/'(.+)'/)?.[1];
+
+	release.poster = [
+		poster.replace(/.jpg$/, '-full.jpg'),
+		poster,
+	];
+
+	release.photos = query.imgs('.small_update_thumb', 'src', { origin: channel.url }).map(img => [
+		img.replace(/.jpg$/, '-full.jpg'),
+		img,
+	]);
+
+	if (trailer) {
+		release.trailer = qu.prefixUrl(encodeURI(trailer), channel.url);
+	}
+
+	release.tags = query.cnts('.tour_update_tags a');
+
+	return release;
+}
+
+async function fetchLatestLocal(channel, page) {
+	return fetchLatest(channel, page, true);
+}
+
+async function fetchScene(url, channel) {
+	const res = await qu.get(url);
+
+	if (res.ok) {
+		return scrapeScene(res.item, channel);
+	}
+
+	return res.status;
+}
+
+module.exports = {
+	fetchLatest: fetchLatestLocal,
+	fetchScene,
+	fetchProfile, // don't scrape scenes, no URL
+};

src/scrapers/julesjordan.js

@@ -7,7 +7,7 @@ const cheerio = require('cheerio');
 const { JSDOM } = require('jsdom');
 const moment = require('moment');
 
-const { get, geta, ctxa, parseDate } = require('../utils/q');
+const { get, geta, ctxa, parseDate, prefixUrl } = require('../utils/q');
 const http = require('../utils/http');
 const { heightToCm } = require('../utils/convert');
 const slugify = require('../utils/slugify');
@@ -134,16 +134,16 @@ function getEntryId(html) {
 	return null;
 }
 
-function scrapeAll(scenes, site) {
+function scrapeAll(scenes, site, entryIdFromTitle) {
 	return scenes.map(({ el, qu }) => {
 		const release = {};
 
-		release.entryId = el.dataset.setid || qu.q('.rating_box')?.dataset.id;
-
 		release.url = qu.url('.update_title a, .dvd_info > a, a ~ a');
 		release.title = qu.q('.update_title a, .dvd_info > a, a ~ a', true);
 		release.date = qu.date('.update_date', 'MM/DD/YYYY');
 
+		release.entryId = (entryIdFromTitle && slugify(release.title)) || el.dataset.setid || qu.q('.rating_box')?.dataset.id;
+
 		release.actors = qu.all('.update_models a', true);
 
 		const dvdPhotos = qu.imgs('.dvd_preview_thumb');
@@ -153,11 +153,22 @@ function scrapeAll(scenes, site) {
 			? dvdPhotos
 			: Array.from({ length: photoCount }).map((value, index) => {
 				const src = qu.img('a img.thumbs', `src${index}_1x`) || qu.img('a img.thumbs', `src${index}`) || qu.img('a img.thumbs');
+				const prefixedSrc = prefixUrl(src, site.url);
 
-				return src ? {
-					src: /^http/.test(src) ? src : `${site.url}${src}`,
-					referer: site.url,
-				} : null;
+				if (src) {
+					return [
+						{
+							src: prefixedSrc.replace(/.jpg$/, '-full.jpg'),
+							referer: site.url,
+						},
+						{
+							src: prefixedSrc,
+							referer: site.url,
+						},
+					];
+				}
+
+				return null;
 			}).filter(Boolean);
 
 		const teaserScript = qu.html('script');
@@ -301,11 +312,11 @@ function scrapeMovie({ el, query }, url, site) {
 	};
 }
 
-function scrapeProfile(html, url, actorName) {
+function scrapeProfile(html, url, actorName, entity) {
 	const { document } = new JSDOM(html).window;
 
 	const bio = document.querySelector('.model_bio').textContent;
-	const avatarEl = document.querySelector('.model_bio_pic img');
+	const avatarEl = document.querySelector('.model_bio_pic img, .model_bio_thumb');
 
 	const profile = {
 		name: actorName,
@@ -336,7 +347,9 @@ function scrapeProfile(html, url, actorName) {
 			avatarEl.getAttribute('src0_1x'),
 			avatarEl.getAttribute('src0'),
 			avatarEl.getAttribute('src'),
-		].filter(Boolean);
+		]
+			.filter(avatar => avatar && !/p\d+.jpe?g/.test(avatar)) // remove non-existing attributes and placeholder images
+			.map(avatar => prefixUrl(avatar, entity.url));
 
 		if (avatarSources.length) profile.avatar = avatarSources;
 	}
@@ -346,7 +359,7 @@ function scrapeProfile(html, url, actorName) {
 	return profile;
 }
 
-async function fetchLatest(site, page = 1) {
+async function fetchLatest(site, page = 1, entryIdFromTitle = false) {
 	const url = site.parameters?.latest
 		? util.format(site.parameters.latest, page)
 		: `${site.url}/trial/categories/movies_${page}_d.html`;
@@ -354,7 +367,7 @@ async function fetchLatest(site, page = 1) {
 	// const res = await bhttp.get(url);
 	const res = await geta(url, '.update_details');
 
-	return res.ok ? scrapeAll(res.items, site) : res.status;
+	return res.ok ? scrapeAll(res.items, site, entryIdFromTitle) : res.status;
 }
 
 async function fetchUpcoming(site) {
@@ -382,30 +395,35 @@ async function fetchMovie(url, site) {
 	return res.ok ? scrapeMovie(res.item, url, site) : res.status;
 }
 
-async function fetchProfile({ name: actorName }) {
-	const actorSlugA = slugify(actorName, '-');
-	const actorSlugB = slugify(actorName, '');
+async function fetchProfile({ name: actorName, url }, entity) {
+	const actorSlugA = slugify(actorName, '');
+	const actorSlugB = slugify(actorName, '-');
 
-	const urlA = `https://julesjordan.com/trial/models/${actorSlugA}.html`;
-	const urlB = `https://julesjordan.com/trial/models/${actorSlugB}.html`;
+	const urls = [
+		url,
+		`${entity.parameters?.profile || `${entity.url}/trial/models`}/${actorSlugA}.html`,
+		`${entity.parameters?.profile || `${entity.url}/trial/models`}/${actorSlugB}.html`,
+	];
 
-	const resA = await bhttp.get(urlA);
+	return urls.reduce(async (chain, profileUrl) => {
+		const profile = await chain;
 
-	if (resA.statusCode === 200) {
-		const profile = scrapeProfile(resA.body.toString(), urlA, actorName);
+		if (profile) {
+			return profile;
+		}
 
-		return profile;
-	}
+		if (!profileUrl) {
+			return null;
+		}
 
-	const resB = await bhttp.get(urlB);
+		const res = await http.get(profileUrl);
 
-	if (resB.statusCode === 200) {
-		const profile = scrapeProfile(resB.body.toString(), urlB, actorName);
+		if (res.statusCode === 200) {
+			return scrapeProfile(res.body.toString(), profileUrl, actorName, entity);
+		}
 
-		return profile;
-	}
-
-	return null;
+		return null;
+	}, Promise.resolve());
 }
 
 module.exports = {

src/scrapers/scrapers.js

@@ -4,6 +4,7 @@ const adulttime = require('./adulttime');
 const assylum = require('./assylum');
 const aziani = require('./aziani');
 const amateurallure = require('./amateurallure');
+const americanpornstar = require('./americanpornstar');
 const babes = require('./babes');
 const bamvisions = require('./bamvisions');
 const bang = require('./bang');
@@ -80,6 +81,7 @@ module.exports = {
 		'21sextury': sextury,
 		adulttime,
 		amateurallure,
+		americanpornstar,
 		amateureuro: porndoe,
 		assylum,
 		aziani,
@@ -158,6 +160,7 @@ module.exports = {
 		'21sextury': sextury,
 		allanal: mikeadriano,
 		amateureuro: porndoe,
+		americanpornstar,
 		analbbc: fullpornnetwork,
 		analized: fullpornnetwork,
 		analviolation: fullpornnetwork,

src/utils/qu.js

@@ -40,6 +40,10 @@ function formatDate(dateValue, format, inputFormat) {
 }
 
 function prefixUrl(urlValue, origin, protocol = 'https') {
+	if (/^http/.test(urlValue)) {
+		return urlValue;
+	}
+
 	if (protocol && /^\/\//.test(urlValue)) {
 		return `${protocol}:${urlValue}`;
 	}
@@ -48,7 +52,7 @@ function prefixUrl(urlValue, origin, protocol = 'https') {
 		return `${origin}${urlValue}`;
 	}
 
-	return urlValue;
+	return `${origin}/${urlValue}`;
 }
 
 function q(context, selector, attrArg, applyTrim = true) {

src/utils/slugify.js

@@ -39,13 +39,18 @@ const substitutes = {
 function slugify(string, delimiter = '-', {
 	encode = false,
 	removeAccents = true,
+	removePunctuation = false,
 	limit = 1000,
 } = {}) {
 	if (!string || typeof string !== 'string') {
 		return string;
 	}
 
-	const slugComponents = string.trim().toLowerCase().match(/[A-Za-zÀ-ÖØ-öø-ÿ0-9]+/g);
+	const slugComponents = string
+		.trim()
+		.toLowerCase()
+		.replace(removePunctuation && /[.,:;'"]/g, '')
+		.match(/[A-Za-zÀ-ÖØ-öø-ÿ0-9]+/g);
 
 	if (!slugComponents) {
 		return '';