1.138.9

package-lock.json

@@ -1,6 +1,6 @@
 {
     "name": "traxxx",
-    "version": "1.138.7",
+    "version": "1.138.9",
     "lockfileVersion": 1,
     "requires": true,
     "dependencies": {

package.json

@@ -1,6 +1,6 @@
 {
     "name": "traxxx",
-    "version": "1.138.7",
+    "version": "1.138.9",
     "description": "All the latest porn releases in one place",
     "main": "src/app.js",
     "scripts": {

seeds/02_sites.js

@@ -3415,21 +3415,21 @@ const sites = [
 	{
 		slug: 'paintoy',
 		name: 'Paintoy',
-		url: 'https://www.paintoy.com',
+		url: 'http://www.paintoy.com',
 		tags: ['bdsm'],
 		parent: 'insex',
 	},
 	{
 		slug: 'aganmedon',
 		name: 'Agan Medon',
-		url: 'https://www.aganmedon.com',
+		url: 'http://www.aganmedon.com',
 		tags: ['bdsm', 'animated'],
 		parent: 'insex',
 	},
 	{
 		slug: 'sensualpain',
 		name: 'Sensual Pain',
-		url: 'https://www.sensualpain.com',
+		url: 'http://www.sensualpain.com',
 		tags: ['bdsm'],
 		parent: 'insex',
 	},

src/actors.js

@@ -114,7 +114,13 @@ function getAverage(items) {
 }
 
 function toBaseActors(actorsOrNames, release) {
-	return actorsOrNames.map((actorOrName) => {
+	if (!actorsOrNames) {
+		return [];
+	}
+
+	const baseActors = actorsOrNames
+		.filter(actorOrName => actorOrName && (typeof actorOrName === 'string' || actorOrName.name))
+		.map((actorOrName) => {
 			const [baseName, entryId] = (actorOrName.name || actorOrName).split(':');
 
 			const name = capitalize(baseName);
@@ -137,6 +143,8 @@ function toBaseActors(actorsOrNames, release) {
 
 			return baseActor;
 		});
+
+	return baseActors;
 }
 
 function curateActor(actor, withDetails = false, isProfile = false) {
@@ -832,4 +840,5 @@ module.exports = {
 	fetchActor,
 	scrapeActors,
 	searchActors,
+	toBaseActors,
 };

src/argv.js

@@ -30,20 +30,20 @@ const { argv } = yargs
 		type: 'boolean',
 		alias: 'web',
 	})
-	.option('networks', {
+	.option('include-networks', {
 		describe: 'Network to scrape all channels from (overrides configuration)',
 		type: 'array',
-		alias: 'network',
+		alias: ['include-network', 'networks', 'network'],
 	})
 	.option('exclude-networks', {
 		describe: 'Network not to scrape any channels from (overrides configuration)',
 		type: 'array',
 		alias: 'exclude-network',
 	})
-	.option('channels', {
+	.option('include-channels', {
 		describe: 'Channel to scrape (overrides configuration)',
 		type: 'array',
-		alias: 'channel',
+		alias: ['include-channel', 'channels', 'channel'],
 	})
 	.option('exclude-channels', {
 		describe: 'Channel not to scrape (overrides configuration)',

src/entities.js

@@ -64,8 +64,8 @@ async function fetchIncludedEntities() {
 		includeAll: !argv.networks && !argv.channels && !config.include?.networks && !config.include?.channels,
 		includedNetworks: argv.networks || (!argv.channels && config.include?.networks) || [],
 		includedChannels: argv.channels || (!argv.networks && config.include?.channels) || [],
-		excludedNetworks: argv.excludeNetworks || config.exclude?.networks || [],
+		excludedNetworks: argv.excludeNetworks || config.exclude?.networks.filter(network => !argv.networks?.includes(network)) || [], // ignore explicitly included networks
-		excludedChannels: argv.excludeChannels || config.exclude?.channels || [],
+		excludedChannels: argv.excludeChannels || config.exclude?.channels.filter(channel => !argv.channels?.includes(channel)) || [], // ignore explicitly included channels
 	};
 
 	const rawNetworks = await knex.raw(`

src/scrapers/jesseloadsmonsterfacials.js

@@ -1,23 +1,35 @@
 'use strict';
 
-const { get, initAll } = require('../utils/qu');
+const { get, initAll, formatDate } = require('../utils/qu');
 
 function scrapeLatest(scenes, dates, site) {
 	return scenes.map(({ qu }, index) => {
 		const release = {};
+		const path = qu.url('a[href*="videos/"]');
 
-		const path = qu.url('a');
+		if (path) {
 			release.url = `${site.url}/visitors/${path}`;
-		release.entryId = path.match(/videos\/([a-zA-Z0-9]+)(?:_hd)?_trailer/)?.[1];
+		}
 
 		if (dates && dates[index]) {
 			release.date = dates[index].qu.date(null, 'MM/DD/YYYY');
 		}
 
+		const entryId = path?.match(/videos\/([a-zA-Z0-9]+)(?:_hd)?_trailer/)?.[1]
+			|| qu.img('img[src*="graphics/fft"]')?.match(/fft_(\w+).gif/)?.[1];
+
+		if (!entryId) {
+			return null;
+		}
+
+		release.entryId = release.date ? `${formatDate(release.date, 'YYYY-MM-DD')}-${entryId}` : entryId;
 		release.description = qu.q('tbody tr:nth-child(3) font', true);
 
 		const infoLine = qu.q('font[color="#663366"]', true);
-		if (infoLine) release.duration = Number(infoLine.match(/(\d+) min/)[1]) * 60;
+
+		if (infoLine) {
+			release.duration = Number(infoLine.match(/(\d+) min/i)?.[1] || infoLine.match(/video: (\d+)/i)?.[1]) * 60 || null;
+		}
 
 		const poster = qu.img('img[src*="photos/"][width="400"]');
 		release.poster = `${site.url}/visitors/${poster}`;

src/scrapers/traxxx.js

@@ -258,7 +258,8 @@ async function fetchLatest(entity, page, options) {
 			.limit(faker.random.number({ min: 2, max: 15 }))
 			.pluck('name');
 
-		release.actors = actors(release);
+		// release.actors = actors(release);
+		release.actors = [null, 'Charles Darwin'];
 		release.title = title(release);
 
 		return release;

src/store-releases.js

@@ -9,7 +9,7 @@ const slugify = require('./utils/slugify');
 const bulkInsert = require('./utils/bulk-insert');
 const resolvePlace = require('./utils/resolve-place');
 const { formatDate } = require('./utils/qu');
-const { associateActors, scrapeActors } = require('./actors');
+const { associateActors, scrapeActors, toBaseActors } = require('./actors');
 const { associateReleaseTags } = require('./tags');
 const { curateEntity } = require('./entities');
 const { associateReleaseMedia } = require('./media');
@@ -291,7 +291,8 @@ async function storeScenes(releases) {
 	const [batchId] = await knex('batches').insert({ comment: null }).returning('id');
 
 	const releasesWithChannels = await attachChannelEntities(releases);
-	const releasesWithStudios = await attachStudios(releasesWithChannels);
+	const releasesWithBaseActors = releasesWithChannels.map(release => ({ ...release, actors: toBaseActors(release.actors) }));
+	const releasesWithStudios = await attachStudios(releasesWithBaseActors);
 
 	// uniqueness is entity ID + entry ID, filter uniques after adding entities
 	const { uniqueReleases, duplicateReleases, duplicateReleaseEntries } = await filterDuplicateReleases(releasesWithStudios);

src/updates.js

@@ -109,7 +109,12 @@ async function scrapeReleases(scraper, entity, preData, isUpcoming) {
 			return accReleases;
 		}
 
-		const pageReleasesWithEntity = pageReleases.map(release => ({ ...release, entity: release.entity || entity }));
+		const validPageReleases = pageReleases.filter(release => release?.entryId); // filter out empty and unidentified releases
+		const pageReleasesWithEntity = validPageReleases.map(release => ({ ...release, entity: release.entity || entity }));
+
+		if (pageReleases.length > validPageReleases.length) {
+			logger.warn(`Found ${pageReleases.length - validPageReleases.length} empty or unidentified releases on page ${page} for '${entity.name}'`);
+		}
 
 		if (needNextPage(pageReleasesWithEntity, accReleases, isUpcoming)) {
 			return scrapeReleasesPage(page + 1, accReleases.concat(pageReleasesWithEntity), isUpcoming);
@@ -119,6 +124,7 @@ async function scrapeReleases(scraper, entity, preData, isUpcoming) {
 	}
 
 	const releases = await scrapeReleasesPage(argv.page || 1, []);
+
 	const hasDates = releases.every(release => !!release.date);
 
 	const limitedReleases = (argv.last && releases.slice(0, Math.max(argv.last, 0)))
@@ -133,7 +139,7 @@ async function scrapeReleases(scraper, entity, preData, isUpcoming) {
 }
 
 async function scrapeLatestReleases(scraper, entity, preData) {
-	if ((!argv.latest && !argv.last && !argv.after) || !scraper.fetchLatest) {
+	if ((!argv.latest && !argv.last) || !scraper.fetchLatest) {
 		return emptyReleases;
 	}