Added preflight method to scrapers. Added Assylum.

src/scrapers/assylum.js

@@ -0,0 +1,131 @@
+'use strict';
+
+const { get, geta, ctxa } = require('../utils/q');
+
+function extractActors(actorString) {
+    return actorString
+        ?.replace(/.*:|\(.*\)|\d+(-|\s)year(-|\s)old|nurses?|tangled/ig, '') // remove Patient:, (date) and other nonsense
+        .split(/\band\b|\bvs\b|\/|,|&/ig)
+        .map(actor => actor.trim())
+        .filter(actor => !!actor && !/\banal\b|\bschool\b|\bgamer\b|\breturn\b|\bfor\b|\bare\b|\bpart\b|realdoll|bimbo|p\d+/ig.test(actor))
+        || [];
+}
+
+function matchActors(actorString, models) {
+    return models
+        .filter(model => new RegExp(model.name, 'i')
+        .test(actorString));
+}
+
+function scrapeLatest(scenes, site, models) {
+    return scenes.map(({ q, qd, qu, qi }) => {
+        const release = {};
+
+        const pathname = qu('a.itemimg').slice(1);
+        [release.entryId] = pathname.split('/').slice(-1);
+        release.url = `${site.url}${pathname}`;
+
+        release.title = q('.itemimg img', 'alt') || q('h4 a', true);
+        release.description = q('.mas_longdescription', true);
+        release.date = qd('.movie_info2', 'MM/DD/YY', /\d{2}\/\d{2}\/\d{2}/);
+
+        const actorString = q('.mas_description', true);
+        const actors = matchActors(actorString, models);
+        if (actors.length > 0) release.actors = actors;
+        else release.actors = extractActors(actorString);
+
+        const posterPath = qi('.itemimg img');
+        release.poster = `${site.url}/${posterPath}`;
+
+        return release;
+    });
+}
+
+function scrapeScene({ html, q, qa, qd, qis }, url, site, models) {
+    const release = { url };
+
+    [release.entryId] = url.split('/').slice(-1);
+    release.title = q('.mas_title', true);
+    release.description = q('.mas_longdescription', true);
+    release.date = qd('.mas_description', 'MMMM DD, YYYY', /\w+ \d{1,2}, \d{4}/);
+
+    const actorString = q('.mas_description', true).replace(/\w+ \d{1,2}, \d{4}/, '');
+    const actors = matchActors(actorString, models);
+    if (actors.length > 0) release.actors = actors;
+    else release.actors = extractActors(actorString);
+
+    release.tags = qa('.tags a', true);
+
+    release.photos = qis('.stills img').map(photoPath => `${site.url}/${photoPath}`);
+
+    const posterIndex = 'splash:';
+    const poster = html.slice(html.indexOf('faceimages/', posterIndex), html.indexOf('.jpg', posterIndex) + 4);
+    if (poster) release.poster = `${site.url}/${poster}`;
+
+    const trailerIndex = html.indexOf('video/mp4');
+    const trailer = html.slice(html.indexOf('/content', trailerIndex), html.indexOf('.mp4', trailerIndex) + 4);
+    if (trailer) release.trailer = { src: `${site.url}${trailer}` };
+
+    return release;
+}
+
+function extractModels({ el }, site) {
+    const models = ctxa(el, '.item');
+
+    return models.map(({ q, qu }) => {
+        const actor = { gender: 'female' };
+
+        const avatar = q('.itemimg img');
+        actor.avatar = `${site.url}/${avatar.src}`;
+        actor.name = avatar.alt
+            .split(':').slice(-1)[0]
+            .replace(/xtreme girl|nurse/ig, '')
+            .trim();
+
+        const actorPath = qu('.itemimg');
+        actor.url = `${site.url}${actorPath.slice(1)}`;
+
+        return actor;
+    });
+}
+
+async function fetchModels(site, page = 1, accModels = []) {
+    const url = `${site.url}/?models/${page}`;
+    const qModels = await get(url);
+
+    if (qModels) {
+        const models = extractModels(qModels, site);
+        const nextPage = qModels.qa('.pagenumbers', true)
+            .map(pageX => Number(pageX))
+            .filter(Boolean) // remove << and >>
+            .includes(page + 1);
+
+        if (nextPage) {
+            return fetchModels(site, page + 1, accModels.concat(models));
+        }
+
+        return accModels.concat(models, { name: 'Dr. Gray' });
+    }
+
+    return [];
+}
+
+async function fetchLatest(site, page = 1, models) {
+    const url = `${site.url}/show.php?a=${site.parameters.a}_${page}`;
+    const qLatest = await geta(url, '.item');
+
+    return qLatest && scrapeLatest(qLatest, site, models);
+}
+
+async function fetchScene(url, site, release, preflight) {
+    const models = preflight || await fetchModels(site);
+    const qScene = await get(url);
+
+    return qScene && scrapeScene(qScene, url, site, models);
+}
+
+module.exports = {
+    fetchLatest,
+    fetchScene,
+    preflight: fetchModels,
+};

src/scrapers/scrapers.js

@@ -1,6 +1,7 @@
 'use strict';
 
 const adulttime = require('./adulttime');
+const assylum = require('./assylum');
 const babes = require('./babes');
 const bang = require('./bang');
 const bangbros = require('./bangbros');
@@ -52,10 +53,11 @@ const xempire = require('./xempire');
 
 module.exports = {
     releases: {
-        adulttime,
         '21naturals': naturals,
         '21sextreme': sextreme,
         '21sextury': sextury,
+        adulttime,
+        assylum,
         babes,
         bang,
         bangbros,