Added partial 'fcuk' (Exploited College Girls) scraper. Added file parameter for actor names and scene URLs.

src/app.js

@@ -10,6 +10,7 @@ const fetchUpdates = require('./updates');
 const { fetchScenes, fetchMovies } = require('./deep');
 const { storeReleases, updateReleasesSearch } = require('./store-releases');
 const { scrapeActors } = require('./actors');
+const getFileEntries = require('./utils/file-entries');
 
 async function init() {
 	if (argv.server) {
@@ -21,13 +22,19 @@ async function init() {
 		await updateReleasesSearch();
 	}
 
-	const actors = argv.actors && await scrapeActors(argv.actors);
+	const actorsFromFile = argv.actorsFile && await getFileEntries(argv.actorsFile);
+	const actorNames = (argv.actors || []).concat(actorsFromFile || []);
+
+	const actors = actorNames.length > 0 && await scrapeActors(actorNames);
 	const actorBaseScenes = argv.actors && argv.actorScenes && actors.map(actor => actor.releases).flat().filter(Boolean);
 
 	const updateBaseScenes = (argv.all || argv.channels || argv.networks) && await fetchUpdates();
 
+	const scenesFromFile = argv.scenesFile && await getFileEntries(argv.scenesFile);
+	const sceneUrls = (argv.scenes || []).concat(scenesFromFile || []);
+
 	const deepScenes = argv.deep
-		? await fetchScenes([...(argv.scenes || []), ...(updateBaseScenes || []), ...(actorBaseScenes || [])])
+		? await fetchScenes([...(sceneUrls), ...(updateBaseScenes || []), ...(actorBaseScenes || [])])
 		: [...(updateBaseScenes || []), ...(actorBaseScenes || [])];
 
 	const sceneMovies = deepScenes && argv.sceneMovies && deepScenes.map(scene => scene.movie).filter(Boolean);

src/argv.js

@@ -30,6 +30,10 @@ const { argv } = yargs
 		type: 'array',
 		alias: 'actor',
 	})
+	.option('actors-file', {
+		describe: 'Scrape actors names from file',
+		type: 'string',
+	})
 	.option('actor-scenes', {
 		describe: 'Fetch all scenes for an actor',
 		type: 'boolean',
@@ -53,10 +57,14 @@ const { argv } = yargs
 		alias: 'with-profiles',
 		default: false,
 	})
-	.option('scene', {
+	.option('scenes', {
 		describe: 'Scrape scene info from URL',
 		type: 'array',
-		alias: 'scenes',
+		alias: 'scene',
+	})
+	.option('scenes-file', {
+		describe: 'Scrape scene info from URLs in a file',
+		type: 'string',
 	})
 	.option('movie', {
 		describe: 'Scrape movie info from URL',

src/media.js

@@ -101,7 +101,7 @@ function toBaseSource(rawSource) {
 		if (rawSource.attempts) baseSource.attempts = rawSource.attempts;
 		if (rawSource.queueMethod) baseSource.queueMethod = rawSource.queueMethod;
 
-		if (rawSource.copyright) baseSource.copyright = rawSource.copyright;
+		if (rawSource.credit !== undefined) baseSource.credit = rawSource.credit;
 		if (rawSource.comment) baseSource.comment = rawSource.comment;
 		if (rawSource.group) baseSource.group = rawSource.group;
 
@@ -569,7 +569,7 @@ function curateMediaEntry(media, index) {
 		source: media.src,
 		source_page: media.url,
 		scraper: media.scraper,
-		copyright: media.copyright,
+		credit: media.credit,
 		comment: media.comment,
 	};
 
@@ -685,7 +685,7 @@ async function associateAvatars(profiles) {
 		? {
 			...profile,
 			avatarBaseMedia: toBaseMedias([profile.avatar], 'avatars', {
-				copyright: profile.network?.name || profile.site?.name || null,
+				credit: (profile.credit !== undefined && (profile.network?.name || profile.site?.name)) || null,
 				scraper: profile.scraper || null,
 			})[0],
 		}

src/scrapers/boobpedia.js

@@ -69,7 +69,7 @@ function scrapeProfile(html) {
 
 		profile.avatar = {
 			src: `http://www.boobpedia.com${avatarPath}`,
-			copyright: null,
+			credit: null,
 		};
 	}
 

src/scrapers/fcuk.js

@@ -0,0 +1,71 @@
+'use strict';
+
+const qu = require('../utils/qu');
+
+function scrapeLatest(scenes, channel) {
+	return scenes.map(({ query }) => {
+		const release = {};
+
+		release.url = query.url('a.more:not([href*="/join.php"])', 'href', { origin: channel.url });
+
+		if (release.url) {
+			release.entryId = new URL(release.url).pathname.match(/\/scene\/(\d+)\/(\d+)/).slice(1, 3).join('-');
+		} else {
+			release.entryId = query.img('.bigthumb').match(/\/scenes\/(\w+)/)?.[1];
+		}
+
+		release.title = query.q('h5 strong', true)?.match(/. - (.+)$/)[1] || query.text('.videos h3');
+		release.description = query.text('p');
+		release.date = query.date('h5 strong, .videos h3', 'MMM. DD, YYYY', /\w+. \d{2}, \d{4}/);
+
+		release.poster = query.img('.bigthumb', null, { origin: channel.url });
+		release.photos = query.imgs('.smallthumb', null, { origin: channel.url });
+
+		release.tags = query.all('a[href*="/keywords"]', true);
+
+		return release;
+	});
+}
+
+function scrapeScene({ query }, url, channel) {
+	const release = {};
+
+	release.entryId = new URL(url).pathname.match(/\/scene\/(\d+)\/(\d+)/).slice(1, 3).join('-');
+
+	release.title = query.q('h4 strong, .videos h3', true);
+	release.description = query.q('#about p, .videos p', true);
+
+	const actors = query.urls('a[href*="/girl/"]').map(actorUrl => actorUrl.match(/video-(\w+)/)?.[1]).filter(Boolean);
+
+	if (actors.length > 0) {
+		release.actors = actors;
+	} else {
+		// release.actors = [query.q('.previewmed h5 strong', true)?.match(/^([\w\s]+),/)?.[0] || query.q('.videos h3', true)].filter(Boolean);
+		release.actors = [release.title];
+	}
+
+	release.tags = query.all('.info a[href*="/keywords"], .buttons a[href*="/keywords"]', true);
+
+	release.poster = query.img('#info .main-preview, .bigthumb', null, { origin: channel.url });
+	release.photos = [query.img('.previewmed img', null, { origin: channel.url })].concat(query.imgs('.hd-clip img, .smallthumb', null, { origin: channel.url })).filter(photo => photo);
+
+	return release;
+}
+
+async function fetchLatest(channel, page = 1) {
+	const url = `${channel.url}/free/updates/videos/${(page - 1) * 10}`;
+	const res = await qu.getAll(url, '.videos');
+
+	return res.ok ? scrapeLatest(res.items, channel) : res.status;
+}
+
+async function fetchScene(url, channel) {
+	const res = await qu.get(url);
+
+	return res.ok ? scrapeScene(res.item, url, channel) : res.status;
+}
+
+module.exports = {
+	fetchLatest,
+	fetchScene,
+};

src/scrapers/freeones.js

@@ -52,7 +52,7 @@ function scrapeProfile(html, actorName) {
 	profile.social = Array.from(document.querySelectorAll('.profile-meta-item a.social-icons'), el => el.href);
 
 	const avatar = document.querySelector('.profile-image-large img').src;
-	if (!avatar.match('placeholder')) profile.avatar = { src: avatar, copyright: null };
+	if (!avatar.match('placeholder')) profile.avatar = { src: avatar, credit: null };
 
 	return profile;
 }

src/scrapers/scrapers.js

@@ -19,6 +19,7 @@ const evilangel = require('./evilangel');
 const fakehub = require('./fakehub');
 const famedigital = require('./famedigital');
 const fantasymassage = require('./fantasymassage');
+const fcuk = require('./fcuk');
 const fullpornnetwork = require('./fullpornnetwork');
 const girlsway = require('./girlsway');
 const hush = require('./hush');
@@ -93,6 +94,7 @@ module.exports = {
 		fakehub,
 		famedigital,
 		fantasymassage,
+		fcuk,
 		forbondage: porndoe,
 		fullpornnetwork,
 		girlsway,

src/utils/file-entries.js

@@ -0,0 +1,16 @@
+'use strict';
+
+const fs = require('fs');
+
+async function getFileEntries(location) {
+	if (!location) {
+		throw new Error('No filepath provided');
+	}
+
+	const file = await fs.promises.readFile(location, 'utf-8');
+	const entries = file.split(/\n/).map(entry => entry.trim()).filter(Boolean);
+
+	return entries;
+}
+
+module.exports = getFileEntries;

src/utils/qu.js

@@ -125,7 +125,7 @@ function date(context, selector, format, match, attr = 'textContent') {
 	return extractDate(dateString, format, match);
 }
 
-function image(context, selector = 'img', attr, origin, protocol = 'https') {
+function image(context, selector = 'img', attr, { origin, protocol = 'https' } = {}) {
 	const imageEl = (attr && q(context, selector, attr))
 		|| q(context, selector, 'data-src')
 		|| q(context, selector, 'src');
@@ -133,7 +133,7 @@ function image(context, selector = 'img', attr, origin, protocol = 'https') {
 	return prefixUrl(imageEl, origin, protocol);
 }
 
-function images(context, selector = 'img', attr, origin, protocol = 'https') {
+function images(context, selector = 'img', attr, { origin, protocol = 'https' } = {}) {
 	const attribute = attr
 		|| (q(context, selector, 'data-src') && 'data-src')
 		|| (q(context, selector, 'src') && 'src');
@@ -143,31 +143,31 @@ function images(context, selector = 'img', attr, origin, protocol = 'https') {
 	return imageEls.map(imageEl => prefixUrl(imageEl, origin, protocol));
 }
 
-function url(context, selector = 'a', attr = 'href', origin, protocol = 'https') {
+function url(context, selector = 'a', attr = 'href', { origin, protocol = 'https' } = {}) {
 	const urlEl = q(context, selector, attr);
 
 	return attr ? prefixUrl(urlEl, origin, protocol) : urlEl;
 }
 
-function urls(context, selector = 'a', attr = 'href', origin, protocol = 'https') {
+function urls(context, selector = 'a', attr = 'href', { origin, protocol = 'https' } = {}) {
 	const urlEls = all(context, selector, attr);
 
 	return attr ? urlEls.map(urlEl => prefixUrl(urlEl, origin, protocol)) : urlEls;
 }
 
-function poster(context, selector = 'video', attr = 'poster', origin, protocol = 'https') {
+function poster(context, selector = 'video', attr = 'poster', { origin, protocol = 'https' } = {}) {
 	const posterEl = q(context, selector, attr);
 
 	return attr ? prefixUrl(posterEl, origin, protocol) : posterEl;
 }
 
-function video(context, selector = 'source', attr = 'src', origin, protocol = 'https') {
+function video(context, selector = 'source', attr = 'src', { origin, protocol = 'https' } = {}) {
 	const trailerEl = q(context, selector, attr);
 
 	return attr ? prefixUrl(trailerEl, origin, protocol) : trailerEl;
 }
 
-function videos(context, selector = 'source', attr = 'src', origin, protocol = 'https') {
+function videos(context, selector = 'source', attr = 'src', { origin, protocol = 'https' } = {}) {
 	const trailerEls = all(context, selector, attr);
 
 	return attr ? trailerEls.map(trailerEl => prefixUrl(trailerEl, origin, protocol)) : trailerEls;