Added conditions to Tokyo Hot scraper to prevent total failure.

seeds/02_sites.js

@@ -5991,6 +5991,13 @@ const sites = [
 		independent: true,
 		parent: 'modelmedia',
 	},
+	{
+		slug: 'jerkaoke',
+		name: 'Jerkaoke',
+		url: 'https://www.jerkaoke.com',
+		independent: true,
+		parent: 'modelmedia',
+	},
 	// MOFOS
 	{
 		slug: 'girlsgonepink',

src/media.js

@@ -279,7 +279,6 @@ async function findSourceDuplicates(baseMedias) {
 	const [existingSourceMedia, existingExtractMedia] = await Promise.all([
 		// may try to check thousands of URLs at once, don't pass all of them to a single query
 		chunk(sourceUrls).reduce(async (chain, sourceUrlsChunk) => {
-			console.log(sourceUrlsChunk);
 			const accUrls = await chain;
 			const existingUrls = await knex('media').whereIn('source', sourceUrlsChunk);
 

src/scrapers/delphine.js

@@ -1,85 +0,0 @@
-'use strict';
-
-const unprint = require('unprint');
-
-const http = require('../utils/http');
-const qu = require('../utils/qu');
-
-function scrapeAll(scenes) {
-	return scenes.map(({ query }) => {
-		const release = {};
-
-		release.title = query.content('.video-title div');
-
-		console.log(release);
-
-		return release;
-	});
-}
-
-async function fetchLatest(channel, page) {
-	const session = http.session();
-
-	await http.get(channel.url, { session });
-	await http.post(`${channel.url}/adult_confirmation_and_accept_cookie`, null, { session });
-	const checkRes = await http.get(`${channel.url}/check_adult_confirmation_and_accept_cookie`, { session });
-
-	const res = await http.get(`${channel.url}/videos?sort=published_at&page=${page}`, { session });
-
-	// const res = await http.get(`${channel.url}/videos?sort=published_at&page=${page}`, { selectAll: '.row a[video-id]' });
-
-	console.log(checkRes.body);
-	console.log(res.body);
-
-	if (res.ok) {
-		return scrapeAll(res.context, channel);
-	}
-
-	return res.status;
-}
-
-/*
-
-    function confirmAdultCookie() {
-        // console.log('confirmed Adult');
-        $('#adult_confirmation').modal('hide');
-
-        var adultCookieRequest = $.ajax({
-            xhrFields: {
-                withCredentials: true
-            },
-            type: "POST",
-            url: "https://www.delphinefilms.com/adult_confirmation_and_accept_cookie"
-        });
-
-        $.when(adultCookieRequest).done(function() {
-            // console.log('Both requests completed successfully');
-            waitForSessionUpdateAndRefresh();
-        });
-
-        return false;
-    }
-
-    function waitForSessionUpdateAndRefresh() {
-        var interval = setInterval(function() {
-            $.ajax({
-                type: "GET",
-                url: "https://www.delphinefilms.com/check_adult_confirmation_and_accept_cookie",
-                success: function(response) {
-                    // console.log(response)
-                    if (response === "1") {
-                        // console.log('Session updated: Adult confirmed and cookie accepted');
-                        clearInterval(interval);
-                        location.reload();
-                    } else {
-                        // console.log('Session not updated: Adult not confirmed or cookie not accepted');
-                    }
-                }
-            });
-        }, 100);
-    }
-*/
-
-module.exports = {
-	fetchLatest,
-};

src/scrapers/modelmedia.js

@@ -0,0 +1,151 @@
+'use strict';
+
+const unprint = require('unprint');
+
+function scrapeAll(scenes) {
+	return scenes.map(({ query }) => {
+		const release = {};
+
+		release.entryId = query.attribute(null, 'video-id');
+
+		const url = query.url(null);
+
+		if (url) {
+			const { origin, pathname, searchParams } = new URL(url);
+
+			release.url = `${origin}${pathname}`;
+			release.actors = searchParams.get('models_name')?.split(',');
+		}
+
+		release.title = query.content('.video-title div');
+		release.duration = query.duration('.timestamp');
+
+		const poster = query.img('img', { attribute: 'data-src' });
+
+		if (poster) {
+			release.poster = [
+				poster.replace(/w=\d+/, 'w=1920').replace(/h=\d+/, 'h=1080'),
+				poster,
+			];
+		}
+
+		release.teaser = query.video(null, { attribute: 'data-video-src' });
+
+		console.log(release);
+
+		return release;
+	});
+}
+
+function scrapeProfile({ query }) {
+	const profile = {};
+	const avatar = query.img('div[class*="prof-pic"] > img');
+
+	if (avatar) {
+		profile.avatar = [
+			avatar.replace(/w=\d+/, 'w=720').replace(/h=\d+/, 'h=1080'),
+			avatar,
+		];
+	}
+
+	profile.description = query.content('h2') || null;
+	profile.height = query.number('//span[text()="Measurements"]/following-sibling::span', { match: /(\d+) cm/, matchIndex: 1 });
+	profile.weight = query.number('//span[text()="Weight"]/following-sibling::span', { match: /(\d+) kg/, matchIndex: 1 });
+
+	profile.measurements = query.number('//span[text()="Birth Place"]/following-sibling::span', { match: /(\d+) cm/, matchIndex: 1 });
+	profile.birthPlace = query.number('//span[text()="Birth Place"]/following-sibling::span');
+
+	profile.banner = query.img('div[class*="banner"] > img');
+	profile.photos = query.imgs('#MusModelSwiper img');
+
+	console.log(profile);
+
+	return profile;
+}
+
+async function getCookie(channel) {
+	const tokenRes = await unprint.get(channel.url);
+
+	if (!tokenRes.ok) {
+		return tokenRes.status;
+	}
+
+	const csrfToken = tokenRes.context?.query.attribute('meta[name="csrf-token"]', 'content');
+	const cookie = tokenRes.response.headers['set-cookie']?.join(';');
+
+	if (!csrfToken || !cookie) {
+		return null;
+	}
+
+	const confirmAdultRes = await unprint.post(`${channel.url}/adult_confirmation_and_accept_cookie`, null, {
+		headers: {
+			cookie,
+			'x-csrf-token': csrfToken,
+		},
+	});
+
+	if (!confirmAdultRes.ok) {
+		return confirmAdultRes.status;
+	}
+
+	return cookie;
+}
+
+async function fetchLatest(channel, page) {
+	const cookie = await getCookie(channel);
+
+	const res = await unprint.get(`${channel.url}/videos?sort=published_at&page=${page}`, {
+		selectAll: '.row a[video-id]',
+		headers: {
+			cookie,
+		},
+	});
+
+	if (res.ok) {
+		return scrapeAll(res.context, channel);
+	}
+
+	return res.status;
+}
+
+// deep pages are paywalled
+
+async function searchProfile(actor, context, cookie) {
+	const searchRes = await unprint.get(`${context.channel.url}/livesearch?keyword=${actor.name}`, {
+		headers: {
+			cookie,
+		},
+	});
+
+	if (!searchRes.ok) {
+		return searchRes.status;
+	}
+
+	return searchRes.context.query.url(`a[title="${actor.name}"]`);
+}
+
+async function fetchProfile(actor, context) {
+	const cookie = await getCookie(context.entity);
+	const actorUrl = actor.url || await searchProfile(actor, context, cookie);
+
+	if (!actorUrl) {
+		return null;
+	}
+
+	const res = await unprint.get(actorUrl, {
+		headers: {
+			cookie,
+		},
+	});
+
+	if (res.ok) {
+		return scrapeProfile(res.context, actorUrl);
+	}
+
+	return null;
+}
+
+module.exports = {
+	fetchLatest,
+	fetchProfile,
+};

src/scrapers/scrapers.js

@@ -15,7 +15,7 @@ const cherrypimps = require('./cherrypimps');
 const cumlouder = require('./cumlouder');
 const czechav = require('./czechav');
 const ddfnetwork = require('./ddfnetwork');
-const delphine = require('./delphine');
+const modelmedia = require('./modelmedia');
 const dorcel = require('./dorcel');
 const fabulouscash = require('./fabulouscash');
 const famedigital = require('./famedigital');
@@ -95,7 +95,7 @@ const scrapers = {
 		cumlouder,
 		czechav,
 		pornworld: ddfnetwork,
-		delphine,
+		delphine: modelmedia,
 		dorcel,
 		elegantangel: adultempire,
 		famedigital,
@@ -191,6 +191,7 @@ const scrapers = {
 		blackedraw: vixen,
 		blackambush: elevatedx,
 		bluedonkeymedia,
+		delphine: modelmedia,
 		meidenvanholland: bluedonkeymedia,
 		vurigvlaanderen: bluedonkeymedia,
 		boobpedia,

src/scrapers/tokyohot.js

@@ -19,10 +19,12 @@ function scrapeAll(scenes, channel) {
 
 		const poster = query.img();
 
-		release.poster = [
-			poster.replace('220x124', '820x462'),
-			poster,
-		];
+		if (poster) {
+			release.poster = [
+				poster.replace('220x124', '820x462'),
+				poster,
+			];
+		}
 
 		return release;
 	});
@@ -59,12 +61,12 @@ function scrapeScene({ query }, url, channel) {
 
 	release.photos = query.imgs('.scap a', { attribute: 'href' }).map((img) => [
 		img,
-		img.replace('640x480_wlimited', '150x150_default'),
+		img?.replace('640x480_wlimited', '150x150_default'),
 	]);
 
 	release.caps = query.imgs('.vcap a', { attribute: 'href' }).map((img) => [
 		img,
-		img.replace('640x480_wlimited', '120x120_default'),
+		img?.replace('640x480_wlimited', '120x120_default'),
 	]);
 
 	return release;
@@ -109,7 +111,7 @@ function scrapeProfile({ query }) {
 	profile.hairStyle = bio.hair_style;
 	profile.shoeSize = getMeasurement(bio.shoes_size);
 
-	profile.bloodType = bio.blood_type.replace('type', '').trim();
+	profile.bloodType = bio.blood_type?.replace('type', '').trim();
 
 	profile.avatar = query.img('#profile img');