Added basic actor and network overview. Added DDF Network actor scraper. Various bug fixes and layout improvements.

src/scrapers/xempire.js

@@ -3,9 +3,10 @@
 const Promise = require('bluebird');
 const bhttp = require('bhttp');
 const cheerio = require('cheerio');
+const { JSDOM } = require('jsdom');
 const moment = require('moment');
 
-const knex = require('../knex');
+const { fetchSites } = require('../sites');
 const { matchTags } = require('../tags');
 const pluckPhotos = require('../utils/pluck-photos');
 
@@ -142,7 +143,7 @@ async function scrapeScene(html, url, site) {
     const duration = moment.duration(data.duration.slice(2).split(':')).asSeconds();
 
     const siteDomain = $('meta[name="twitter:domain"]').attr('content');
-    const siteId = siteDomain && siteDomain.split('.')[0].toLowerCase();
+    const siteSlug = siteDomain && siteDomain.split('.')[0].toLowerCase();
     const siteUrl = siteDomain && `https://www.${siteDomain}`;
 
     const poster = videoData.picPreview;
@@ -152,14 +153,14 @@ async function scrapeScene(html, url, site) {
 
     const rawTags = data.keywords.split(', ');
 
-    const [channelSite, tags] = await Promise.all([
+    const [[channelSite], tags] = await Promise.all([
         site.isFallback
-            ? knex('sites')
-                .where({ url: siteUrl })
-                .orWhere({ slug: siteId })
-                .first()
-            : site,
-        matchTags([...defaultTags[siteId], ...rawTags]),
+            ? fetchSites({
+                url: siteUrl,
+                slug: siteSlug,
+            })
+            : [site],
+        matchTags([...defaultTags[siteSlug], ...rawTags]),
     ]);
 
     return {
@@ -185,6 +186,31 @@ async function scrapeScene(html, url, site) {
     };
 }
 
+function scrapeActorSearch(html, url, actorName) {
+    const { document } = new JSDOM(html).window;
+    const actorLink = document.querySelector(`a[title="${actorName}" i]`);
+
+    return actorLink ? actorLink.href : null;
+}
+
+function scrapeProfile(html, url, actorName) {
+    const { document } = new JSDOM(html).window;
+
+    const avatarEl = document.querySelector('img.actorPicture');
+    const descriptionEl = document.querySelector('.actorBio p:not(.bioTitle)');
+
+    const profile = {
+        name: actorName,
+    };
+
+    if (avatarEl) profile.avatar = avatarEl.src;
+    if (descriptionEl) profile.description = descriptionEl.textContent.trim();
+
+    profile.releases = Array.from(document.querySelectorAll('.sceneList .scene a.imgLink'), el => `https://xempire.com${el.href}`);
+
+    return profile;
+}
+
 async function fetchLatest(site, page = 1) {
     const res = await bhttp.get(`${site.url}/en/videos/AllCategories/0/${page}`);
 
@@ -203,8 +229,34 @@ async function fetchScene(url, site) {
     return scrapeScene(res.body.toString(), url, site);
 }
 
+async function fetchProfile(actorName) {
+    const actorSlug = actorName.toLowerCase().replace(/\s+/, '+');
+    const searchUrl = `https://www.xempire.com/en/search/xempire/actor/${actorSlug}`;
+    const searchRes = await bhttp.get(searchUrl);
+
+    if (searchRes.statusCode !== 200) {
+        return null;
+    }
+
+    const actorUrl = scrapeActorSearch(searchRes.body.toString(), searchUrl, actorName);
+
+    if (actorUrl) {
+        const url = `https://xempire.com${actorUrl}`;
+        const actorRes = await bhttp.get(url);
+
+        if (actorRes.statusCode !== 200) {
+            return null;
+        }
+
+        return scrapeProfile(actorRes.body.toString(), url, actorName);
+    }
+
+    return null;
+}
+
 module.exports = {
     fetchLatest,
+    fetchProfile,
     fetchUpcoming,
     fetchScene,
 };