traxxx/src/scrapers/score.js

262 lines
7.1 KiB
JavaScript

'use strict';
const bhttp = require('bhttp');
const { ex, exa, get } = require('../utils/q');
const slugify = require('../utils/slugify');
const { heightToCm, lbsToKg } = require('../utils/convert');
function scrapePhotos(html) {
const { qis } = ex(html, '#photos-page');
const photos = qis('img');
return photos.map(photo => [
photo
.replace('x_800', 'x_xl')
.replace('_tn', ''),
photo,
]);
}
async function fetchPhotos(url) {
const res = await bhttp.get(url);
if (res.statusCode === 200) {
return scrapePhotos(res.body.toString(), url);
}
return [];
}
function scrapeAll(html, site) {
return exa(html, '.container .video, .container-fluid .video').map(({ q, qa, qd, ql }) => {
const release = {};
release.title = q('.title, .i-title', true);
const linkEl = q('a');
const url = new URL(linkEl.href);
release.url = `${url.origin}${url.pathname}`;
// this is a photo album, not a scene (used for profiles)
if (/photos\//.test(url)) return null;
[release.entryId] = url.pathname.split('/').slice(-2);
release.date = qd('.i-date', 'MMM DD', /\w+ \d{1,2}$/)
|| qd('.dt-box', 'MMM.DD YYYY');
release.actors = site?.parameters?.actors || qa('.model, .i-model', true);
release.duration = ql('.i-amount, .amount');
const posterEl = q('.item-img img');
if (posterEl) {
release.poster = `https:${posterEl.src}`;
}
if (posterEl?.dataset.gifPreview) {
release.teaser = {
src: `https:${posterEl.dataset.gifPreview}`,
};
}
return release;
}).filter(Boolean);
}
async function scrapeScene(html, url, site) {
const { qu } = ex(html, '#videos-page, #content');
const release = {};
[release.entryId] = new URL(url).pathname.split('/').slice(-2);
release.title = qu.q('h2.text-uppercase, h2.title, #breadcrumb-top + h1', true)
|| qu.q('h1.m-title', true)?.split(/»|\//).slice(-1)[0].trim();
release.description = qu.text('.p-desc, .desc');
release.actors = qu.all('.value a[href*=models], .value a[href*=performer], .value a[href*=teen-babes]', true);
if (release.actors.length === 0) {
const actorEl = qu.all('.stat').find(stat => /Featuring/.test(stat.textContent));
const actorString = qu.text(actorEl);
release.actors = actorString?.split(/,\band\b|,/g).map(actor => actor.trim()) || [];
}
if (release.actors.length === 0 && site.parameters?.actors) release.actors = site.parameters.actors;
release.tags = qu.all('a[href*=tag]', true);
const dateEl = qu.all('.value').find(el => /\w+ \d+\w+, \d{4}/.test(el.textContent));
release.date = qu.date(dateEl, null, 'MMMM Do, YYYY')
|| qu.date('.date', 'MMMM Do, YYYY', /\w+ \d{1,2}\w+, \d{4}/)
|| qu.date('.info .holder', 'MM/DD/YYYY', /\d{2}\/\d{2}\/\d{4}/);
const durationEl = qu.all('value').find(el => /\d{1,3}:\d{2}/.test(el.textContent));
release.duration = qu.dur(durationEl);
release.poster = qu.poster('video') || qu.img('.flowplayer img') || qu.img('img'); // _800.jpg is larger than _xl.jpg in landscape
const photosUrl = qu.url('.stat a[href*=photos]');
if (photosUrl) {
release.photos = await fetchPhotos(photosUrl);
} else {
release.photos = qu.imgs('img[src*=ThumbNails], .p-photos .tn img').map(photo => [
photo.replace('_tn', ''),
photo,
]);
}
const trailers = qu.all('a[href*=Trailers]');
if (trailers) {
release.trailer = trailers.map((trailer) => {
const src = `https:${trailer.href}`;
const format = trailer.textContent.trim().match(/^\w+/)[0].toLowerCase();
const quality = parseInt(trailer.textContent.trim().match(/\d+([a-zA-Z]+)?$/)[0], 10);
return format === 'mp4' ? { src, quality } : null;
}).filter(Boolean);
}
const stars = qu.q('.rate-box').dataset.score;
if (stars) release.rating = { stars };
return release;
}
function scrapeModels(html, actorName) {
const { qa } = ex(html);
const model = qa('.model a').find(link => link.title === actorName);
return model?.href || null;
}
async function fetchActorReleases(url, accReleases = []) {
const res = await get(url);
if (res.ok) {
const releases = accReleases.concat(scrapeAll(res.item.document.body.outerHTML));
const nextPage = res.item.qu.url('.next-pg');
if (nextPage && new URL(nextPage).searchParams.has('page')) { // last page has 'next' button linking to join page
return fetchActorReleases(nextPage, releases);
}
return releases;
}
return null;
}
async function scrapeProfile(html, actorUrl, withReleases) {
const { q, qa, qi } = ex(html, '#model-page');
const profile = { gender: 'female' };
const bio = qa('.stat').reduce((acc, el) => {
const prop = q(el, '.label', true).slice(0, -1);
const key = slugify(prop, '_');
const value = q(el, '.value', true);
return {
...acc,
[key]: value,
};
}, {});
if (bio.location) profile.residencePlace = bio.location.replace('Czech Repulic', 'Czech Republic'); // see Laura Lion
if (bio.birthday) {
const birthMonth = bio.birthday.match(/^\w+/)[0].toLowerCase();
const [birthDay] = bio.birthday.match(/\d+/);
profile.birthday = [birthMonth, birthDay]; // currently unused, not to be confused with birthdate
}
if (bio.ethnicity) profile.ethnicity = bio.ethnicity;
if (bio.hair_color) profile.hair = bio.hair_color;
if (bio.height) profile.height = heightToCm(bio.height);
if (bio.weight) profile.weight = lbsToKg(bio.weight);
if (bio.bra_size) profile.bust = bio.bra_size;
if (bio.measurements) [, profile.waist, profile.hip] = bio.measurements.split('-');
if (bio.occupation) profile.occupation = bio.occupation;
const avatar = qi('img');
if (avatar) profile.avatar = avatar;
if (withReleases) {
const { origin, pathname } = new URL(actorUrl);
profile.releases = await fetchActorReleases(`${origin}${pathname}/scenes?page=1`);
}
return profile;
}
async function fetchLatest(site, page = 1) {
const latestPath = site.parameters?.path || '/big-boob-videos';
const url = `${site.url}${latestPath}?page=${page}`;
const res = await bhttp.get(url);
if (res.statusCode === 200) {
return scrapeAll(res.body.toString(), site);
}
return res.statusCode;
}
async function fetchScene(url, site) {
const res = await bhttp.get(url);
if (res.statusCode === 200) {
return scrapeScene(res.body.toString(), url, site);
}
return null;
}
async function fetchProfile(actorName, scraperSlug, site, include, page = 1, source = 0) {
const letter = actorName.charAt(0).toUpperCase();
const sources = [
`https://www.scoreland.com/big-boob-models/browse/${letter}/?page=${page}`,
`https://www.50plusmilfs.com/xxx-milf-models/browse/${letter}/?page=${page}`,
];
const url = sources[source];
const res = await bhttp.get(url, {
followRedirects: false,
});
if (res.statusCode === 200) {
const actorUrl = scrapeModels(res.body.toString(), actorName);
if (actorUrl) {
const actorRes = await bhttp.get(actorUrl);
if (actorRes.statusCode === 200) {
return scrapeProfile(actorRes.body.toString(), actorUrl, include.scenes);
}
return null;
}
return fetchProfile(actorName, scraperSlug, site, include, page + 1, source);
}
if (sources[source + 1]) {
return fetchProfile(actorName, scraperSlug, site, include, 1, source + 1);
}
return null;
}
module.exports = {
fetchLatest,
fetchScene,
fetchProfile,
};