Fixed beforeFetchScenes not running for update releases. Fixed Hookup Hotshot deep scrape broken due missing NATS cookie.

migrations/20260922165429_anonymous_actors.js

@@ -0,0 +1,24 @@
+exports.up = async function(knex) {
+	// we want to be able to assign unidentified actors
+	await knex.raw(`
+		ALTER TABLE releases_actors
+		ALTER COLUMN actor_id DROP NOT NULL
+	`);
+
+	await knex.schema.alterTable('releases_actors', (table) => {
+		table.increments('id');
+		table.string('gender');
+	});
+};
+
+exports.down = async function(knex) {
+	await knex.raw(`
+		ALTER TABLE releases_actors
+		ALTER COLUMN actor_id SET NOT NULL
+	`);
+
+	await knex.schema.alterTable('releases_actors', (table) => {
+		table.dropColumn('id');
+		table.dropColumn('gender');
+	});
+};

seeds/00_tags.js

@@ -348,6 +348,11 @@ const tags = [
 		slug: 'brunette',
 		group: 'hair',
 	},
+	{
+		name: 'body writing',
+		slug: 'body-writing',
+		description: 'Grab a marker or a lipstick and use your body as a canvas. Label all your holes and make it clear what they should call you.',
+	},
 	{
 		name: 'boots',
 		slug: 'boots',

seeds/04_media.js

@@ -706,6 +706,7 @@ const tagMedia = [
 	['blowjob', 'azul_hermosa_realitykings', 'Azul Hermosa and Scott Nails in "Diva For A Day"', 'brazzers'],
 	['blowjob', 3, 'Rose Valie', 'handsonhardcore'],
 	['blowjob', 2, 'Luna Kitsuen in "Gag Reflex"', 'evilangel'],
+	['body-writing', 'emma_rosie_julesjordan', 'Emma Rosie', 'julesjordan'],
 	['bondage', 0, 'Veronica Leal', 'herlimit'],
 	['brunette', 0, 'Darcie Dolce', 'playboy'],
 	['bts', 'charlie_red_private', 'Charlie Red', 'private'],

src/deep.js

@@ -123,15 +123,21 @@ function fetchMovie(scraper, url, entity, baseRelease, options) {
 	return fetchScene(scraper, url, entity, baseRelease, options, 'movie');
 }
 
-async function scrapeRelease(baseRelease, entitiesByHostname, type = 'scene') {
-	const entity = baseRelease.entity || entitiesByHostname[urlToHostname(baseRelease.url)];
+function shouldDeepScrape(baseRelease) {
+	return argv.deep && !!(baseRelease.url || baseRelease.path || baseRelease.forceDeep);
+}
+
+async function scrapeRelease(baseRelease, entities, type = 'scene') {
+	const entity = entities.byId[baseRelease.entity?.id]
+		|| entities.byHostname[urlToHostname(baseRelease.url)]
+		|| baseRelease.entity;
 
 	if (!entity) {
 		logger.warn(`No entity available for ${baseRelease.url}`);
 		return baseRelease;
 	}
 
-	if ((!baseRelease.url && !baseRelease.path && !baseRelease.forceDeep) || !argv.deep) {
+	if (!shouldDeepScrape(baseRelease)) {
 		return {
 			...baseRelease,
 			entity,
@@ -247,22 +253,37 @@ async function scrapeRelease(baseRelease, entitiesByHostname, type = 'scene') {
 }
 
 async function scrapeReleases(baseReleases, entitiesByHostname, type) {
-	const entitiesWithBeforeDataEntries = await Promise.all(Object.entries(entitiesByHostname).map(async ([slug, entity]) => {
-		if (entity.scraper?.beforeFetchScenes) {
+	// entities attached to base releases (e.g. from updates) are not included in entitiesByHostname
+	const entitiesById = Object.fromEntries([
+		...Object.values(entitiesByHostname),
+		...baseReleases.map((baseRelease) => baseRelease.entity),
+	].filter(Boolean).map((entity) => [entity.id, entity]));
+
+	// only run before hook for entities that will actually be deep scraped
+	const deepEntityIds = new Set(baseReleases
+		.filter((baseRelease) => shouldDeepScrape(baseRelease))
+		.map((baseRelease) => baseRelease.entity?.id || entitiesByHostname[urlToHostname(baseRelease.url)]?.id)
+		.filter(Boolean));
+
+	const entitiesWithBeforeDataById = Object.fromEntries(await Promise.all(Object.values(entitiesById).map(async (entity) => {
+		if (deepEntityIds.has(entity.id) && entity.scraper?.beforeFetchScenes) {
 			const parameters = getRecursiveParameters(entity);
 			const preData = await entity.scraper.beforeFetchScenes(entity, parameters);
 
-			return [slug, { ...entity, preData }];
+			return [entity.id, { ...entity, preData }];
 		}
 
-		return [slug, entity];
-	}));
+		return [entity.id, entity];
+	})));
 
-	const entitiesWithBeforeDataBySlug = Object.fromEntries(entitiesWithBeforeDataEntries.filter(Boolean));
+	const entitiesWithBeforeData = {
+		byId: entitiesWithBeforeDataById,
+		byHostname: Object.fromEntries(Object.entries(entitiesByHostname).map(([hostname, entity]) => [hostname, entitiesWithBeforeDataById[entity.id]])),
+	};
 
 	return Promise.map(
 		baseReleases,
-		async (baseRelease) => scrapeRelease(baseRelease, entitiesWithBeforeDataBySlug, type),
+		async (baseRelease) => scrapeRelease(baseRelease, entitiesWithBeforeData, type),
 		{ concurrency: 1 },
 	);
 }

src/scrapers/hookuphotshot.js

@@ -1,6 +1,7 @@
 'use strict';
 
 const unprint = require('unprint');
+const { nanoid } = require('nanoid');
 
 function scrapeAll(scenes, _channel) {
 	return scenes.map(({ query }) => {
@@ -40,6 +41,12 @@ async function fetchLatest(channel, page = 1) {
 	return res.status;
 }
 
+async function beforeFetchScenes(channel) {
+	const res = await unprint.get(channel.url);
+
+	return { nats: res.cookies.nats || nanoid() };
+}
+
 function scrapeScene({ query, html }, { url, entity, baseRelease }) {
 	const release = {};
 
@@ -81,6 +88,20 @@ function scrapeScene({ query, html }, { url, entity, baseRelease }) {
 	return release;
 }
 
+async function fetchScene(url, entity, baseRelease, context) {
+	const res = await unprint.get(url, {
+		cookies: {
+			nats: context.beforeFetchScenes?.nats,
+		},
+	});
+
+	if (res.ok) {
+		return scrapeScene(res.context, { url, entity, baseRelease });
+	}
+
+	return res.status;
+}
+
 function scrapeProfile({ query }) {
 	const profile = {};
 
@@ -110,5 +131,6 @@ async function fetchProfile(actor, entity) {
 module.exports = {
 	fetchLatest,
 	fetchProfile,
-	scrapeScene,
+	fetchScene,
+	beforeFetchScenes,
 };