traxxx/src/scrapers/perfectgonzo.js

150 lines
4.3 KiB
JavaScript
Raw Normal View History

'use strict';
const bhttp = require('bhttp');
const blake2 = require('blake2');
const knex = require('../knex');
const { ex, ctxa } = require('../utils/q');
async function getSiteSlugs() {
return knex('sites')
.pluck('sites.slug')
.join('networks', 'networks.id', 'sites.network_id')
.where('networks.slug', 'perfectgonzo');
}
function getHash(identifier) {
const hash = blake2.createHash('blake2b', { digestLength: 8 });
hash.update(Buffer.from(identifier));
return hash.digest('hex');
}
function extractMaleModelsFromTags(tagContainer) {
if (!tagContainer) {
return [];
}
const tagEls = Array.from(tagContainer.childNodes, node => ({ type: node.nodeType, text: node.textContent.trim() })).filter(node => node.text.length > 0);
const modelLabelIndex = tagEls.findIndex(node => node.text === 'Male Models');
if (modelLabelIndex > -1) {
const nextLabelIndex = tagEls.findIndex((node, index) => index > modelLabelIndex && node.type === 3);
const maleModels = tagEls.slice(modelLabelIndex + 1, nextLabelIndex);
return maleModels.map(model => model.text);
}
return [];
}
async function extractChannelFromPhoto(photo, metaSiteSlugs) {
const siteSlugs = metaSiteSlugs || await getSiteSlugs();
const channelMatch = photo.match(new RegExp(siteSlugs.join('|')));
if (channelMatch) {
return channelMatch[0];
}
return null;
}
async function scrapeLatest(html, site) {
const siteSlugs = await getSiteSlugs();
const { element } = ex(html);
return ctxa(element, '#content-main .itemm').map(({
q, qa, qlength, qdate, qimages,
}) => {
const release = {
site,
meta: {
siteSlugs,
},
};
const sceneLink = q('a');
release.title = sceneLink.title;
release.url = `${site.url}${sceneLink.href}`;
release.date = qdate('.nm-date', 'MM/DD/YYYY');
const slug = new URL(release.url).pathname.split('/')[2];
release.entryId = getHash(`${site.slug}${slug}${release.date.toISOString()}`);
release.actors = release.title.split('&').map(actor => actor.trim());
[release.poster, ...release.photos] = qimages('.bloc-link img');
release.tags = qa('.dropdown ul a', true).slice(1);
release.duration = qlength('.dropdown p:first-child');
return release;
});
}
async function scrapeScene(html, site, url, metaSiteSlugs) {
const {
q, qa, qlength, qdate, qposter, qtrailer,
} = ex(html);
const release = { url, site };
release.title = q('#movie-header h2', true);
release.date = qdate('#movie-header div span', 'MMMM DD, YYYY', /\w+ \d{1,2}, \d{4}/);
release.description = q('.container .mg-md', true);
release.duration = qlength('#video-ribbon .container > div > span:nth-child(3)');
release.actors = qa('#video-info a', true).concat(extractMaleModelsFromTags(q('.tag-container')));
release.tags = qa('.tag-container a', true);
const uhd = q('#video-ribbon .container > div > span:nth-child(2)', true);
if (/4K/.test(uhd)) release.tags = release.tags.concat('4k');
release.photos = qa('.bxslider_pics img').map(el => el.dataset.original || el.src);
release.poster = qposter();
const trailer = qtrailer();
if (trailer) release.trailer = { src: trailer };
if (release.photos.length > 0) release.channel = await extractChannelFromPhoto(release.photos[0], metaSiteSlugs);
if (release.channel) {
const { pathname } = new URL(url);
release.url = `https://${release.channel}.com${pathname}`;
const slug = pathname.split('/')[2];
release.entryId = getHash(`${release.channel}${slug}${release.date.toISOString()}`);
}
return release;
}
async function fetchLatest(site, page = 1) {
const url = `${site.url}/movies/page-${page}`;
const res = await bhttp.get(url);
if (res.statusCode === 200) {
return scrapeLatest(res.body.toString(), site);
}
return [];
}
async function fetchScene(url, site, release) {
const res = await bhttp.get(url);
if (res.statusCode === 200) {
return scrapeScene(res.body.toString(), site, url, release?.meta.siteSlugs);
}
return [];
}
module.exports = {
fetchLatest,
fetchScene,
};