forked from DebaucheryLibrarian/traxxx
215 lines
7.7 KiB
JavaScript
215 lines
7.7 KiB
JavaScript
'use strict';
|
|
|
|
/* eslint-disable newline-per-chained-call */
|
|
const bhttp = require('bhttp');
|
|
const cheerio = require('cheerio');
|
|
const { JSDOM } = require('jsdom');
|
|
const moment = require('moment');
|
|
|
|
const { get, ex } = require('../utils/q');
|
|
const slugify = require('../utils/slugify');
|
|
const { heightToCm, lbsToKg } = require('../utils/convert');
|
|
|
|
const hairMap = {
|
|
Blonde: 'blonde',
|
|
Brunette: 'brown',
|
|
'Black Hair': 'black',
|
|
Redhead: 'red',
|
|
};
|
|
|
|
function scrapeAll(html, site, upcoming) {
|
|
const $ = cheerio.load(html, { normalizeWhitespace: true });
|
|
const sceneElements = $('.release-card.scene').toArray();
|
|
|
|
return sceneElements.reduce((acc, element) => {
|
|
const isUpcoming = $(element).find('.icon-upcoming.active').length === 1;
|
|
|
|
if ((upcoming && !isUpcoming) || (!upcoming && isUpcoming)) {
|
|
return acc;
|
|
}
|
|
|
|
const sceneLinkElement = $(element).find('a');
|
|
|
|
const url = `https://www.brazzers.com${sceneLinkElement.attr('href')}`;
|
|
const title = sceneLinkElement.attr('title');
|
|
const entryId = url.split('/').slice(-3, -2)[0];
|
|
|
|
const date = moment.utc($(element).find('time').text(), 'MMMM DD, YYYY').toDate();
|
|
const actors = $(element).find('.model-names a').map((actorIndex, actorElement) => $(actorElement).attr('title')).toArray();
|
|
|
|
const likes = Number($(element).find('.label-rating .like-amount').text());
|
|
const dislikes = Number($(element).find('.label-rating .dislike-amount').text());
|
|
|
|
const poster = `https:${$(element).find('.card-main-img').attr('data-src')}`;
|
|
const photos = $(element).find('.card-overlay .image-under').map((photoIndex, photoElement) => `https:${$(photoElement).attr('data-src')}`).toArray();
|
|
|
|
const channel = slugify($(element).find('.collection').attr('title'), { delimiter: '' });
|
|
|
|
return acc.concat({
|
|
url,
|
|
entryId,
|
|
title,
|
|
actors,
|
|
date,
|
|
poster,
|
|
photos,
|
|
rating: {
|
|
likes,
|
|
dislikes,
|
|
},
|
|
channel,
|
|
site,
|
|
});
|
|
}, []);
|
|
}
|
|
|
|
async function scrapeScene(html, url, _site) {
|
|
const $ = cheerio.load(html, { normalizeWhitespace: true });
|
|
const release = {};
|
|
|
|
const videoJson = $('script:contains("window.videoUiOptions")').html();
|
|
const videoString = videoJson.slice(videoJson.indexOf('{"stream_info":'), videoJson.lastIndexOf('},') + 1);
|
|
const videoData = JSON.parse(videoString);
|
|
|
|
[release.entryId] = url.split('/').slice(-3, -2);
|
|
release.title = $('.scene-title[itemprop="name"]').text();
|
|
|
|
release.description = $('#scene-description p[itemprop="description"]')
|
|
.contents()
|
|
.first()
|
|
.text()
|
|
.trim();
|
|
|
|
release.date = moment.utc($('.more-scene-info .scene-date').text(), 'MMMM DD, YYYY').toDate();
|
|
release.actors = $('.related-model a').map((actorIndex, actorElement) => $(actorElement).text()).toArray();
|
|
release.duration = Number($('.scene-length[itemprop="duration"]').attr('content').slice(1, -1)) * 60;
|
|
|
|
release.likes = Number($('.label-rating .like').text());
|
|
release.dislikes = Number($('.label-rating .dislike').text());
|
|
|
|
const siteElement = $('.niche-site-logo');
|
|
// const siteUrl = `https://www.brazzers.com${siteElement.attr('href').slice(0, -1)}`;
|
|
const siteName = siteElement.attr('title');
|
|
release.channel = siteName.replace(/\s+/g, '').toLowerCase();
|
|
|
|
release.tags = $('.tag-card-container a').map((tagIndex, tagElement) => $(tagElement).text()).toArray();
|
|
release.photos = $('.carousel-thumb a').map((photoIndex, photoElement) => `https:${$(photoElement).attr('href')}`).toArray();
|
|
|
|
const posterPath = videoData?.poster || $('meta[itemprop="thumbnailUrl"]').attr('content') || $('#trailer-player-container').attr('data-player-img');
|
|
if (posterPath) release.poster = `https:${posterPath}`;
|
|
|
|
if (videoData) {
|
|
release.trailer = Object.entries(videoData.stream_info.http.paths).map(([quality, path]) => ({
|
|
src: `https:${path}`,
|
|
quality: Number(quality.match(/\d{3,}/)[0]),
|
|
}));
|
|
}
|
|
|
|
return release;
|
|
}
|
|
|
|
function scrapeActorSearch(html, url, actorName) {
|
|
const { document } = new JSDOM(html).window;
|
|
const actorLink = document.querySelector(`a[title="${actorName}" i]`);
|
|
|
|
return actorLink ? actorLink.href : null;
|
|
}
|
|
|
|
async function fetchActorReleases({ qu, html }, accReleases = []) {
|
|
const releases = scrapeAll(html);
|
|
const next = qu('.pagination .next a');
|
|
|
|
if (next) {
|
|
const url = `https://www.brazzers.com${next}`;
|
|
const qNext = await get(url);
|
|
|
|
return fetchActorReleases(qNext, accReleases.concat(releases));
|
|
}
|
|
|
|
return accReleases.concat(releases);
|
|
}
|
|
|
|
async function scrapeProfile(html, url, actorName) {
|
|
const qProfile = ex(html);
|
|
const { q, qa } = qProfile;
|
|
|
|
const bioKeys = qa('.profile-spec-list label', true).map(key => key.replace(/\n+|\s{2,}/g, '').trim());
|
|
const bioValues = qa('.profile-spec-list var', true).map(value => value.replace(/\n+|\s{2,}/g, '').trim());
|
|
|
|
const bio = bioKeys.reduce((acc, key, index) => ({ ...acc, [key]: bioValues[index] }), {});
|
|
|
|
const profile = {
|
|
name: actorName,
|
|
};
|
|
|
|
profile.description = q('.model-profile-specs p', true);
|
|
|
|
if (bio.Ethnicity) profile.ethnicity = bio.Ethnicity;
|
|
if (bio.Measurements && bio.Measurements.match(/\d+[A-Z]+-\d+-\d+/)) [profile.bust, profile.waist, profile.hip] = bio.Measurements.split('-');
|
|
if (bio['Date of Birth'] && bio['Date of Birth'] !== 'Unknown') profile.birthdate = moment.utc(bio['Date of Birth'], 'MMMM DD, YYYY').toDate();
|
|
if (bio['Birth Location']) profile.birthPlace = bio['Birth Location'];
|
|
if (bio['Pussy Type']) profile.pussy = bio['Pussy Type'].split(',').slice(-1)[0].toLowerCase();
|
|
|
|
if (bio.Height) profile.height = heightToCm(bio.Height);
|
|
if (bio.Weight) profile.weight = lbsToKg(bio.Weight.match(/\d+/)[0]);
|
|
if (bio['Hair Color']) profile.hair = hairMap[bio['Hair Color']] || bio['Hair Color'].toLowerCase();
|
|
|
|
if (bio['Tits Type'] && bio['Tits Type'].match('Natural')) profile.naturalBoobs = true;
|
|
if (bio['Tits Type'] && bio['Tits Type'].match('Enhanced')) profile.naturalBoobs = false;
|
|
|
|
if (bio['Body Art'] && bio['Body Art'].match('Tattoo')) profile.hasTattoos = true;
|
|
if (bio['Body Art'] && bio['Body Art'].match('Piercing')) profile.hasPiercings = true;
|
|
|
|
const avatarEl = q('.big-pic-model-container img');
|
|
if (avatarEl) profile.avatar = `https:${avatarEl.src}`;
|
|
|
|
profile.releases = await fetchActorReleases(qProfile);
|
|
|
|
return profile;
|
|
}
|
|
|
|
async function fetchLatest(site, page = 1) {
|
|
const res = await bhttp.get(`${site.url}/page/${page}/`);
|
|
|
|
return scrapeAll(res.body.toString(), site, false);
|
|
}
|
|
|
|
async function fetchUpcoming(site) {
|
|
const res = await bhttp.get(`${site.url}/`);
|
|
|
|
return scrapeAll(res.body.toString(), site, true);
|
|
}
|
|
|
|
async function fetchScene(url, site) {
|
|
const res = await bhttp.get(url);
|
|
|
|
return scrapeScene(res.body.toString(), url, site);
|
|
}
|
|
|
|
async function fetchProfile(actorName) {
|
|
const searchUrl = 'https://brazzers.com/pornstars-search/';
|
|
const searchRes = await bhttp.get(searchUrl, {
|
|
headers: {
|
|
Cookie: `textSearch=${encodeURIComponent(actorName)};`,
|
|
},
|
|
});
|
|
|
|
const actorLink = scrapeActorSearch(searchRes.body.toString(), searchUrl, actorName);
|
|
|
|
if (actorLink) {
|
|
const url = `https://brazzers.com${actorLink}`;
|
|
const res = await bhttp.get(url);
|
|
|
|
return scrapeProfile(res.body.toString(), url, actorName);
|
|
}
|
|
|
|
return null;
|
|
}
|
|
|
|
module.exports = {
|
|
fetchLatest,
|
|
fetchProfile,
|
|
fetchScene,
|
|
fetchUpcoming,
|
|
};
|