From 1163b010fb513023bda9c96f983638382d414698 Mon Sep 17 00:00:00 2001
From: DebaucheryLibrarian <moonloop.adult@protonmail.com>
Date: Thu, 17 Oct 2024 23:50:55 +0200
Subject: [PATCH] Added actor page deep scrape for the few Sperm Mania scenes
 not on the homepage.

---
 src/deep.js                |  2 +-
 src/scrapers/snowvalley.js | 38 +++++++++++++++++++++++++++-----------
 2 files changed, 28 insertions(+), 12 deletions(-)

diff --git a/src/deep.js b/src/deep.js
index e1d75b17..6dd7ae02 100755
--- a/src/deep.js
+++ b/src/deep.js
@@ -185,7 +185,7 @@ async function scrapeRelease(baseRelease, entitiesByHostname, type = 'scene') {
 
 		if (!scrapedRelease || typeof scrapedRelease !== 'object' || Array.isArray(scrapedRelease)) {
 			// scraper is unable to fetch the releases and returned a HTTP code or null
-			throw new Error(`Scraper returned '${scrapedRelease}' when fetching latest from '${entity.name}' (${entity.parent?.name})`);
+			throw new Error(`Scraper returned '${scrapedRelease}' when deep fetching (${entity.name}, ${entity.parent?.name}) ${baseRelease.url || baseRelease.path}`);
 		}
 
 		// object-merge-advance will use null as explicit false on hard merged keys, even when null as explicit falls is disabled
diff --git a/src/scrapers/snowvalley.js b/src/scrapers/snowvalley.js
index 1158c6ea..a6743056 100755
--- a/src/scrapers/snowvalley.js
+++ b/src/scrapers/snowvalley.js
@@ -15,8 +15,18 @@ const tagsMap = {
 	'pussy bukkake': ['cum-on-pussy'],
 };
 
-function entryIdFromMedia(release) {
-	return [release.poster, release.trailer, ...(release.photos || [])].flat().filter(Boolean)[0]?.match(/(?:(?:preview)|(?:samples)|(?:tour))\/(.*)\//)?.[1].toLowerCase();
+function entryIdFromMedia(release, toLowercase = true) {
+	const originalEntryId = [release.poster, release.trailer, ...(release.photos || [])].flat().filter(Boolean)[0]?.match(/(?:(?:preview)|(?:samples)|(?:tour))\/(.*)\//)?.[1];
+
+	if (!originalEntryId) {
+		return null;
+	}
+
+	if (toLowercase) {
+		return originalEntryId.toLowerCase();
+	}
+
+	return originalEntryId;
 }
 
 function scrapeAll(scenes, tilesByEntryId, channel) {
@@ -63,6 +73,9 @@ function scrapeAll(scenes, tilesByEntryId, channel) {
 					release[key] = value;
 				}
 			});
+		} else {
+			// most tiles are on the front page, but not all, deep scrape actor's page
+			release.path = release.actors[0]?.url;
 		}
 
 		return release;
@@ -94,9 +107,6 @@ function scrapeAllTiles(tiles, channel) {
 		const release = {};
 		const sceneString = query.content();
 
-		const originalEntryId = query.attribute('.scene-hover', 'data-path');
-		release.entryId = originalEntryId?.toLowerCase();
-
 		release.title = query.content('.scene-title');
 
 		release.date = query.date('.scene-date, .sDate', 'YYYY-MM-DD');
@@ -106,7 +116,7 @@ function scrapeAllTiles(tiles, channel) {
 			name: unprint.query.content(actorEl),
 			url: channel.slug === 'fellatiojapan'
 				? `${channel.url}/en/girl/${unprint.query.url(actorEl, null)}`
-				: unprint.query.element(actorEl, null, { origin: channel.url }),
+				: unprint.query.url(actorEl, null, { origin: channel.url }),
 		}));
 
 		release.tags = [...query.contents('.data a[href*="/tag"]'), ...(tagsMap[query.content('.scene-type')?.toLowerCase()] || [])].filter(Boolean);
@@ -124,6 +134,10 @@ function scrapeAllTiles(tiles, channel) {
 			];
 		}
 
+		const originalEntryId = query.attribute('.scene-hover', 'data-path') || entryIdFromMedia(release, false);
+
+		release.entryId = originalEntryId?.toLowerCase();
+
 		release.teaser = originalEntryId && `https://img.${channel.slug}.com/preview/${originalEntryId}/hover.mp4`;
 
 		release.photoCount = Number(sceneString.match(/(\d+) photos/)?.[1]) || null;
@@ -699,20 +713,21 @@ function scrapeSceneCospuri({ query }, { url, entity }) {
 	return release;
 }
 
-// Fellatio Japan
-async function fetchSceneFellatio(url, channel, baseRelease) {
+// Sperm Mania, Fellatio Japan
+async function fetchScene(url, channel, baseRelease) {
 	if (!baseRelease.entryId || !baseRelease.path) {
 		return null;
 	}
 
 	// no dedicated scene page, but there are dates on actor page; use that as 'deep' scrape
 	// can't use front page like on Sperm Mania because dates are missing
-	const res = await unprint.get(baseRelease.path, { selectAll: '.scene-obj' });
+	const res = await unprint.get(baseRelease.path, { selectAll: '.scene, .scene-obj' });
 
 	if (res.ok) {
 		const tiles = scrapeAllTiles(res.context, channel);
+		const sceneTile = tiles.find((tile) => tile.entryId === baseRelease.entryId) || null;
 
-		return tiles.find((tile) => tile.entryId === baseRelease.entryId) || null;
+		return sceneTile;
 	}
 
 	return res.status;
@@ -830,6 +845,7 @@ async function fetchProfile({ slug, url: actorUrl }, { entity, parameters }) {
 module.exports = {
 	fetchLatest,
 	fetchProfile,
+	fetchScene,
 	cospuri: {
 		fetchLatest: fetchLatestCospuri,
 		scrapeScene: scrapeSceneCospuri,
@@ -837,7 +853,7 @@ module.exports = {
 	},
 	fellatio: {
 		fetchLatest: fetchLatestFellatio,
-		fetchScene: fetchSceneFellatio,
+		fetchScene,
 		fetchProfile,
 	},
 	handjob: {