Refactored Cum Louder scraper with unprint, changed entry ID to URL slug due unreliable ID.

src/scrapers/cumlouder.js

@@ -1,8 +1,8 @@
 'use strict';
 
+const unprint = require('unprint');
 const { decode } = require('html-entities');
 
-const qu = require('../utils/qu');
 const slugify = require('../utils/slugify');
 
 function scrapeAll(items, _channel) {
@@ -12,13 +12,13 @@ function scrapeAll(items, _channel) {
 		const { date, precision } = query.dateAgo('.fecha');
 		const poster = query.img('.thumb');
 
-		release.entryId = query.number(null, /\d+/, 'onclick');
-		release.url = query.url(null, 'href', { origin: 'https://www.cumlouder.com' });
+		release.url = query.url(null, { origin: 'https://www.cumlouder.com' });
+		release.entryId = new URL(release.url).pathname.match(/video\/([\w-]+)/)?.[1];
 
 		release.date = date;
 		release.datePrecision = precision;
 
-		release.title = query.cnt('h2');
+		release.title = query.content('h2');
 		release.duration = query.duration('.minutos');
 
 		release.poster = [
@@ -30,26 +30,36 @@ function scrapeAll(items, _channel) {
 	});
 }
 
-function scrapeScene({ query }, channel, html) {
+async function fetchLatest(channel, page) {
+	const res = await unprint.get(`${channel.url}/${page}/`, { selectAll: '.muestra-escena' });
+
+	if (res.ok) {
+		return scrapeAll(res.context, channel);
+	}
+
+	return res.status;
+}
+
+function scrapeScene({ query, html }, url) {
 	const release = {};
 
 	const { date, precision } = query.dateAgo('.sub-video .added');
 
-	release.entryId = html.match(/cumlouder_(\d+)/)?.[1];
+	release.entryId = new URL(url).pathname.match(/video\/([\w-]+)/)?.[1];
 
-	release.title = query.cnt('.video-top h1');
+	release.title = query.content('.video-top h1');
 	release.description = query.text('.sub-video p');
 
 	release.date = date;
 	release.datePrecision = precision;
 
 	release.actors = query.all('.sub-video .pornstar-link').map((el) => ({
-		name: query.cnt(el, null),
-		url: query.url(el, null, 'href', { origin: 'https://www.cumlouder.com' }),
+		name: unprint.query.content(el, null),
+		url: unprint.query.url(el, null, { origin: 'https://www.cumlouder.com' }),
 	}));
 
 	release.duration = query.duration('.video-top .duracion');
-	release.tags = query.cnts('.video-top .tag-link');
+	release.tags = query.contents('.video-top .tag-link');
 
 	release.poster = query.poster() || html.match(/urlImg\s*=\s*'(.*)';/)?.[1];
 	release.video = query.video() || decode(html.match(/urlVideo\s*=\s*'(.*)';/)?.[1]); // no trailers but full-length videos
@@ -59,55 +69,47 @@ function scrapeScene({ query }, channel, html) {
 	return release;
 }
 
-function scrapeProfile({ query, el }, channel) {
+async function fetchScene(url, channel) {
+	const res = await unprint.get(url);
+
+	if (res.ok) {
+		return scrapeScene(res.context, url, channel);
+	}
+
+	return res.status;
+}
+
+function scrapeProfile({ query }, channel) {
 	const profile = {};
 
 	const bio = query.all('.data-bio li').reduce((acc, bioEl) => ({
 		...acc,
-		[slugify(query.cnt(bioEl, 'strong'), '_')]: query.text(bioEl),
+		[slugify(unprint.query.content(bioEl, 'strong'), '_')]: unprint.query.text(bioEl),
 	}), {});
 
 	profile.nationality = bio.nationality;
-	profile.dateOfBirth = qu.extractDate(bio.date_of_birth, 'DD-MM-YYYY');
+	profile.dateOfBirth = unprint.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.description = query.content('.data-bio p:last-of-type');
 	profile.avatar = query.img('.thumb-bio');
 
-	profile.scenes = scrapeAll(qu.initAll(el, '.muestra-escena'), channel);
+	profile.socials = query.urls('a.twitter-timeline');
+
+	profile.scenes = scrapeAll(unprint.initAll(query.all('.muestra-escena')), channel);
 
 	return profile;
 }
 
-async function fetchLatest(channel, page) {
-	const res = await qu.getAll(`${channel.url}/${page}/`, '.muestra-escena');
-
-	if (res.ok) {
-		return scrapeAll(res.items, channel);
-	}
-
-	return res.status;
-}
-
-async function fetchScene(url, channel) {
-	const res = await qu.get(url);
-
-	if (res.ok) {
-		return scrapeScene(res.item, channel, res.html);
-	}
-
-	return res.status;
-}
-
 async function fetchProfile(actor, channel) {
-	const res = await qu.get(`https://www.cumlouder.com/girl/${actor.slug}/`, '.listado-escenas');
+	const res = await unprint.get(`https://www.cumlouder.com/girl/${actor.slug}/`, { select: '.listado-escenas' });
 
 	if (res.ok) {
-		return scrapeProfile(res.item, channel);
+		return scrapeProfile(res.context, channel);
 	}
 
 	return res.status;