237 lines
7.1 KiB
JavaScript
Executable File
237 lines
7.1 KiB
JavaScript
Executable File
'use strict';
|
|
|
|
const unprint = require('unprint');
|
|
|
|
const slugify = require('../utils/slugify');
|
|
const { stripQuery } = require('../utils/url');
|
|
|
|
function scrapeAllA(scenes, channel) {
|
|
return scenes.map(({ query }) => {
|
|
const release = {};
|
|
|
|
release.url = query.url('a.thumb-img, a.thumb', { origin: channel.url, protocol: 'http' });
|
|
release.entryId = new URL(release.url).pathname.match(/(\d+)\/?$/)?.[1];
|
|
|
|
release.title = query.text('.thumb-title, .title');
|
|
release.date = query.date('.thumb-added, .date', ['MMM D, YYYY', 'MMMM DD, YYYY'], /\w+ \d{1,2}, \d{4}/);
|
|
release.duration = query.duration('.thumb-duration');
|
|
|
|
release.actors = query.all('.thumb-models a, .models a').map((actorEl) => ({
|
|
name: unprint.query.content(actorEl),
|
|
url: unprint.query.url(actorEl, null, { origin: channel.url, protocol: 'http' }),
|
|
}));
|
|
|
|
const [, photoUrl, photoCount] = query.attribute('.thumb-img img', 'onmouseover')?.match(/'(.*)', (\d+)\)/) || [];
|
|
|
|
if (photoUrl && photoCount) {
|
|
[release.poster, ...release.photos] = Array.from({ length: 5 }, (_value, index) => unprint.prefixUrl(`${photoUrl}${index + 1}.jpg`, channel.origin, { protocol: 'http' }));
|
|
} else {
|
|
release.poster = query.img('.thumb-img img, .thumb img', { origin: channel.url, protocol: 'http' });
|
|
}
|
|
|
|
release.tags = query.contents('.tags a');
|
|
release.rating = query.number('.thumb-rating');
|
|
|
|
return release;
|
|
});
|
|
}
|
|
|
|
async function fetchLatestA(channel, page) {
|
|
const url = channel.parameters?.latest
|
|
? `${channel.parameters.latest}/${page}`
|
|
: `${channel.url}/latest-updates/${page}/`;
|
|
|
|
const res = await unprint.get(url, { selectAll: '.list-thumbs ul > li, .main-thumbs > li' });
|
|
|
|
if (res.ok) {
|
|
return scrapeAllA(res.context, channel);
|
|
}
|
|
|
|
return res.status;
|
|
}
|
|
|
|
function scrapeAllB(scenes, channel) {
|
|
return scenes.map(({ query }) => {
|
|
const release = {};
|
|
|
|
release.title = query.content('.title, h2');
|
|
release.duration = query.duration('.time');
|
|
|
|
const description = query.content('.description, p textarea');
|
|
|
|
if (!/there is no description/i.test(description)) {
|
|
release.description = description;
|
|
}
|
|
|
|
release.poster = query.poster('#player, #example_video_1', { origin: channel.origin, protocol: 'http' });
|
|
release.trailer = query.video('#player source, #example_video_1 source', { origin: channel.origin, protocol: 'http' });
|
|
|
|
release.photos = query.imgs('img[src*="sets/"], img[src*="thumbnails/"]', { origin: channel.origin, protocol: 'http' });
|
|
|
|
release.entryId = release.poster?.match(/\/sets\/(.*)\//)?.[1] || slugify(release.title);
|
|
|
|
return release;
|
|
});
|
|
}
|
|
|
|
async function fetchLatestB(channel, page) {
|
|
const url = channel.parameters?.paginated
|
|
? `${channel.url}/page/${page}`
|
|
: channel.url;
|
|
|
|
const res = await unprint.get(url, {
|
|
selectAll: '#container, article:not(.sortby)',
|
|
parser: {
|
|
runScripts: 'dangerously',
|
|
},
|
|
});
|
|
|
|
if (res.ok) {
|
|
return scrapeAllB(res.context, channel);
|
|
}
|
|
|
|
return res.status;
|
|
}
|
|
|
|
function scrapeSceneA({ query }, url, channel) {
|
|
const release = {};
|
|
|
|
release.entryId = new URL(url).pathname.match(/(\d+)\/?$/)?.[1];
|
|
|
|
release.title = query.content('.title, .scene-title h3').replace(/:$/, '');
|
|
|
|
const description = query.content('.text-desc p, .info-description p');
|
|
|
|
if (!/there is no description/i.test(description)) {
|
|
release.description = description;
|
|
}
|
|
|
|
release.duration = query.duration('.media-body li span, .duration');
|
|
|
|
release.actors = query.all('.media-body a[href*="models/"], .models a').map((actorEl) => ({
|
|
name: unprint.query.content(actorEl),
|
|
url: unprint.query.url(actorEl, null, { origin: channel.url, protocol: 'http' }),
|
|
}));
|
|
|
|
release.tags = query.contents('.media-body a[href*="tags/"], .tags a');
|
|
|
|
release.poster = Array.from(new Set([
|
|
query.img('.player-preview', { protocol: 'http' }),
|
|
unprint.prefixUrl(`/contents/videos_screenshots/0/${release.entryId}/preview_trailer.mp4.jpg`, channel.url, { protocol: 'http' }),
|
|
unprint.prefixUrl(query.attribute('param[name="flashvars"]', 'value')?.match(/poster=(.*\.jpg)/)?.[1], channel.url, { protocol: 'http' }),
|
|
unprint.prefixUrl(`/contents/scenes/${release.entryId}/thumbnails/920x518.jpg`, channel.url, { protocol: 'http' }),
|
|
].filter(Boolean)));
|
|
|
|
release.photos = query.urls('.thumb-album a:not([href="#"]), .thumbs-photo a:not([href*="signup"])', { origin: channel.url, protocol: 'http' })
|
|
.concat(query.imgs('.thumb-album a[href="#"] img, .thumbs-photo a[href*="signup"] img', { origin: channel.url, protocol: 'http' }));
|
|
|
|
release.trailer = stripQuery(query.url('a[href*="get_file/"], .download a'));
|
|
|
|
return release;
|
|
}
|
|
|
|
async function fetchSceneA(url, channel) {
|
|
const res = await unprint.get(url, { select: '.main, .main-content' });
|
|
|
|
if (res.ok) {
|
|
return scrapeSceneA(res.context, url, channel);
|
|
}
|
|
|
|
return res.status;
|
|
}
|
|
|
|
function scrapeProfileA({ query }, entity) {
|
|
const profile = {};
|
|
|
|
const bio = query.all('.list-model-info li, .profile-info li').reduce((acc, bioEl) => ({
|
|
...acc,
|
|
[slugify(unprint.query.content(bioEl, '.title, span'), '_')]: unprint.query.content(bioEl, ':nth-child(2)')
|
|
|| unprint.query.attribute(bioEl, ':nth-child(2)', 'title')
|
|
|| unprint.query.text(bioEl),
|
|
}), {});
|
|
|
|
profile.dateOfBirth = unprint.extractDate(bio.birth_date || bio.date_of_birth, 'DD MMMM, YYYY', { match: null });
|
|
profile.birthPlace = bio.nationality || bio.place_of_birth || null;
|
|
|
|
profile.weight = unprint.extractNumber(bio.weight);
|
|
profile.height = unprint.extractNumber(bio.height);
|
|
|
|
profile.eyes = bio.eye_color;
|
|
profile.hairColor = bio.hair || bio.hair_color;
|
|
|
|
profile.aliases = query.text('.sub-title')?.replace(/:\s*/, '').split(/,\s*/);
|
|
|
|
profile.measurements = bio.measurements || bio.body_shape_dimensions;
|
|
|
|
const description = query.content('.model-biography p');
|
|
const avatar = query.img('.model-box img, .profile-model-photo', { origin: entity.url, protocol: 'http' });
|
|
|
|
if (!/there is no description/i.test(description)) {
|
|
profile.description = description;
|
|
}
|
|
|
|
if (avatar) {
|
|
profile.avatar = Array.from(new Set([
|
|
avatar,
|
|
avatar.replace('s2_', 's1_'),
|
|
avatar.replace('s1_', 's2_'),
|
|
]));
|
|
}
|
|
|
|
profile.scenes = scrapeAllA(unprint.initAll(query.all('.list-thumbs .thumb, .main-thumbs > li')), entity);
|
|
|
|
return profile;
|
|
}
|
|
|
|
async function getActorUrl(actor, entity) {
|
|
if (actor.url) {
|
|
return actor.url;
|
|
}
|
|
|
|
// Double View Casting seems to be case sensitive...
|
|
const res = await unprint.get(`${entity.origin}/models/search/?q=${actor.name}`, { selectAll: '.thumb-modal, .big-thumb' });
|
|
|
|
if (!res.ok) {
|
|
return res.status;
|
|
}
|
|
|
|
const actorItem = res.context.find(({ query }) => slugify(query.content('.thumb-title a, .title')) === actor.slug);
|
|
|
|
if (!actorItem) {
|
|
return null;
|
|
}
|
|
|
|
const actorUrl = actorItem.query.url('a', { origin: entity.url, protocol: 'http' });
|
|
|
|
if (actorUrl) {
|
|
return actorUrl;
|
|
}
|
|
|
|
return null;
|
|
}
|
|
|
|
async function fetchProfileA(actor, { entity }) {
|
|
const actorUrl = await getActorUrl(actor, entity);
|
|
|
|
if (actorUrl) {
|
|
const actorRes = await unprint.get(actorUrl);
|
|
|
|
if (actorRes.ok) {
|
|
return scrapeProfileA(actorRes.context, entity);
|
|
}
|
|
}
|
|
|
|
return null;
|
|
}
|
|
|
|
module.exports = {
|
|
a: {
|
|
fetchLatest: fetchLatestA,
|
|
fetchScene: fetchSceneA,
|
|
fetchProfile: fetchProfileA,
|
|
},
|
|
b: {
|
|
fetchLatest: fetchLatestB,
|
|
},
|
|
};
|