Finished Cum Louder scraper, updated Vixen scraper. Added tag posters.

src/entities.js

@@ -218,7 +218,7 @@ async function fetchEntitiesBySlug(entitySlugs, sort = 'asc') {
 	const entitiesBySlug = entities.rows.reduce((accEntities, { entity }) => ({
 		...accEntities,
 		[entity.slug]: accEntities[entity.slug] || curateEntity(entity, true),
-		[urlToSiteSlug(entity.url)]: accEntities[entity.slug] || curateEntity(entity, true),
+		[urlToSiteSlug(entity.url)]: accEntities[urlToSiteSlug(entity.url)] || curateEntity(entity, true),
 	}), {});
 
 	return entitiesBySlug;

src/scrapers/cumlouder.js

@@ -3,6 +3,7 @@
 const { decode } = require('html-entities');
 
 const qu = require('../utils/qu');
+const slugify = require('../utils/slugify');
 
 function scrapeAll(items, _channel) {
 	return items.map(({ query }) => {
@@ -25,8 +26,6 @@ function scrapeAll(items, _channel) {
 			poster,
 		];
 
-		console.log(release);
-
 		return release;
 	});
 }
@@ -53,21 +52,33 @@ function scrapeScene({ query }, channel, html) {
 	release.tags = query.cnts('.video-top .tag-link');
 
 	release.poster = query.poster() || html.match(/urlImg\s*=\s*'(.*)';/)?.[1];
-	release.trailer = query.video() || decode(html.match(/urlVideo\s*=\s*'(.*)';/)?.[1]);
+	release.video = query.video() || decode(html.match(/urlVideo\s*=\s*'(.*)';/)?.[1]); // no trailers but full-length videos
 
-	release.shootId = release.poster?.match(/\/rc(\d+)/)?.[1] || release.trailer?.match(/\/episodio_(\d+)/)?.[1];
+	release.shootId = release.poster?.match(/\/rc(\d+)/)?.[1] || release.video?.match(/\/episodio_(\d+)/)?.[1];
 
-	console.log(release);
 	return release;
 }
 
-function scrapeProfile({ query }) {
+function scrapeProfile({ query, el }, channel) {
 	const profile = {};
 
+	const bio = query.all('.data-bio li').reduce((acc, bioEl) => ({
+		...acc,
+		[slugify(query.cnt(bioEl, 'strong'), '_')]: query.text(bioEl),
+	}), {});
+
+	profile.nationality = bio.nationality;
+	profile.dateOfBirth = qu.extractDate(bio.date_of_birth, 'DD-MM-YYYY');
+
+	profile.height = Number(bio.height) * 100;
+	profile.weight = parseInt(bio.weight, 10);
+	profile.eyes = bio.eye_color;
+	profile.hairColor = bio.hair_color;
+
 	profile.description = query.cnt('.data-bio p:last-of-type');
 	profile.avatar = query.img('.thumb-bio');
 
-	console.log(profile);
+	profile.scenes = scrapeAll(qu.initAll(el, '.muestra-escena'), channel);
 
 	return profile;
 }
@@ -92,11 +103,11 @@ async function fetchScene(url, channel) {
 	return res.status;
 }
 
-async function fetchProfile(actor) {
+async function fetchProfile(actor, channel) {
 	const res = await qu.get(`https://www.cumlouder.com/girl/${actor.slug}/`, '.listado-escenas');
 
 	if (res.ok) {
-		return scrapeProfile(res.item);
+		return scrapeProfile(res.item, channel);
 	}
 
 	return res.status;

src/scrapers/vixen.js

@@ -204,7 +204,7 @@ function scrapeUpcoming(scene, site) {
 	release.poster = getPosterFallbacks(scene.images.poster);
 	release.teaser = getTeaserFallbacks(scene.previews.poster);
 
-	release.entryId = (release.poster[0] || release.teaser[0])?.match(/\/(\d+)/)?.[1];
+	release.entryId = (release.poster[0] || release.teaser[0])?.src?.match(/\/(\d+)/)?.[1];
 
 	return [release];
 }