Added tags and duration to scraping. Added LegalPorno scraper.

src/scrapers/xempire.js

@@ -4,6 +4,36 @@ const bhttp = require('bhttp');
 const cheerio = require('cheerio');
 const moment = require('moment');
 
+const tagMap = {
+    Anal: 'anal',
+    'Ass Licking': 'ass licking',
+    'Ass To Mouth': 'ATM',
+    'Big Ass': 'big butt',
+    'Big Tits': 'big boobs',
+    Black: 'big black cock',
+    Blonde: 'blonde',
+    Blowjob: 'blowjob',
+    'Blowjob (double)': 'double blowjob',
+    Brunette: 'brunette',
+    'Cum Swallowing': 'swallowing',
+    Cumshot: 'cumshot',
+    Deepthroat: 'deepthroat',
+    'Double Penetration (DP)': 'DP',
+    Ebony: 'ebony',
+    Facial: 'facial',
+    Gangbang: 'gangbang',
+    Gonzo: 'gonzo',
+    Hardcore: 'hardcore',
+    Interracial: 'interracial',
+    Latina: 'latina',
+    Petite: 'petite',
+    'Pussy Licking': 'pussy licking',
+    Rimjob: 'ass licking',
+    'Rough Sex': 'rough',
+    'Small Tits': 'small boobs',
+    Threesome: 'threesome',
+};
+
 function scrape(html, site) {
     const $ = cheerio.load(html, { normalizeWhitespace: true });
     const scenesElements = $('.sceneInfo').toArray();
@@ -39,21 +69,70 @@ function scrape(html, site) {
     });
 }
 
-function scrapeScene(html, url, site) {
-    const $ = cheerio.load(html, { normalizeWhitespace: true });
-
+function scrapeSceneFallback($, url, site) {
     const title = $('h1.title').text();
     const date = moment.utc($('.updatedDate').text(), 'MM-DD-YYYY').toDate();
     const actors = $('.sceneColActors a').map((actorIndex, actorElement) => $(actorElement).text()).toArray();
-    const description = $('.sceneDesc').text().replace(/Video Description:/g, ' ').trim();
+
+    const description = ($('.sceneDesc').text() || '').replace(/Video Description:/g, ' ').trim();
     const stars = $('.currentRating').text().split('/')[0] / 2;
 
+    const rawTags = $('.sceneColCategories > a').map((tagIndex, tagElement) => $(tagElement).text()).toArray();
+    const tags = rawTags.reduce((accTags, tag) => (tagMap[tag] ? [...accTags, tagMap[tag]] : accTags), []);
+
     return {
         url,
         title,
         date,
         actors,
         description,
+        tags,
+        rating: {
+            stars,
+        },
+        site,
+    };
+}
+
+function scrapeScene(html, url, site) {
+    const $ = cheerio.load(html, { normalizeWhitespace: true });
+    const json = $('script[type="application/ld+json"]').html();
+
+    if (!json) {
+        return scrapeSceneFallback($, url, site);
+    }
+
+    const data = JSON.parse(json)[0];
+
+    const title = data.isPartOf.name;
+    const date = moment.utc(data.dateCreated, 'YYYY-MM-DD').toDate();
+
+    const actors = data.actor
+        .sort(({ genderA }, { genderB }) => {
+            if (genderA === 'female' && genderB === 'male') return 1;
+            if (genderA === 'male' && genderB === 'female') return -1;
+
+            return 0;
+        })
+        .map(actor => actor.name);
+
+    const description = data.description || undefined;
+    const stars = (data.aggregateRating.ratingValue / data.aggregateRating.bestRating) * 5;
+
+    const runtime = data.duration.slice(2).split(':');
+    const duration = Number(runtime[0]) * 3600 + Number(runtime[1]) * 60 + Number(runtime[2]);
+
+    const rawTags = data.keywords.split(', ');
+    const tags = rawTags.reduce((accTags, tag) => (tagMap[tag] ? [...accTags, tagMap[tag]] : accTags), []);
+
+    return {
+        url,
+        title,
+        date,
+        actors,
+        description,
+        duration,
+        tags,
         rating: {
             stars,
         },