Added Manuel Ferrara site to Jules Jordan. Refactored Jules Jordan photo scraper for better compatability and quality.

src/scrapers/bang.js

@@ -7,6 +7,10 @@ const slugify = require('../utils/slugify');
 const clusterId = '617fb597b659459bafe6472470d9073a';
 const authKey = 'YmFuZy1yZWFkOktqVDN0RzJacmQ1TFNRazI=';
 
+function getScreenUrl(item, scene) {
+    return `https://i.bang.com/screenshots/${scene.dvd.id}/movie/${scene.order}/${item.screenId}.jpg`;
+}
+
 function encodeId(id) {
     return Buffer
         .from(id, 'hex')
@@ -53,8 +57,8 @@ function scrapeScene(scene, site) {
     const photos = defaultPoster ? photoset : photoset.slice(1);
     const poster = defaultPoster || photoset[0];
 
-    release.poster = `https://i.bang.com/screenshots/${scene.dvd.id}/movie/${scene.order}/${poster.screenId}.jpg`;
-    release.photos = photos.map(photo => `https://i.bang.com/screenshots/${scene.dvd.id}/movie/${scene.order}/${photo.screenId}.jpg`);
+    release.poster = getScreenUrl(poster, scene);
+    release.photos = photos.map(photo => getScreenUrl(photo, scene));
 
     release.trailer = {
         src: `https://i.bang.com/v/${scene.dvd.id}/${scene.identifier}/preview.mp4`,

src/scrapers/julesjordan.js

@@ -1,6 +1,6 @@
 'use strict';
 
-const Promise = require('bluebird');
+// const Promise = require('bluebird');
 const bhttp = require('bhttp');
 const cheerio = require('cheerio');
 const { JSDOM } = require('jsdom');
@@ -32,6 +32,8 @@ function scrapePhotos(html, type) {
 
             return [
                 src.replace('thumbs/', 'photos/'),
+                src.replace('thumbs/', '1600watermarked/'),
+                src.replace('thumbs/', '1280watermarked/'),
                 src.replace('thumbs/', '1024watermarked/'),
                 src,
             ];
@@ -40,8 +42,10 @@ function scrapePhotos(html, type) {
     return photos;
 }
 
-async function getPhotos(entryId, site, page = 1, type = 'highres') {
-    const albumUrl = `https://www.julesjordan.com/trial/gallery.php?id=${entryId}&type=${type}&page=${page}`;
+async function getPhotosLegacy(entryId, site, type = 'highres', page = 1) {
+    const albumUrl = `${site.url}/trial/gallery.php?id=${entryId}&type=${type}&page=${page}`;
+
+    console.warn(`Jules Jordan is using legacy photo scraper for ${albumUrl} (page ${page})`);
 
     const html = await fetchPhotos(albumUrl);
     const $ = cheerio.load(html, { normalizeWhitespace: true });
@@ -65,12 +69,48 @@ async function getPhotos(entryId, site, page = 1, type = 'highres') {
 
     if (allPhotos.length === 0 && type === 'highres') {
         // photos not available, try for screencaps instead
-        return getPhotos(entryId, site, 1, 'caps');
+        return getPhotosLegacy(entryId, site, 'caps', 1);
     }
 
     return allPhotos;
 }
 
+async function getPhotos(entryId, site, type = 'highres', page = 1) {
+    const albumUrl = `${site.url}/trial/gallery.php?id=${entryId}&type=${type}&page=${page}`;
+
+    const res = await bhttp.get(albumUrl);
+    const html = res.body.toString();
+
+    const sourceLines = html.split(/\n/).filter(line => line.match(/ptx\["\w+"\]/));
+    const sources = sourceLines.reduce((acc, sourceLine) => {
+        const quality = sourceLine.match(/\["\w+"\]/)[0].slice(2, -2);
+        const source = sourceLine.slice(sourceLine.indexOf('/trial'), sourceLine.indexOf('.jpg') + 4);
+
+        if (!source) return acc;
+        if (!acc[quality]) acc[quality] = [];
+
+        acc[quality].push(`${site.url}${source}`);
+
+        return acc;
+    }, {});
+
+    if (type === 'highres') {
+        if (sources['1600'] && sources['1600'].length > 0) return sources['1600'];
+        if (sources['1280'] && sources['1280'].length > 0) return sources['1280'];
+        if (sources['1024'] && sources['1024'].length > 0) return sources['1024'];
+        if (sources.Thumbs && sources.Thumbs.length > 0) return sources.Thumbs;
+
+        // no photos available, try for screencaps instead
+        return getPhotos(entryId, site, 'caps', 1);
+    }
+
+    if (sources.jpg && sources.jpg.length > 0) return sources.jpg;
+    if (sources['Video Cap Thumbs'] && sources['Video Cap Thumbs'].length > 0) return sources['Video Cap Thumbs'];
+
+    // no screencaps available either, try legacy scraper just in case
+    return getPhotosLegacy(entryId, site, 'highres', 1);
+}
+
 function scrapeLatest(html, site) {
     const $ = cheerio.load(html, { normalizeWhitespace: true });
     const scenesElements = $('.update_details').toArray();
@@ -171,9 +211,24 @@ async function scrapeScene(html, url, site) {
 
     release.title = $('.title_bar_hilite').text().trim();
     [release.entryId] = $('.suggest_tags a').attr('href').match(/\d+/);
-    release.date = moment
-        .utc($('.update_date').text(), 'MM/DD/YYYY')
-        .toDate();
+
+    const dateElement = $('.update_date').text().trim();
+    const dateComment = $('*')
+        .contents()
+        .toArray()
+        .find(({ type, data }) => type === 'comment' && data.match('Date OFF'));
+
+    if (dateElement) {
+        release.date = moment
+            .utc($('.update_date').text(), 'MM/DD/YYYY')
+            .toDate();
+    }
+
+    if (dateComment) {
+        release.date = moment
+            .utc(dateComment.nodeValue.match(/\d{2}\/\d{2}\/\d{4}/), 'MM/DD/YYYY')
+            .toDate();
+    }
 
     release.description = $('.update_description').text().trim();
 
@@ -190,10 +245,12 @@ async function scrapeScene(html, url, site) {
 
     const trailerLine = infoLines.find(line => line.match('movie["Trailer_720"]'));
 
-    release.trailer = {
-        src: trailerLine.slice(trailerLine.indexOf('path:"') + 6, trailerLine.indexOf('",movie')),
-        quality: 720,
-    };
+    if (site.slug !== 'manuelferrara') {
+        release.trailer = {
+            src: trailerLine.slice(trailerLine.indexOf('path:"') + 6, trailerLine.indexOf('",movie')),
+            quality: 720,
+        };
+    }
 
     release.photos = await getPhotos(release.entryId, site);