Splitting Han titles and actors in Model Media scraper.

assets/components/releases/release.vue

@@ -35,7 +35,10 @@
 		/>
 
 		<div class="info column">
-			<div class="row row-title">
+			<div
+				class="row row-title"
+				:class="{ 'has-alt': release.altTitles?.length > 0 }"
+			>
 				<h2
 					v-if="release.title"
 					class="title"
@@ -62,6 +65,19 @@
 				/>
 			</div>
 
+			<div
+				v-if="release.altTitles?.length > 0"
+				class="row alttitles"
+			>
+				<h2
+					v-for="(altTitle, index) in release.altTitles"
+					:key="`altitle-${index}`"
+					class="alttitle"
+				>
+					{{ altTitle }}
+				</h2>
+			</div>
+
 			<Releases
 				v-if="release.scenes && release.scenes.length > 0"
 				:releases="release.scenes"
@@ -520,6 +536,11 @@ export default {
 	color: var(--shadow);
 }
 
+.alttitle {
+	color: var(--shadow);
+	font-size: 1rem;
+}
+
 .album-toggle {
 	height: fit-content;
 	display: inline-flex;

assets/js/fragments.js

@@ -545,6 +545,7 @@ const releaseFragment = `
   release(id: $releaseId) {
     id
     title
+	altTitles
     description
     date
 	datePrecision

config/default.js

@@ -30,6 +30,9 @@ module.exports = {
 			},
 		},
 	},
+	location: {
+		userAgent: 'contact via https://traxxx.me/',
+	},
 	analytics: {
 		enabled: false,
 		address: 'http://localhost:3000/script.js',

migrations/20230801225038_scene_titles.js

@@ -0,0 +1,11 @@
+exports.up = async (knex) => {
+	await knex.schema.alterTable('releases', (table) => {
+		table.specificType('alt_titles', 'text ARRAY');
+	});
+};
+
+exports.down = async (knex) => {
+	await knex.schema.alterTable('releases', (table) => {
+		table.dropColumn('alt_titles');
+	});
+};

src/scrapers/modelmedia.js

@@ -14,10 +14,38 @@ function scrapeAll(scenes) {
 			const { origin, pathname, searchParams } = new URL(url);
 
 			release.url = `${origin}${pathname}`;
-			release.actors = searchParams.get('models_name')?.split(',');
+			release.shootId = pathname.match(/((LA)|(LT)|(MA)|(MD)|(MM)|(MS)|(MT)|(RR))[\w-]+/)?.[0]; // pathname sometimes contains other text, match at least two letters to prevent false positives
+
+			release.actors = searchParams.get('models_name')?.split(',').map((actor) => {
+				const [han, english] = actor.split('/').map((name) => name.trim());
+
+				if (/amateur/i.test(english)) {
+					// not a name
+					return null;
+				}
+
+				return {
+					name: english || han,
+					alias: english && han,
+				};
+			}).filter(Boolean);
+		}
+
+		const rawTitle = query.content('.video-title div')?.replace(release.shootId, '');
+
+		if (rawTitle) {
+			// find / closest to Han in case there are multiple, account for no / at all
+			const hanIndex = rawTitle.match(/\p{Script_Extensions=Han}/u)?.index;
+			const splitIndex = rawTitle.slice(0, hanIndex).lastIndexOf('/') || hanIndex;
+
+			if (hanIndex && splitIndex > -1) {
+				release.title = rawTitle.slice(0, splitIndex).trim();
+				release.altTitles = [rawTitle.slice(splitIndex + 1).trim()];
+			} else {
+				release.title = rawTitle;
+			}
 		}
 
-		release.title = query.content('.video-title div');
 		release.duration = query.duration('.timestamp');
 
 		const poster = query.img('img', { attribute: 'data-src' });
@@ -31,8 +59,6 @@ function scrapeAll(scenes) {
 
 		release.teaser = query.video(null, { attribute: 'data-video-src' });
 
-		console.log(release);
-
 		return release;
 	});
 }
@@ -49,17 +75,16 @@ function scrapeProfile({ query }) {
 	}
 
 	profile.description = query.content('h2') || null;
-	profile.height = query.number('//span[text()="Measurements"]/following-sibling::span', { match: /(\d+) cm/, matchIndex: 1 });
+	profile.height = query.number('//span[text()="Height"]/following-sibling::span', { match: /(\d+) cm/, matchIndex: 1 });
 	profile.weight = query.number('//span[text()="Weight"]/following-sibling::span', { match: /(\d+) kg/, matchIndex: 1 });
 
-	profile.measurements = query.number('//span[text()="Birth Place"]/following-sibling::span', { match: /(\d+) cm/, matchIndex: 1 });
+	// can't find a single profile wiht this information available, but add for good measure
+	profile.measurements = query.content('//span[text()="Measurements"]/following-sibling::span');
 	profile.birthPlace = query.number('//span[text()="Birth Place"]/following-sibling::span');
 
 	profile.banner = query.img('div[class*="banner"] > img');
 	profile.photos = query.imgs('#MusModelSwiper img');
 
-	console.log(profile);
-
 	return profile;
 }
 

src/scrapers/scrapers.js

@@ -82,6 +82,7 @@ const scrapers = {
 		americanpornstar,
 		amateureuro: porndoe,
 		archangel,
+		asiam: modelmedia,
 		assylum,
 		aziani,
 		badoink,
@@ -115,6 +116,7 @@ const scrapers = {
 		interracialpass: hush,
 		inthecrack,
 		jayrock,
+		jerkaoke: modelmedia,
 		jesseloadsmonsterfacials,
 		julesjordan,
 		karups,
@@ -178,6 +180,7 @@ const scrapers = {
 		analviolation: fullpornnetwork,
 		anilos: nubiles,
 		archangel,
+		asiam: modelmedia,
 		aziani,
 		babes: mindgeek,
 		babevr: badoink,
@@ -234,6 +237,7 @@ const scrapers = {
 		interracialpovs: hush,
 		inthecrack,
 		jamesdeen: fullpornnetwork,
+		jerkaoke: modelmedia,
 		julesjordan,
 		karups,
 		kellymadison,

src/store-releases.js

@@ -32,6 +32,7 @@ async function curateReleaseEntry(release, batchId, existingRelease, type = 'sce
 
 	const curatedRelease = {
 		title: decode(release.title),
+		alt_titles: release.altTitles?.map((title) => decode(title)),
 		entry_id: release.entryId || null,
 		entity_id: release.entity.id,
 		studio_id: release.studio?.id || null,
@@ -46,6 +47,8 @@ async function curateReleaseEntry(release, batchId, existingRelease, type = 'sce
 		updated_batch_id: batchId,
 	};
 
+	console.log(curatedRelease);
+
 	if (release.id) {
 		// release is updated
 		curatedRelease.id = release.id;

src/utils/resolve-place.js

@@ -1,5 +1,7 @@
 'use strict';
 
+const config = require('config');
+
 const knex = require('../knex');
 const logger = require('../logger')(__filename);
 const http = require('./http');
@@ -27,7 +29,7 @@ async function resolvePlace(query) {
 		// https://operations.osmfoundation.org/policies/nominatim/
 		const res = await http.get(`https://nominatim.openstreetmap.org/search/${encodeURI(query)}?format=json&accept-language=en&addressdetails=1`, {
 			headers: {
-				'User-Agent': 'contact at moonloop.adult@protonmail.com',
+				'User-Agent': config.location.userAgent,
 			},
 			interval: 1000,
 			concurrency: 1,