traxxx/src/scrapers/xempire.js

258 lines
8.0 KiB
JavaScript
Raw Normal View History

'use strict';
const Promise = require('bluebird');
const bhttp = require('bhttp');
const cheerio = require('cheerio');
const { JSDOM } = require('jsdom');
const moment = require('moment');
const defaultTags = {
hardx: [],
darkx: ['interracial'],
eroticax: [],
lesbianx: ['lesbian'],
allblackx: ['ebony', 'bbc'],
};
async function fetchPhotos(url) {
const res = await bhttp.get(url);
return res.body.toString();
}
function scrapePhotos(html) {
const $ = cheerio.load(html, { normalizeWhitespace: true });
return $('.preview .imgLink').toArray().map((linkEl) => {
const url = $(linkEl).attr('href');
if (url.match('/join')) {
// URL links to join page instead of full photo, extract thumbnail
const src = $(linkEl).find('img').attr('src');
if (src.match('previews/')) {
// resource often serves full photo at a modifier URL anyway, add as primary source
const highRes = src
.replace('previews/', '')
.replace('_tb.jpg', '.jpg');
// keep original thumbnail as fallback in case full photo is not available
return [highRes, src];
}
return src;
}
// URL links to full photo
return url;
});
}
2019-12-09 04:00:49 +00:00
async function getPhotos(albumPath, siteDomain) {
const albumUrl = `https://${siteDomain}${albumPath}`;
try {
const html = await fetchPhotos(albumUrl);
const $ = cheerio.load(html, { normalizeWhitespace: true });
const photos = scrapePhotos(html);
const pages = $('.paginatorPages a').map((pageIndex, pageElement) => $(pageElement).attr('href')).toArray();
const otherPhotos = await Promise.map(pages, async (page) => {
const pageUrl = `https://${siteDomain}${page}`;
const pageHtml = await fetchPhotos(pageUrl);
return scrapePhotos(pageHtml);
}, {
concurrency: 2,
});
return photos.concat(otherPhotos.flat());
} catch (error) {
console.error(`Failed to fetch XEmpire photos from ${albumPath}: ${error.message}`);
return [];
}
}
function scrape(html, site) {
const $ = cheerio.load(html, { normalizeWhitespace: true });
const scenesElements = $('li[data-itemtype=scene]').toArray();
return scenesElements.map((element) => {
const sceneLinkElement = $(element).find('.sceneTitle a');
const url = `${site.url}${sceneLinkElement.attr('href')}`;
const title = sceneLinkElement.attr('title');
const entryId = $(element).attr('data-itemid');
const date = moment
.utc($(element).find('.sceneDate').text(), 'MM-DD-YYYY')
.toDate();
const actors = $(element).find('.sceneActors a')
.map((actorIndex, actorElement) => $(actorElement).attr('title'))
.toArray();
const [likes, dislikes] = $(element).find('.value')
.toArray()
.map(value => Number($(value).text()));
const poster = $(element).find('.imgLink img').attr('data-original');
const trailer = `https://videothumb.gammacdn.com/307x224/${entryId}.mp4`;
return {
url,
entryId,
title,
actors,
director: 'Mason',
date,
poster,
trailer: {
src: trailer,
quality: 224,
},
rating: {
likes,
dislikes,
},
site,
};
});
}
async function scrapeScene(html, url, site) {
const $ = cheerio.load(html, { normalizeWhitespace: true });
const json = $('script[type="application/ld+json"]').html();
const json2 = $('script:contains("dataLayer = ")').html();
const videoJson = $('script:contains("window.ScenePlayerOptions")').html();
const data = JSON.parse(json)[0];
const data2 = JSON.parse(json2.slice(json2.indexOf('[{'), -1))[0];
const videoData = JSON.parse(videoJson.slice(videoJson.indexOf('{"id":'), videoJson.indexOf('};') + 1));
const entryId = data2.sceneDetails.sceneId || new URL(url).pathname.split('/').slice(-1)[0];
const title = data2.sceneDetails.sceneTitle || $('meta[name="twitter:title"]').attr('content');
const description = data2.sceneDetails.sceneDescription || data.description || $('meta[name="twitter:description"]').attr('content');
// date in data object is not the release date of the scene, but the date the entry was added
const date = moment.utc($('.updatedDate').first().text(), 'MM-DD-YYYY').toDate();
const actors = (data2.sceneDetails.sceneActors || data.actor).map(actor => actor.actorName || actor.name);
const stars = (data.aggregateRating.ratingValue / data.aggregateRating.bestRating) * 5;
const duration = moment.duration(data.duration.slice(2).split(':')).asSeconds();
const siteDomain = $('meta[name="twitter:domain"]').attr('content') || 'allblackx.com'; // only AllBlackX has no twitter domain, no other useful hints available
const siteSlug = siteDomain && siteDomain.split('.')[0].toLowerCase();
const siteUrl = siteDomain && `https://www.${siteDomain}`;
const poster = videoData.picPreview;
const trailer = `${videoData.playerOptions.host}${videoData.url}`;
const photos = await getPhotos($('.picturesItem a').attr('href'), siteDomain, site);
const rawTags = data.keywords.split(', ');
const tags = [...defaultTags[siteSlug], ...rawTags];
return {
url: `${siteUrl}/en/video/${new URL(url).pathname.split('/').slice(-2).join('/')}`,
entryId,
title,
date,
actors,
director: 'Mason',
description,
duration,
poster,
photos,
trailer: {
src: trailer,
quality: parseInt(videoData.sizeOnLoad, 10),
},
tags,
rating: {
stars,
},
site,
channel: siteSlug,
};
}
function scrapeActorSearch(html, url, actorName) {
const { document } = new JSDOM(html).window;
const actorLink = document.querySelector(`a[title="${actorName}" i]`);
return actorLink ? actorLink.href : null;
}
function scrapeProfile(html, url, actorName) {
const { document } = new JSDOM(html).window;
const avatarEl = document.querySelector('img.actorPicture');
const descriptionEl = document.querySelector('.actorBio p:not(.bioTitle)');
const profile = {
name: actorName,
};
if (avatarEl) profile.avatar = avatarEl.src;
if (descriptionEl) profile.description = descriptionEl.textContent.trim();
profile.releases = Array.from(document.querySelectorAll('.sceneList .scene a.imgLink'), el => `https://xempire.com${el.href}`);
return profile;
}
async function fetchLatest(site, page = 1) {
const res = await bhttp.get(`${site.url}/en/videos/AllCategories/0/${page}`);
return scrape(res.body.toString(), site);
}
async function fetchUpcoming(site) {
const res = await bhttp.get(`${site.url}/en/videos/AllCategories/0/1/upcoming`);
return scrape(res.body.toString(), site);
}
async function fetchScene(url, site) {
const res = await bhttp.get(url);
return scrapeScene(res.body.toString(), url, site);
}
async function fetchProfile(actorName) {
const actorSlug = actorName.toLowerCase().replace(/\s+/, '+');
const searchUrl = `https://www.xempire.com/en/search/xempire/actor/${actorSlug}`;
const searchRes = await bhttp.get(searchUrl);
if (searchRes.statusCode !== 200) {
return null;
}
const actorUrl = scrapeActorSearch(searchRes.body.toString(), searchUrl, actorName);
if (actorUrl) {
const url = `https://xempire.com${actorUrl}`;
const actorRes = await bhttp.get(url);
if (actorRes.statusCode !== 200) {
return null;
}
return scrapeProfile(actorRes.body.toString(), url, actorName);
}
return null;
}
module.exports = {
fetchLatest,
fetchProfile,
fetchUpcoming,
fetchScene,
};