Refactored Bang! scraper, added My Stepdaughters Friend.

package-lock.json

@@ -78,7 +78,7 @@
                 "tunnel": "0.0.6",
                 "ua-parser-js": "^1.0.32",
                 "undici": "^4.13.0",
-                "unprint": "^0.9.1",
+                "unprint": "^0.9.3",
                 "url-pattern": "^1.0.3",
                 "v-tooltip": "^2.0.3",
                 "video.js": "^7.11.4",
@@ -17004,9 +17004,9 @@
             }
         },
         "node_modules/unprint": {
-            "version": "0.9.1",
+            "version": "0.9.3",
-            "resolved": "https://registry.npmjs.org/unprint/-/unprint-0.9.1.tgz",
+            "resolved": "https://registry.npmjs.org/unprint/-/unprint-0.9.3.tgz",
-            "integrity": "sha512-TEdPfly6qOST3Vessa9gNFFkJsSsdWe04k0FCU5XuvdpCSb8eVRrAvLouuyJI/GkIhrn6ZHc9VgX/gRW/R5UcQ==",
+            "integrity": "sha512-ujDlQL0yeVVd6V+kN5uURG/6F9jUblF0VWMOcpI9u3ZjsWp2tC4mQy0/kK4epU8QhkEFPE9uZ0pAMKORzEdp5g==",
             "dependencies": {
                 "axios": "^0.27.2",
                 "bottleneck": "^2.19.5",
@@ -31449,9 +31449,9 @@
             "integrity": "sha1-sr9O6FFKrmFltIF4KdIbLvSZBOw="
         },
         "unprint": {
-            "version": "0.9.1",
+            "version": "0.9.3",
-            "resolved": "https://registry.npmjs.org/unprint/-/unprint-0.9.1.tgz",
+            "resolved": "https://registry.npmjs.org/unprint/-/unprint-0.9.3.tgz",
-            "integrity": "sha512-TEdPfly6qOST3Vessa9gNFFkJsSsdWe04k0FCU5XuvdpCSb8eVRrAvLouuyJI/GkIhrn6ZHc9VgX/gRW/R5UcQ==",
+            "integrity": "sha512-ujDlQL0yeVVd6V+kN5uURG/6F9jUblF0VWMOcpI9u3ZjsWp2tC4mQy0/kK4epU8QhkEFPE9uZ0pAMKORzEdp5g==",
             "requires": {
                 "axios": "^0.27.2",
                 "bottleneck": "^2.19.5",

package.json

@@ -137,7 +137,7 @@
         "tunnel": "0.0.6",
         "ua-parser-js": "^1.0.32",
         "undici": "^4.13.0",
-        "unprint": "^0.9.1",
+        "unprint": "^0.9.3",
         "url-pattern": "^1.0.3",
         "v-tooltip": "^2.0.3",
         "video.js": "^7.11.4",

seeds/02_sites.js

@@ -1020,6 +1020,13 @@ const sites = [
 		parameters: { siteId: 6305 },
 		parent: 'bang',
 	},
+	{
+		name: 'My Stepdaughter\'s Friend',
+		slug: 'mystepdaughtersfriend',
+		url: 'https://www.bang.com/videos?in=My%20Stepdaughter%27s%20Friend',
+		parameters: { siteId: 7072 },
+		parent: 'bang',
+	},
 	// BANGBROS
 	{
 		name: 'Ass Parade',

src/scrapers/bang.js

@@ -51,13 +51,15 @@ function scrapeAll(scenes, entity) {
 	return scenes.map(({ query }) => {
 		const release = {};
 
-		release.url = query.url('.video_preview_container > a', { origin: entity.url });
+		release.url = query.url('a', { origin: entity.url });
-		release.entryId = query.attribute(null, 'data-video-id') || decodeId(new URL(release.url).pathname.match(/\/video\/([\w-]+)\//)?.[1]);
+		release.entryId = query.dataset('a', 'videopreview-id-value') || decodeId(new URL(release.url).pathname.match(/\/video\/([\w-]+)\//)?.[1]);
 
-		release.title = query.content('.video_preview_container >a > span.block');
+		release.title = query.content('a > span.block');
-		release.date = query.date('.videoInfo .statistics span', 'MMM DD, YYYY');
+		release.date = query.date('a + div', 'MMM DD, YYYY');
 
-		release.actors = query.elements('.videoInfo a[href*="/pornstar"]').map((el) => ({
+		release.duration = query.duration('[data-videopreview-target="duration"]', { attribute: 'data-content' });
+
+		release.actors = query.elements('a + div a[href*="/pornstar"]').map((el) => ({
 			name: unprint.query.content(el),
 			url: unprint.query.url(el, null, { origin: 'https://www.bang.com' }),
 		}));
@@ -72,7 +74,16 @@ function scrapeAll(scenes, entity) {
 			];
 		}
 
-		release.teaser = query.video();
+		const videoData = query.json('a', { attribute: 'data-videopreview-sources-value' });
+
+		if (videoData) {
+			release.teaser = [
+				videoData.mp4_large,
+				videoData.webm_large,
+				videoData.mp4,
+				videoData.webm,
+			];
+		}
 
 		return release;
 	});
@@ -80,21 +91,21 @@ function scrapeAll(scenes, entity) {
 
 async function scrapeScene({ query }, { url, entity }) {
 	const release = {};
-	const data = query.json('script[type="application/ld+json"]');
+	const data = query.json('//script[contains(text(), "VideoObject")]');
 
 	release.entryId = data?.['@id'] || decodeId(new URL(url).pathname.match(/\/video\/([\w-]+)\//)?.[1]);
 
-	release.title = data?.name || query.content('.video-heading');
+	release.title = data?.name || query.content('.video-container + div h1');
-	release.description = data?.description || query.content('.expanded p.clear-both');
+	release.description = data?.description || query.content('//div[contains(@class, "actions")]/preceding-sibling::p');
 
 	release.date = unprint.extractDate(data?.datePublished, 'YYYY-MM-DD') || query.date('//p[contains(text(), "Date:")]', 'MMM DD, YYYY');
 	release.duration = unprint.extractTimestamp(data?.duration) || query.duration('//p[contains(text(), "Playtime:")]//span');
 
-	if (data?.actors) {
+	if (data?.actor) {
 		release.actors = data.actor.map((actor) => ({
 			name: actor.name,
 			url: actor.url,
-			avatar: getAvatarFallback(query.img(`.video-actors img[alt="${actor.name}"]`)),
+			avatar: getAvatarFallback(query.img(`a[href*="/pornstar"] img[alt="${actor.name}"]`)),
 		}));
 	} else {
 		release.actors = query.elements('//div[contains(@class, "video-actors")]//a[img|picture]').map((element) => ({
@@ -104,27 +115,35 @@ async function scrapeScene({ query }, { url, entity }) {
 		}));
 	}
 
-	release.tags = query.contents('.expanded .genres');
+	release.tags = query.contents('.actions .genres');
 
-	release.poster = data?.thumbnailUrl || data?.contentUrl || query.attribute('meta[name*="og:image"]', 'content');
+	const videoData = query.json('.video-container [data-videopreview-sources-value]', { attribute: 'data-videopreview-sources-value' });
-	release.teaser = query.video('video[data-videocontainer-target] source');
 
-	release.photos = JSON.parse(query.attribute('[data-video-gallery-photos-value]', 'data-video-gallery-photos-value'));
+	release.poster = data?.thumbnailUrl || query.attribute('meta[property="og:image"]', 'content');
-	release.photoCount = query.number('[data-video-gallery-count-value]', { attribute: 'data-video-gallery-count-value' });
+	release.teaser = (videoData && [
+			videoData.mp4_large,
+			videoData.webm_large,
+			videoData.mp4,
+			videoData.webm,
+		])
+		|| data?.contentUrl
+		|| query.attribute('meta[property="og:video"]')
+		|| query.video('video[data-videocontainer-target] source');
 
-	const channelName = query.content('.expanded a[href*="?in="]')?.trim();
+	release.photos = query.sourceSets('.photo-set img');
+	release.photoCount = query.number('//h2[contains(text(), "Photos")]/following-sibling::span');
+
+	const channelName = query.content('.video-container + div a[href*="?in="]')?.trim();
 
 	if (channelName) {
 		release.channel = entity.children?.find((channel) => new RegExp(channel.name, 'i').test(channelName) || slugify(channelName) === channel.slug)?.slug;
 	}
 
-	console.log(release);
-
 	return release;
 }
 
 async function fetchActorScenes(element, url, entity, page = 1, acc = []) {
-	const scenes = scrapeAll(unprint.initAll(element, '.search-grid li'), entity);
+	const scenes = scrapeAll(unprint.initAll(element, '.video_container'), entity);
 
 	if (scenes.length) {
 		const nextPageRes = await unprint.post(url, { page: page + 1 });
@@ -141,7 +160,7 @@ async function scrapeProfile({ query, element }, url, entity, include) {
 	const profile = { url };
 
 	profile.dateOfBirth = query.date('//text()[contains(., "Born")]/following-sibling::span[contains(@class, "font-bold")][1]', 'MMMM D, YYYY');
-	profile.birthPlace = query.content('//text()[contains(., "in")]/following-sibling::span[contains(@class, "font-bold")][1]');
+	profile.birthPlace = query.content('//text()[contains(., "From")]/following-sibling::span[contains(@class, "font-bold")][1]');
 
 	profile.ethnicity = query.content('//text()[contains(., "Ethnicity")]/following-sibling::span[contains(@class, "font-bold")][1]');
 
@@ -158,8 +177,8 @@ async function scrapeProfile({ query, element }, url, entity, include) {
 }
 
 async function fetchLatest(channel, page = 1) {
-	const url = `${channel.url}&page=${page}`;
+	const url = `${channel.url}&by=date.desc&page=${page}`;
-	const res = await unprint.get(url, { selectAll: '.search-grid li' });
+	const res = await unprint.get(url, { selectAll: '.video_container' });
 
 	if (res.ok) {
 		return scrapeAll(res.context, channel);
@@ -168,8 +187,8 @@ async function fetchLatest(channel, page = 1) {
 	return res.status;
 }
 async function fetchUpcoming(channel) {
-	const url = `${channel.url}&early-access=true`;
+	const url = `${channel.url}&by=date.desc&early-access=true`;
-	const res = await unprint.get(url, { selectAll: '.search-grid li' });
+	const res = await unprint.get(url, { selectAll: '.video_container' });
 
 	if (res.ok) {
 		return scrapeAll(res.context, channel);

src/scrapers/newsensations.js

@@ -76,6 +76,8 @@ function scrapeSceneBlock({ query }) {
 	release.poster = query.img('#trailer_thumb img[src*=content]');
 	release.trailer = query.video('#trailerVideo source');
 
+	release.photoCount = query.number('.sceneDateP', { match: /(\d+)\s+(photo|pic)/i, matchIndex: 1 });
+
 	return release;
 }