Refactored Bang! scraper to match new website, first use of unprint.

README.md

@@ -7,7 +7,7 @@ Use [nvm](https://github.com/creationix/nvm) to install NodeJS v16.8.0 or newer.
 `npm install`
 
 ### Set up database
-Install PostgreSQL, make sure password authentication is enabled (scram-sha-256) and create a database with a privileged user.
+Install PostgreSQL, make sure password authentication is enabled (scram-sha-256). Create a database with a fully privileged user, and a visitor user without privileges (they will be provided by the migration).
 
 ### Configuration
 Do not modify `config/default.js`, but instead create a copy at `config/local.js` containing the properties you wish to change. If you have set `NODE_ENV`, copy `assets/js/config/default.js` to `assets/js/config/[environment].js`. After setting up PostgreSQL and configuring the details, run the following commands to create and populate the tables, and build the project:

config/default.js

@@ -294,13 +294,13 @@ module.exports = {
 	},
 	bypass: {
 		browser: {
-			enable: true,
+			enable: false,
 			hostnames: [ // these can run in the same browser session
 				'www.kink.com',
 			],
 		},
 		cloudflare: {
-			enable: true,
+			enable: false,
 			auto: true, // try bypass when CF challenge is detected
 			path: 'http://localhost:8191/v1',
 			sharedHostnames: [ // these can run in the same browser session

package.json

@@ -134,6 +134,7 @@
         "tough-cookie": "^4.0.0",
         "tunnel": "0.0.6",
         "undici": "^4.13.0",
+        "unprint": "^0.7.2",
         "url-pattern": "^1.0.3",
         "v-tooltip": "^2.0.3",
         "video.js": "^7.11.4",

seeds/02_sites.js

@@ -906,7 +906,7 @@ const sites = [
 	{
 		name: 'Trickery',
 		slug: 'bangtrickery',
-		url: 'https://www.bang.com/original/4800/bang-trickery',
+		url: 'https://www.bang.com/videos?in=BANG%21+Trickery',
 		parameters: { siteId: 4800 },
 		parent: 'bang',
 	},
@@ -914,23 +914,21 @@ const sites = [
 		name: 'Yngr',
 		slug: 'yngrcom',
 		alias: ['byngr'],
-		// url: 'https://www.bang.com/original/5010/bang-yngr',
-		url: 'https://yngr.com',
+		url: 'https://www.bang.com/videos?in=yngr.com',
 		parameters: { siteId: 5010 },
 		parent: 'bang',
 	},
 	{
 		name: 'Roadside XXX',
 		slug: 'bangroadsidexxx',
-		// url: 'https://www.bang.com/original/4864/roadside-xxx',
-		url: 'https://roadsidexxx.com',
+		url: 'https://www.bang.com/videos?in=Bang%21+Roadside+XXX',
 		parameters: { siteId: 4864 },
 		parent: 'bang',
 	},
 	{
 		name: 'Surprise',
 		slug: 'bangsurprise',
-		url: 'https://www.bang.com/original/5000/bang-surprise',
+		url: 'https://www.bang.com/videos?in=BANG%21+Surprise',
 		parameters: { siteId: 5000 },
 		parent: 'bang',
 	},
@@ -938,37 +936,35 @@ const sites = [
 		name: 'Real Teens',
 		slug: 'bangrealteens',
 		alias: ['brealteens'],
-		url: 'https://www.bang.com/original/3366/bang-real-teens',
+		url: 'https://www.bang.com/videos?in=BANG%21+Real+Teens',
 		parameters: { siteId: 3366 },
 		parent: 'bang',
 	},
 	{
 		name: 'FCK.news',
 		slug: 'bangfakenews',
-		// url: 'https://www.bang.com/original/4998/bang-fckNews',
-		url: 'https://fck.news',
+		url: 'https://www.bang.com/videos?in=Bang%21+Fake+news',
 		parameters: { siteId: 4998 },
 		parent: 'bang',
 	},
 	{
 		name: 'Pretty & Raw',
 		slug: 'prettyandraw',
-		// url: 'https://www.bang.com/original/4792/bang-pretty-and-raw',
-		url: 'https://prettyandraw.com',
+		url: 'https://www.bang.com/videos?in=Pretty+%26+Raw',
 		parameters: { siteId: 4792 },
 		parent: 'bang',
 	},
 	{
 		name: 'Japan',
 		slug: 'bangjapan',
-		url: 'https://www.bang.com/original/3079/bang-japan',
+		url: 'https://www.bang.com/videos?in=BANG%21+Japan',
 		parameters: { siteId: 3079, ignore: true },
 		parent: 'bang',
 	},
 	{
 		name: 'Rammed',
 		slug: 'bangrammed',
-		url: 'https://www.bang.com/original/4836/bang-rammed',
+		url: 'https://www.bang.com/videos?in=BANG%21+Rammed',
 		parameters: { siteId: 4836 },
 		parent: 'bang',
 	},
@@ -976,14 +972,14 @@ const sites = [
 		name: 'Glamkore',
 		slug: 'bangglamkore',
 		alias: ['bglamkore'],
-		url: 'https://www.bang.com/original/4586/bang-glamkore',
+		url: 'https://www.bang.com/videos?in=BANG%21+Glamkore',
 		parameters: { siteId: 4586 },
 		parent: 'bang',
 	},
 	{
 		name: 'Screw The Cops',
 		slug: 'screwthecops',
-		url: 'https://www.bang.com/original/4710/bang-screw-cops',
+		url: 'https://www.bang.com/videos?in=Screw+the+Cops',
 		parameters: { siteId: 4710 },
 		parent: 'bang',
 	},
@@ -991,7 +987,7 @@ const sites = [
 		name: 'Real MILFs',
 		slug: 'bangrealmilfs',
 		alias: ['brealmilfs'],
-		url: 'https://www.bang.com/original/4448/bang-real-milfs',
+		url: 'https://www.bang.com/videos?in=BANG%21+Real+Milfs',
 		parameters: { siteId: 4448 },
 		parent: 'bang',
 	},
@@ -999,7 +995,7 @@ const sites = [
 		name: 'Confessions',
 		slug: 'bangconfessions',
 		alias: ['bconfessions'],
-		url: 'https://www.bang.com/original/4308/bang-confessions',
+		url: 'https://www.bang.com/videos?in=BANG%21+Confessions',
 		parameters: { siteId: 4308 },
 		parent: 'bang',
 	},
@@ -1007,14 +1003,14 @@ const sites = [
 		name: 'Casting',
 		slug: 'bangcasting',
 		alias: ['bcasting'],
-		url: 'https://www.bang.com/original/3261/bang-casting',
+		url: 'https://www.bang.com/videos?in=BANG%21+Casting',
 		parameters: { siteId: 3261 },
 		parent: 'bang',
 	},
 	{
 		name: 'Bang! Podcast',
 		slug: 'bangpodcast',
-		url: 'https://www.bang.com/videos?in=bang!%20podcast',
+		url: 'https://www.bang.com/videos?in=bang%21+podcast',
 		parameters: { siteId: 6305 },
 		parent: 'bang',
 	},
@@ -11518,6 +11514,15 @@ const sites = [
 			movie: 'https://www.addicted2girls.com/en/dvd',
 		},
 	},
+	{
+		slug: '3rddegreefilms',
+		name: '3rd Degree Films',
+		url: 'https://www.3rddegreefilms.com',
+		parent: 'zerotolerance',
+		parameters: {
+			movie: 'https://www.genderxfilms.com/en/dvd',
+		},
+	},
 	{
 		slug: 'genderxfilms',
 		name: 'GenderXFilms',
@@ -11525,7 +11530,8 @@ const sites = [
 		tags: ['transsexual'],
 		parent: 'zerotolerance',
 		parameters: {
-			movie: 'https://www.genderxfilms.com/en/dvd',
+			scene: 'https://www.3rddegreefilms.com/en/video/3rddegreefilms',
+			movie: 'https://www.3rddegreefilms.com/en/movie',
 		},
 	},
 	{

src/app.js

@@ -2,6 +2,7 @@
 
 const config = require('config');
 const util = require('util');
+const unprint = require('unprint');
 // const log = require('why-is-node-running');
 const Inspector = require('inspector-api');
 const fs = require('fs').promises;
@@ -25,6 +26,13 @@ const getFileEntries = require('./utils/file-entries');
 const inspector = new Inspector();
 let done = false;
 
+unprint.options({
+	timeout: 5000,
+	headers: {
+		'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36',
+	},
+});
+
 /*
 function logActive() {
 	setTimeout(() => {

src/deep.js

@@ -2,6 +2,7 @@
 
 const util = require('util');
 const Promise = require('bluebird');
+const unprint = require('unprint');
 const { mergeAdvanced: merge } = require('object-merge-advanced');
 
 const argv = require('./argv');
@@ -54,12 +55,33 @@ function toBaseReleases(baseReleasesOrUrls, entity = null) {
 		.filter(Boolean);
 }
 
+async function fetchUnprintScene(scraper, url, entity, baseRelease, options, type) {
+	const res = await unprint.get(url, {
+		rejectUnauthorized: false,
+	});
+
+	if (res.ok) {
+		return scraper[type === 'movie' ? 'scrapeMovie' : 'scrapeScene'](res.context, {
+			url,
+			entity,
+			baseRelease,
+			headers: res.headers,
+		}, options);
+	}
+
+	return res.status;
+}
+
 async function fetchScene(scraper, url, entity, baseRelease, options, type = 'scene') {
 	if ((type === 'scene' && scraper.fetchScene) || (type === 'movie' && scraper.fetchMovie)) {
 		return scraper[type === 'movie' ? 'fetchMovie' : 'fetchScene'](baseRelease.url, entity, baseRelease, options, null);
 	}
 
 	if ((type === 'scene' && scraper.scrapeScene) || (type === 'movie' && scraper.scrapeMovie)) {
+		if (scraper.useUnprint) {
+			return fetchUnprintScene(scraper, url, entity, baseRelease, options, type);
+		}
+
 		const session = qu.session();
 
 		const res = await qu.get(url, null, null, {

src/scrapers/bang-legacy.js

@@ -0,0 +1,429 @@
+'use strict';
+
+const http = require('../utils/http');
+const qu = require('../utils/qu');
+const { extractDate } = require('../utils/qu');
+const { inchesToCm } = require('../utils/convert');
+const slugify = require('../utils/slugify');
+const capitalize = require('../utils/capitalize');
+
+const clusterId = '617fb597b659459bafe6472470d9073a';
+const authKey = 'YmFuZy1yZWFkOktqVDN0RzJacmQ1TFNRazI=';
+
+const genderMap = {
+	M: 'male',
+	F: 'female',
+};
+
+function getScreenUrl(item, scene) {
+	if (!scene.dvd?.id || !item?.screenId) {
+		return null;
+	}
+
+	return `https://i.bang.com/screenshots/${scene.dvd.id}/${scene.type}/${scene.order}/${item.screenId}.jpg`;
+}
+
+function encodeId(id) {
+	return Buffer
+		.from(id, 'hex')
+		.toString('base64')
+		.replace(/\+/g, '-')
+		.replace(/\//g, '_')
+		.replace(/=/g, ',');
+}
+
+function decodeId(id) {
+	const restoredId = id
+		.replace(/-/g, '+')
+		.replace(/_/g, '/')
+		.replace(/,/g, '=');
+
+	return Buffer
+		.from(restoredId, 'base64')
+		.toString('hex');
+}
+
+async function fetchPhotos(scene) {
+	const photoPaths = Array.from({ length: scene.photos }, (value, index) => `/${scene.dvd.id}/${scene.identifier}/final/${String(index + 1).padStart(6, '0')}.jpg`);
+
+	const res = await http.post('https://www.bang.com/sign-images', {
+		images: photoPaths,
+	}, {
+		encodeJSON: false,
+	});
+
+	if (res.ok && res.body.images) {
+		return res.body.images.map((image) => qu.prefixUrl(image, 'https://photos.bang.com'));
+	}
+
+	return null;
+}
+
+async function scrapeScene(scene, entity, options) {
+	const release = {
+		entryId: scene.id,
+		title: scene.name || (scene.dvd?.name && scene.type === 'bonus' && capitalize(`${scene.dvd.name} - Bonus Scene ${scene.order || 1}`)) || null,
+		description: scene.description,
+		tags: scene.genres.concat(scene.actions).map((genre) => genre.name),
+		duration: scene.duration,
+	};
+
+	const slug = slugify(release.title);
+	release.url = `https://www.bang.com/video/${encodeId(release.entryId)}/${slug}`;
+
+	const date = new Date(scene.releaseDate);
+	release.date = new Date(Date.UTC(date.getUTCFullYear(), date.getUTCMonth(), date.getUTCDate()));
+
+	release.actors = scene.actors.map((actor) => ({ name: actor.name, gender: genderMap[actor.gender] }));
+
+	if (scene.is4k) release.tags.push('4k');
+	if (scene.gay) release.tags.push('gay');
+
+	const defaultPoster = scene.screenshots.find((photo) => photo.default === true);
+	const screens = scene.screenshots.filter((photo) => photo.default === false);
+
+	const remainingScreens = defaultPoster ? screens : screens.slice(1);
+	const poster = defaultPoster || screens[0];
+
+	release.poster = getScreenUrl(poster, scene);
+	release.photos = remainingScreens.map((photo) => getScreenUrl(photo, scene));
+
+	if (options?.includePhotos) {
+		const photos = await fetchPhotos(scene);
+
+		if (photos?.length > 0) {
+			release.photos = photos;
+		}
+	}
+
+	release.teaser = `https://i.bang.com/v/${scene.dvd.id}/${scene.identifier}/preview.mp4`;
+
+	release.channel = scene.series.name
+		.replace(/[! .]/g, '')
+		.replace('&', 'and');
+
+	return release;
+}
+
+function scrapeAll(scenes, entity) {
+	return Promise.all(scenes.map(({ _source: scene }) => scrapeScene(scene, entity)));
+}
+
+async function fetchActorReleases(actor, entity) {
+	const res = await http.post(`https://${clusterId}.us-east-1.aws.found.io/videos/video/_search`, {
+		size: 50,
+		query: {
+			bool: {
+				must: [
+					{
+						match: {
+							status: 'ok',
+						},
+					},
+					{
+						nested: {
+							path: 'actors',
+							query: {
+								bool: {
+									must: [
+										{
+											match: {
+												'actors.mongoId': {
+													operator: 'AND',
+													query: actor.id,
+												},
+											},
+										},
+									],
+								},
+							},
+						},
+					},
+				],
+				must_not: [
+					{
+						match: {
+							type: 'trailer',
+						},
+					},
+				],
+			},
+		},
+		sort: [
+			{
+				releaseDate: {
+					order: 'desc',
+				},
+			},
+		],
+	}, {
+		encodeJSON: true,
+		headers: {
+			Authorization: `Basic ${authKey}`,
+		},
+	});
+
+	return scrapeAll(res.body.hits.hits, entity);
+}
+
+async function scrapeProfile(actor, entity, include) {
+	const profile = {};
+
+	profile.aliases = actor.aliases;
+	profile.dateOfBirth = extractDate(actor.birthDate);
+	profile.gender = ({ F: 'female', M: 'male' })[actor.gender];
+
+	profile.ethnicity = actor.ethnicity;
+	profile.nationality = actor.nationality;
+	profile.birthPlace = `${actor.birthCity}, ${actor.birthCountry || ''}`;
+
+	profile.hair = actor.hairColor;
+	profile.eyes = actor.eyeColor;
+
+	profile.naturalBoobs = actor.naturalBreasts;
+
+	if (actor.measurements) {
+		const { cupSize, shoulder, chest, waist, height } = actor.measurements;
+
+		if (height) profile.height = inchesToCm(height);
+		if (cupSize) profile.cup = cupSize;
+
+		// [SIC]
+		if (shoulder) profile.bust = shoulder;
+		if (chest) profile.waist = chest;
+		if (waist) profile.hip = waist;
+	}
+
+	if (actor.twitter) profile.social = [`https://www.twitter.com/${actor.twitter}`];
+	if (actor.image) profile.avatar = `https://i.bang.com/pornstars/${actor.identifier}.jpg`;
+
+	if (include.releases) {
+		profile.releases = await fetchActorReleases(actor, entity);
+	}
+
+	return profile;
+}
+
+async function fetchLatest(site, page = 1) {
+	const res = await http.post(`https://${clusterId}.us-east-1.aws.found.io/videos/video/_search`, {
+		size: 50,
+		from: (page - 1) * 50,
+		query: {
+			bool: {
+				must: [
+					{
+						match: {
+							status: 'ok',
+						},
+					},
+					{
+						range: {
+							releaseDate: {
+								lte: 'now',
+							},
+						},
+					},
+					/*
+                     * global fetch
+                    {
+                        nested: {
+                            path: 'studio',
+                            query: {
+                                bool: {
+                                    must: [
+                                        {
+                                            match: {
+                                                'studio.name': {
+                                                    operator: 'AND',
+                                                    query: 'bang! originals',
+                                                },
+                                            },
+                                        },
+                                    ],
+                                },
+                            },
+                        },
+                    },
+                    */
+					{
+						nested: {
+							path: 'series',
+							query: {
+								bool: {
+									must: [
+										{
+											match: {
+												'series.id': {
+													operator: 'AND',
+													query: site.parameters.siteId,
+												},
+											},
+										},
+									],
+								},
+							},
+						},
+					},
+				],
+				must_not: [
+					{
+						match: {
+							type: 'trailer',
+						},
+					},
+				],
+			},
+		},
+		sort: [
+			{
+				releaseDate: {
+					order: 'desc',
+				},
+			},
+		],
+	}, {
+		encodeJSON: true,
+		headers: {
+			Authorization: `Basic ${authKey}`,
+		},
+	});
+
+	return scrapeAll(res.body.hits.hits, site);
+}
+
+async function fetchUpcoming(site, page = 1) {
+	const res = await http.post(`https://${clusterId}.us-east-1.aws.found.io/videos/video/_search`, {
+		size: 50,
+		from: (page - 1) * 50,
+		query: {
+			bool: {
+				must: [
+					{
+						match: {
+							status: 'ok',
+						},
+					},
+					{
+						range: {
+							releaseDate: {
+								lte: 'now+7d',
+							},
+						},
+					},
+					{
+						nested: {
+							path: 'series',
+							query: {
+								bool: {
+									must: [
+										{
+											match: {
+												'series.id': {
+													operator: 'AND',
+													query: site.parameters.siteId,
+												},
+											},
+										},
+									],
+								},
+							},
+						},
+					},
+				],
+				must_not: [
+					{
+						match: {
+							type: 'trailer',
+						},
+					},
+				],
+			},
+		},
+		sort: [
+			{
+				releaseDate: {
+					order: 'desc',
+				},
+			},
+		],
+	}, {
+		encodeJSON: true,
+		headers: {
+			Authorization: `Basic ${authKey}`,
+		},
+	});
+
+	return scrapeAll(res.body.hits.hits, site);
+}
+
+async function fetchScene(url, entity, baseRelease, options) {
+	if (baseRelease?.entryId) {
+		// overview and deep data is the same, don't hit server unnecessarily
+		return baseRelease;
+	}
+
+	const encodedId = new URL(url).pathname.split('/')[2];
+	const entryId = decodeId(encodedId);
+
+	const res = await http.get(`https://${clusterId}.us-east-1.aws.found.io/videos/video/${entryId}`, {
+		headers: {
+			Authorization: `Basic ${authKey}`,
+		},
+	});
+
+	return scrapeScene(res.body._source, entity, options); // eslint-disable-line no-underscore-dangle
+}
+
+async function fetchProfile({ name: actorName }, context, include) {
+	const res = await http.post(`https://${clusterId}.us-east-1.aws.found.io/actors/actor/_search`, {
+		size: 5,
+		sort: [{
+			_score: {
+				order: 'desc',
+			},
+		}],
+		query: {
+			bool: {
+				must: [
+					{
+						match: {
+							name: {
+								query: actorName,
+								operator: 'and',
+							},
+						},
+					},
+					{
+						match: {
+							status: 'ok',
+						},
+					},
+				],
+			},
+		},
+	}, {
+		headers: {
+			Authorization: `Basic ${authKey}`,
+		},
+		encodeJSON: true,
+	});
+
+	if (res.ok) {
+		const actor = res.body.hits.hits.find((hit) => hit._source.name.toLowerCase() === actorName.toLowerCase());
+
+		if (actor) {
+			return scrapeProfile(actor._source, context.entity, include);
+		}
+
+		return null;
+	}
+
+	return res.status;
+}
+
+module.exports = {
+	fetchLatest,
+	fetchProfile,
+	fetchScene,
+	fetchUpcoming,
+};

src/scrapers/bang.js

@@ -1,29 +1,15 @@
 'use strict';
 
-const http = require('../utils/http');
-const qu = require('../utils/qu');
-const { extractDate } = require('../utils/qu');
-const { inchesToCm } = require('../utils/convert');
+const unprint = require('unprint');
+
 const slugify = require('../utils/slugify');
-const capitalize = require('../utils/capitalize');
 
-const clusterId = '617fb597b659459bafe6472470d9073a';
-const authKey = 'YmFuZy1yZWFkOktqVDN0RzJacmQ1TFNRazI=';
-
-const genderMap = {
-	M: 'male',
-	F: 'female',
-};
-
-function getScreenUrl(item, scene) {
-	if (!scene.dvd?.id || !item?.screenId) {
-		return null;
+/*
+function encodeId(id) {
+	if (!id) {
+		return id;
 	}
 
-	return `https://i.bang.com/screenshots/${scene.dvd.id}/${scene.type}/${scene.order}/${item.screenId}.jpg`;
-}
-
-function encodeId(id) {
 	return Buffer
 		.from(id, 'hex')
 		.toString('base64')
@@ -31,8 +17,13 @@ function encodeId(id) {
 		.replace(/\//g, '_')
 		.replace(/=/g, ',');
 }
+*/
 
 function decodeId(id) {
+	if (!id) {
+		return id;
+	}
+
 	const restoredId = id
 		.replace(/-/g, '+')
 		.replace(/_/g, '/')
@@ -43,387 +34,150 @@ function decodeId(id) {
 		.toString('hex');
 }
 
-async function fetchPhotos(scene) {
-	const photoPaths = Array.from({ length: scene.photos }, (value, index) => `/${scene.dvd.id}/${scene.identifier}/final/${String(index + 1).padStart(6, '0')}.jpg`);
+function scrapeAll(scenes, entity) {
+	return scenes.map(({ query }) => {
+		const release = {};
 
-	const res = await http.post('https://www.bang.com/sign-images', {
-		images: photoPaths,
-	}, {
-		encodeJSON: false,
+		release.url = query.url('.video_preview_container > a', { origin: entity.url });
+		release.entryId = query.attribute(null, 'data-video-id') || decodeId(new URL(release.url).pathname.match(/\/video\/([\w-]+)\//)?.[1]);
+
+		release.title = query.content('.video_preview_container >a > span.block');
+		release.date = query.date('.videoInfo .statistics span', 'MMM DD, YYYY');
+
+		release.actors = query.elements('.videoInfo a[href*="/pornstar"]').map((el) => ({
+			name: unprint.query.content(el),
+			url: unprint.query.url(el, null, { origin: 'https://www.bang.com' }),
+		}));
+
+		const poster = query.img('img[data-videopreview-target="image"]');
+		const posterUrl = new URL(poster);
+
+		if (poster) {
+			release.poster = [
+				`${posterUrl.origin}${posterUrl.pathname}`,
+				posterUrl.href,
+			];
+		}
+
+		release.teaser = query.video();
+
+		return release;
 	});
-
-	if (res.ok && res.body.images) {
-		return res.body.images.map((image) => qu.prefixUrl(image, 'https://photos.bang.com'));
-	}
-
-	return null;
 }
 
-async function scrapeScene(scene, entity, options) {
-	const release = {
-		entryId: scene.id,
-		title: scene.name || (scene.dvd?.name && scene.type === 'bonus' && capitalize(`${scene.dvd.name} - Bonus Scene ${scene.order || 1}`)) || null,
-		description: scene.description,
-		tags: scene.genres.concat(scene.actions).map((genre) => genre.name),
-		duration: scene.duration,
-	};
+async function scrapeScene({ query }, { url, entity }) {
+	const release = {};
+	const data = query.json('script[type="application/ld+json"]');
 
-	const slug = slugify(release.title);
-	release.url = `https://www.bang.com/video/${encodeId(release.entryId)}/${slug}`;
+	release.entryId = data?.['@id'] || decodeId(new URL(url).pathname.match(/\/video\/([\w-]+)\//)?.[1]);
 
-	const date = new Date(scene.releaseDate);
-	release.date = new Date(Date.UTC(date.getUTCFullYear(), date.getUTCMonth(), date.getUTCDate()));
+	release.title = data?.name || query.content('.video-heading');
+	release.description = data?.description || query.content('.expanded p.clear-both');
 
-	release.actors = scene.actors.map((actor) => ({ name: actor.name, gender: genderMap[actor.gender] }));
+	release.date = unprint.extractDate(data?.datePublished, 'YYYY-MM-DD');
+	release.duration = unprint.extractTimestamp(data?.duration) || query.duration('//p[contains(text(), "Playtime:")]//span');
 
-	if (scene.is4k) release.tags.push('4k');
-	if (scene.gay) release.tags.push('gay');
+	release.actors = data?.actor.map((actor) => ({
+		name: actor.name,
+		url: actor.url,
+	})) || query.contents('.expanded a[href*="/pornstar"]');
 
-	const defaultPoster = scene.screenshots.find((photo) => photo.default === true);
-	const screens = scene.screenshots.filter((photo) => photo.default === false);
+	release.tags = query.contents('.expanded .genres');
 
-	const remainingScreens = defaultPoster ? screens : screens.slice(1);
-	const poster = defaultPoster || screens[0];
+	release.poster = data?.thumbnailUrl || data?.contentUrl || query.attribute('meta[name*="og:image"]', 'content');
+	release.teaser = query.video('video[data-modal-target="videoImage"] source');
 
-	release.poster = getScreenUrl(poster, scene);
-	release.photos = remainingScreens.map((photo) => getScreenUrl(photo, scene));
+	release.photos = JSON.parse(query.attribute('[data-video-gallery-photos-value]', 'data-video-gallery-photos-value'));
+	release.photoCount = query.number('[data-video-gallery-count-value]', { attribute: 'data-video-gallery-count-value' });
 
-	if (options?.includePhotos) {
-		const photos = await fetchPhotos(scene);
+	const channelName = query.content('.expanded a[href*="?in="]')?.trim();
 
-		if (photos?.length > 0) {
-			release.photos = photos;
-		}
+	if (channelName) {
+		release.channel = entity.children?.find((channel) => new RegExp(channel.name, 'i').test(channelName) || slugify(channelName) === channel.slug)?.slug;
 	}
 
-	release.teaser = `https://i.bang.com/v/${scene.dvd.id}/${scene.identifier}/preview.mp4`;
-
-	release.channel = scene.series.name
-		.replace(/[! .]/g, '')
-		.replace('&', 'and');
-
 	return release;
 }
 
-function scrapeAll(scenes, entity) {
-	return Promise.all(scenes.map(({ _source: scene }) => scrapeScene(scene, entity)));
-}
+async function fetchActorScenes(element, url, entity, page = 1, acc = []) {
+	const scenes = scrapeAll(unprint.initAll(element, '.search-grid li'), entity);
 
-async function fetchActorReleases(actor, entity) {
-	const res = await http.post(`https://${clusterId}.us-east-1.aws.found.io/videos/video/_search`, {
-		size: 50,
-		query: {
-			bool: {
-				must: [
-					{
-						match: {
-							status: 'ok',
-						},
-					},
-					{
-						nested: {
-							path: 'actors',
-							query: {
-								bool: {
-									must: [
-										{
-											match: {
-												'actors.mongoId': {
-													operator: 'AND',
-													query: actor.id,
-												},
-											},
-										},
-									],
-								},
-							},
-						},
-					},
-				],
-				must_not: [
-					{
-						match: {
-							type: 'trailer',
-						},
-					},
-				],
-			},
-		},
-		sort: [
-			{
-				releaseDate: {
-					order: 'desc',
-				},
-			},
-		],
-	}, {
-		encodeJSON: true,
-		headers: {
-			Authorization: `Basic ${authKey}`,
-		},
-	});
+	if (scenes.length) {
+		const nextPageRes = await unprint.post(url, { page: page + 1 });
 
-	return scrapeAll(res.body.hits.hits, entity);
-}
-
-async function scrapeProfile(actor, entity, include) {
-	const profile = {};
-
-	profile.aliases = actor.aliases;
-	profile.dateOfBirth = extractDate(actor.birthDate);
-	profile.gender = ({ F: 'female', M: 'male' })[actor.gender];
-
-	profile.ethnicity = actor.ethnicity;
-	profile.nationality = actor.nationality;
-	profile.birthPlace = `${actor.birthCity}, ${actor.birthCountry || ''}`;
-
-	profile.hair = actor.hairColor;
-	profile.eyes = actor.eyeColor;
-
-	profile.naturalBoobs = actor.naturalBreasts;
-
-	if (actor.measurements) {
-		const { cupSize, shoulder, chest, waist, height } = actor.measurements;
-
-		if (height) profile.height = inchesToCm(height);
-		if (cupSize) profile.cup = cupSize;
-
-		// [SIC]
-		if (shoulder) profile.bust = shoulder;
-		if (chest) profile.waist = chest;
-		if (waist) profile.hip = waist;
+		if (nextPageRes.ok) {
+			return fetchActorScenes(nextPageRes.context.element, url, entity, page + 1, acc.concat(scenes));
+		}
 	}
 
-	if (actor.twitter) profile.social = [`https://www.twitter.com/${actor.twitter}`];
-	if (actor.image) profile.avatar = `https://i.bang.com/pornstars/${actor.identifier}.jpg`;
+	return acc.concat(scenes);
+}
 
-	if (include.releases) {
-		profile.releases = await fetchActorReleases(actor, entity);
+async function scrapeProfile({ query, element }, url, entity, include) {
+	const profile = {};
+
+	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.ethnicity = query.content('//text()[contains(., "Ethnicity")]/following-sibling::span[contains(@class, "font-bold")][1]');
+
+	profile.hairColor = query.content('//text()[contains(., "Hair Color")]/following-sibling::span[contains(@class, "font-bold")][1]');
+	profile.eyes = query.content('//text()[contains(., "Eye Color")]/following-sibling::span[contains(@class, "font-bold")][1]');
+
+	const avatar = query.img('img[alt*="profile"][src*="https://i.bang.com/pornstars/"]');
+
+	if (avatar) {
+		const { origin, pathname } = new URL(avatar);
+
+		profile.avatar = [
+			`${origin}${pathname}`, // full size
+			avatar,
+		];
+	}
+
+	if (include.scenes) {
+		profile.scenes = await fetchActorScenes(element, url, entity);
 	}
 
 	return profile;
 }
 
-async function fetchLatest(site, page = 1) {
-	const res = await http.post(`https://${clusterId}.us-east-1.aws.found.io/videos/video/_search`, {
-		size: 50,
-		from: (page - 1) * 50,
-		query: {
-			bool: {
-				must: [
-					{
-						match: {
-							status: 'ok',
-						},
-					},
-					{
-						range: {
-							releaseDate: {
-								lte: 'now',
-							},
-						},
-					},
-					/*
-                     * global fetch
-                    {
-                        nested: {
-                            path: 'studio',
-                            query: {
-                                bool: {
-                                    must: [
-                                        {
-                                            match: {
-                                                'studio.name': {
-                                                    operator: 'AND',
-                                                    query: 'bang! originals',
-                                                },
-                                            },
-                                        },
-                                    ],
-                                },
-                            },
-                        },
-                    },
-                    */
-					{
-						nested: {
-							path: 'series',
-							query: {
-								bool: {
-									must: [
-										{
-											match: {
-												'series.id': {
-													operator: 'AND',
-													query: site.parameters.siteId,
-												},
-											},
-										},
-									],
-								},
-							},
-						},
-					},
-				],
-				must_not: [
-					{
-						match: {
-							type: 'trailer',
-						},
-					},
-				],
-			},
-		},
-		sort: [
-			{
-				releaseDate: {
-					order: 'desc',
-				},
-			},
-		],
-	}, {
-		encodeJSON: true,
-		headers: {
-			Authorization: `Basic ${authKey}`,
-		},
-	});
-
-	return scrapeAll(res.body.hits.hits, site);
-}
-
-async function fetchUpcoming(site, page = 1) {
-	const res = await http.post(`https://${clusterId}.us-east-1.aws.found.io/videos/video/_search`, {
-		size: 50,
-		from: (page - 1) * 50,
-		query: {
-			bool: {
-				must: [
-					{
-						match: {
-							status: 'ok',
-						},
-					},
-					{
-						range: {
-							releaseDate: {
-								lte: 'now+7d',
-							},
-						},
-					},
-					{
-						nested: {
-							path: 'series',
-							query: {
-								bool: {
-									must: [
-										{
-											match: {
-												'series.id': {
-													operator: 'AND',
-													query: site.parameters.siteId,
-												},
-											},
-										},
-									],
-								},
-							},
-						},
-					},
-				],
-				must_not: [
-					{
-						match: {
-							type: 'trailer',
-						},
-					},
-				],
-			},
-		},
-		sort: [
-			{
-				releaseDate: {
-					order: 'desc',
-				},
-			},
-		],
-	}, {
-		encodeJSON: true,
-		headers: {
-			Authorization: `Basic ${authKey}`,
-		},
-	});
-
-	return scrapeAll(res.body.hits.hits, site);
-}
-
-async function fetchScene(url, entity, baseRelease, options) {
-	if (baseRelease?.entryId) {
-		// overview and deep data is the same, don't hit server unnecessarily
-		return baseRelease;
-	}
-
-	const encodedId = new URL(url).pathname.split('/')[2];
-	const entryId = decodeId(encodedId);
-
-	const res = await http.get(`https://${clusterId}.us-east-1.aws.found.io/videos/video/${entryId}`, {
-		headers: {
-			Authorization: `Basic ${authKey}`,
-		},
-	});
-
-	return scrapeScene(res.body._source, entity, options); // eslint-disable-line no-underscore-dangle
-}
-
-async function fetchProfile({ name: actorName }, context, include) {
-	const res = await http.post(`https://${clusterId}.us-east-1.aws.found.io/actors/actor/_search`, {
-		size: 5,
-		sort: [{
-			_score: {
-				order: 'desc',
-			},
-		}],
-		query: {
-			bool: {
-				must: [
-					{
-						match: {
-							name: {
-								query: actorName,
-								operator: 'and',
-							},
-						},
-					},
-					{
-						match: {
-							status: 'ok',
-						},
-					},
-				],
-			},
-		},
-	}, {
-		headers: {
-			Authorization: `Basic ${authKey}`,
-		},
-		encodeJSON: true,
-	});
+async function fetchLatest(channel, page = 1) {
+	const url = `${channel.url}&page=${page}`;
+	const res = await unprint.get(url, { selectAll: '.search-grid li' });
 
 	if (res.ok) {
-		const actor = res.body.hits.hits.find((hit) => hit._source.name.toLowerCase() === actorName.toLowerCase());
-
-		if (actor) {
-			return scrapeProfile(actor._source, context.entity, include);
-		}
-
-		return null;
+		return scrapeAll(res.context, channel);
 	}
 
 	return res.status;
 }
 
+async function fetchProfile({ name: actorName }, { entity }, include) {
+	const searchRes = await unprint.get(`https://www.bang.com/pornstars?term=${slugify(actorName, '+')}`);
+
+	if (!searchRes.ok) {
+		return searchRes.status;
+	}
+
+	const url = searchRes.context.query.url(`//a[contains(.//span, "${actorName}")]`);
+
+	if (!url) {
+		return null;
+	}
+
+	const actorRes = await unprint.get(url);
+
+	if (actorRes.ok) {
+		return scrapeProfile(actorRes.context, url, entity, include);
+	}
+
+	return actorRes.status;
+}
+
 module.exports = {
 	fetchLatest,
 	fetchProfile,
-	fetchScene,
-	fetchUpcoming,
+	scrapeScene,
+	useUnprint: true,
 };

src/utils/http.js

@@ -237,6 +237,10 @@ async function destroyBypassSession(sessionId) {
 }
 
 async function destroyBypassSessions() {
+	if (!config.bypass.cloudflare.enabled) {
+		return;
+	}
+
 	const sessionListRes = await limiters.bypass.schedule(async () => bhttp.post(config.bypass.cloudflare.path, {
 		cmd: 'sessions.list',
 	}, {