Added Kink VR to Kink scraper, no longer using Badoink?

This commit is contained in:
DebaucheryLibrarian
2026-01-06 02:30:35 +01:00
parent 899691ebd7
commit c311964a8a
6 changed files with 207 additions and 28 deletions

View File

@@ -496,20 +496,23 @@ async function curateProfile(profile, actor) {
}
}
curatedProfile.social = [].concat(profile.social).map((social) => {
if (!social) {
return null;
}
curatedProfile.social = []
.concat(profile.social) // legacy
.concat(profile.socials)
.map((social) => {
if (!social) {
return null;
}
try {
const { origin, pathname } = new URL(social);
try {
const { origin, pathname } = new URL(social);
return `${origin}${pathname}`;
} catch (error) {
logger.warn(`Profile scraper for '${profile.entity.name}' returned invalid social link: ${social}`);
return null;
}
}).filter(Boolean);
return `${origin}${pathname}`;
} catch (error) {
logger.warn(`Profile scraper for '${profile.entity.name}' returned invalid social link: ${social}`);
return null;
}
}).filter(Boolean);
curatedProfile.scenes = toBaseReleases(profile.scenes || profile.releases, profile.entity, actor)
// attach actor to base scene, in case it was not scraped

View File

@@ -66,13 +66,11 @@ function scrapeAll(scenes, entity) {
async function fetchLatest(channel, page = 1) {
const url = `${channel.parent.url}/search?type=shoots&channelIds=${channel.parameters?.slug || channel.slug}&sort=published&page=${page}`;
const res = await unprint.browserRequest(url, {
const res = await unprint.browser(url, {
selectAll: '.container .card',
});
if (res.status === 200) {
// const items = unprint.initAll(html, '.container .card');
const scenes = scrapeAll(res.context, channel);
return scenes;
@@ -81,6 +79,52 @@ async function fetchLatest(channel, page = 1) {
return res.status;
}
function scrapeAllVr(scenes, channel) {
return scenes.map(({ query }) => {
const release = {};
const url = query.url('a.image-link, a.video-title');
const { pathname } = new URL(url);
release.url = url;
// legacy ID in slug preferred to match old entries, but prepare for retirement just in case
release.entryId = pathname.match(/-(\d+)\/?$/)?.[1] || pathname.match(/\/vd\/(\d+)\//)[1];
release.title = query.content('.video-title');
release.description = query.content('.description');
release.date = query.date('.main-info', 'MMM Do YYYY', { match: /\w{3} \d+\w+ \d{4}/ });
release.actors = query.all('.actors a').map((actorEl) => ({
name: unprint.query.content(actorEl),
url: unprint.query.url(actorEl, null, { origin: channel.url }),
}));
release.poster = query.sourceSet('.image-link img');
release.photos = query.dataset('.image-link div[data-gallery-images]', 'galleryImages')?.split(',').filter(Boolean); // can sometimes be ,,,, with no URLs
return release;
});
}
async function fetchLatestVr(channel, page = 1) {
const url = `${channel.url}/videos/page${page}`;
const res = await unprint.get(url, {
selectAll: '#listView .video-list-view', // more details than #gridView
headers: {
Cookie: 'agreedToDisclaimer=true',
},
});
if (res.ok) {
const scenes = scrapeAllVr(res.context, channel);
return scenes;
}
return res.status;
}
function scrapeScene({ query }, url, entity) {
const release = { url };
const data = query.json('div[data-setup]', { attribute: 'data-setup' });
@@ -145,7 +189,7 @@ function scrapeScene({ query }, url, entity) {
}
async function fetchScene(url, channel) {
const res = await unprint.browserRequest(url);
const res = await unprint.browser(url);
if (res.status === 200) {
const scene = scrapeScene(res.context, url, channel);
@@ -156,6 +200,66 @@ async function fetchScene(url, channel) {
return res.status;
}
const qualityMap = {
psvr: 1080, // as of recent, might've been lower in the past
'4k': 2160,
'5k': 2280,
'8k': 4320,
};
function scrapeSceneVr({ query }, url, channel) {
const release = {};
const { pathname } = new URL(url);
// legacy ID in slug preferred to match old entries, but prepare for retirement just in case
release.entryId = pathname.match(/-(\d+)\/?$/)?.[1] || pathname.match(/\/vd\/(\d+)\//)[1];
release.title = query.content('.page-title');
release.description = query.content('#collapseDescription .accordion-body') || query.attribute('meta[name="description"]', 'content');
release.date = query.date('.video-description-list', 'MMMM D, YYYY');
release.actors = query.all('.video-description-list a[href*="/girl"]').map((actorEl) => ({
name: unprint.query.content(actorEl),
url: unprint.query.url(actorEl, null, { origin: channel.url }),
})); // no sign of boys
release.tags = query.contents('.video-description-list a[href*="/category"]');
release.poster = query.poster('dl8-video');
release.photos = query.sourceSets('.carousel .item img');
if (query.exists('dl8-video source[src*=".mp4"]')) {
// sometimes the trailer URL is missing the filename, it won't play on their site either
release.trailer = {
src: query.video('dl8-video source'),
vr: true,
};
}
release.qualities = query
.contents('#downloadsData a')
.map((button) => qualityMap[button.match(/download (\w+)/i)?.[1]?.toLowerCase()])
.filter(Boolean);
return release;
}
async function fetchSceneVr(url, channel) {
const res = await unprint.get(url, {
headers: {
Cookie: 'agreedToDisclaimer=true',
},
});
if (res.ok) {
return scrapeSceneVr(res.context, url, channel);
}
return res.status;
}
async function scrapeProfile({ query }, actorUrl) {
const profile = { url: actorUrl };
@@ -196,7 +300,7 @@ async function getActorUrl({ name: actorName, url }, networkUrl) {
}
// const searchRes = await tab.goto(`${networkUrl}/search?type=performers&q=${actorName}`);
const searchApiRes = await unprint.browserRequest(`https://www.kink.com/api/v2/search/suggestions/performers?term=${actorName}`);
const searchApiRes = await unprint.browser(`https://www.kink.com/api/v2/search/suggestions/performers?term=${actorName}`);
if (searchApiRes.status === 200) {
const data = searchApiRes.context.query.json('body pre');
@@ -217,7 +321,7 @@ async function fetchProfile(actor, entity) {
const actorUrl = await getActorUrl(actor, networkUrl);
if (actorUrl) {
const actorRes = await unprint.browserRequest(actorUrl);
const actorRes = await unprint.browser(actorUrl);
if (actorRes.status === 200) {
return scrapeProfile(actorRes.context, actorUrl);
@@ -229,9 +333,82 @@ async function fetchProfile(actor, entity) {
return null;
}
async function getActorUrlVr(actor, entity) {
if (actor.url) {
return actor.url;
}
const res = await unprint.get(`${entity.url}/search/`, {
selectAll: '#actors option',
headers: {
Cookie: 'agreedToDisclaimer=true',
},
});
if (res.ok) {
const actors = res.context.map(({ query }) => ({
name: query.content(),
id: query.attribute(null, 'value'),
}));
const targetActor = actors.find((actorOption) => actor.slug === slugify(actorOption.name));
if (targetActor?.id) {
return `${entity.url}/girl/${targetActor.id}/${slugify(targetActor.name)}`;
}
}
return null;
}
function scrapeProfileVr({ query }, url) {
const profile = { url };
const keys = query.contents('.info .key');
const values = query.contents('.info .value', { filter: false });
const bio = Object.fromEntries(keys.map((key, index) => [slugify(key, '_'), values[index]]));
profile.description = query.content('#readMoreFull');
profile.avatar = query.sourceSet('.images img');
if (bio.birthdate) profile.dateOfBirth = unprint.extractDate(bio.birthdate, 'MMMM DD, YYYY');
if (bio.country) profile.birthPlace = bio.country;
if (bio.cup) profile.cup = bio.cup;
if (bio.height) profile.height = Number(bio.height.match(/(\d+) cm/i)?.[1]) || null;
if (bio.weight) profile.weight = Number(bio.weight.match(/(\d+) kg/i)?.[1]) || null;
profile.socials = query.urls('.value.social a');
return profile;
}
async function fetchProfileVr(actor, entity) {
const url = await getActorUrlVr(actor, entity);
if (url) {
const res = await unprint.get(url, {
headers: {
Cookie: 'agreedToDisclaimer=true',
},
});
if (res.ok) {
return scrapeProfileVr(res.context, url, entity);
}
return res.status;
}
return null;
}
module.exports = {
// beforeNetwork,
fetchLatest,
fetchScene,
fetchProfile,
vr: {
fetchLatest: fetchLatestVr,
fetchScene: fetchSceneVr,
fetchProfile: fetchProfileVr,
},
};

View File

@@ -138,7 +138,7 @@ const scrapers = {
'5kvids': kellymadison,
killergram,
kink,
kinkvr: badoink,
// kinkvr: badoink,
// analvids,
analvids: pornbox,
littlecapricedreams,
@@ -273,7 +273,7 @@ const scrapers = {
killergram,
kink,
kinkmen: kink,
kinkvr: badoink,
kinkvr: kink,
loveherfilms,
loveherfeet: loveherfilms,
shelovesblack: loveherfilms,