From 9d9eda29be547ad294d8ba99546fc43d5a800610 Mon Sep 17 00:00:00 2001
From: Niels Simenon <niels.simenon@gmail.com>
Date: Sun, 9 Feb 2020 03:09:06 +0100
Subject: [PATCH] Added scene count to actor inspect. Preferring network slug
 over data brand for scene URLs in MindGeek scraper, since milehighmedia.com's
 brand is milehigh, resulting in milehigh.com.

---
 src/actors.js            |  1 +
 src/scrape-releases.js   |  2 +-
 src/scrapers/mindgeek.js | 12 ++++++------
 src/utils/posters.js     |  5 +++--
 4 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/src/actors.js b/src/actors.js
index c5024b5a..8fc00bcf 100644
--- a/src/actors.js
+++ b/src/actors.js
@@ -387,6 +387,7 @@ async function scrapeActors(actorNames) {
 
             if (argv.inspect) {
                 console.log(profile);
+                logger.info(`Found ${profile.releases.length} releases for ${actorName}`);
             }
 
             if (profile === null) {
diff --git a/src/scrape-releases.js b/src/scrape-releases.js
index cc19a8b8..4f0712b0 100644
--- a/src/scrape-releases.js
+++ b/src/scrape-releases.js
@@ -39,7 +39,7 @@ async function scrapeRelease(source, basicRelease = null, type = 'scene') {
     const site = await findSite(url, release);
 
     if (!site) {
-        throw new Error('Could not find site in database');
+        throw new Error(`Could not find site ${url} in database`);
     }
 
     const scraper = scrapers.releases[site.slug] || scrapers.releases[site.network.slug];
diff --git a/src/scrapers/mindgeek.js b/src/scrapers/mindgeek.js
index 4c40a11d..5cfa4e77 100644
--- a/src/scrapers/mindgeek.js
+++ b/src/scrapers/mindgeek.js
@@ -73,7 +73,7 @@ async function scrapeLatest(items, site) {
     return latestReleases.filter(Boolean);
 }
 
-function scrapeScene(data, url, _site) {
+function scrapeScene(data, url, _site, networkName) {
     const release = {};
 
     const { id: entryId, title, description } = data;
@@ -100,7 +100,7 @@ function scrapeScene(data, url, _site) {
     const siteName = data.collections[0]?.name || data.brand;
     release.channel = siteName.replace(/\s+/g, '').toLowerCase();
 
-    release.url = url || `https://www.${data.brand}.com/scene/${entryId}/`;
+    release.url = url || `https://www.${networkName || data.brand}.com/scene/${entryId}/`;
 
     return release;
 }
@@ -139,7 +139,7 @@ async function getSession(url) {
     return { session, instanceToken };
 }
 
-function scrapeProfile(data, html, releases = []) {
+function scrapeProfile(data, html, releases = [], networkName) {
     const { qa, qd } = ex(html);
 
     const profile = {
@@ -170,7 +170,7 @@ function scrapeProfile(data, html, releases = []) {
     const birthdate = qa('li').find(el => /Date of Birth/.test(el.textContent));
     if (birthdate) profile.birthdate = qd(birthdate, 'span', 'MMMM Do, YYYY');
 
-    profile.releases = releases.map(release => scrapeScene(release));
+    profile.releases = releases.map(release => scrapeScene(release, null, null, networkName));
 
     return profile;
 }
@@ -247,11 +247,11 @@ async function fetchProfile(actorName, networkName, actorPath = 'model') {
             ]);
 
             if (actorRes.statusCode === 200 && actorReleasesRes.statusCode === 200 && actorReleasesRes.body.result) {
-                return scrapeProfile(actorData, actorRes.body.toString(), actorReleasesRes.body.result);
+                return scrapeProfile(actorData, actorRes.body.toString(), actorReleasesRes.body.result, networkName);
             }
 
             if (actorRes.statusCode === 200) {
-                return scrapeProfile(actorData, actorRes.body.toString());
+                return scrapeProfile(actorData, actorRes.body.toString(), null, networkName);
             }
         }
     }
diff --git a/src/utils/posters.js b/src/utils/posters.js
index eefe9508..8f44284c 100644
--- a/src/utils/posters.js
+++ b/src/utils/posters.js
@@ -3,13 +3,14 @@
 const config = require('config');
 const path = require('path');
 const fs = require('fs-extra');
+const moment = require('moment');
 
 const argv = require('../argv');
 const knex = require('../knex');
 
 async function init() {
     const posters = await knex('actors')
-        .select('actors.name as actor_name', 'releases.title', 'media.path', 'sites.name as site_name', 'networks.name as network_name')
+        .select('actors.name as actor_name', 'releases.title', 'releases.date', 'media.path', 'sites.name as site_name', 'networks.name as network_name')
         .whereIn('actors.name', argv.actors)
         .join('releases_actors', 'releases_actors.actor_id', 'actors.id')
         .join('releases', 'releases_actors.release_id', 'releases.id')
@@ -20,7 +21,7 @@ async function init() {
 
     await Promise.all(posters.map(async (poster) => {
         const source = path.join(config.media.path, poster.path);
-        const target = path.join(config.media.path, 'posters', `${poster.actor_name} - ${poster.network_name}: ${poster.site_name} - ${poster.title.replace(/[/.]/g, '_')}.jpeg`);
+        const target = path.join(config.media.path, 'posters', `${poster.actor_name} - ${poster.network_name}: ${poster.site_name} - ${poster.title.replace(/[/.]/g, '_')} (${moment.utc(poster.date).format('YYYY-MM-DD')}).jpeg`);
 
         const file = await fs.readFile(source);
         await fs.writeFile(target, file);