371 lines
12 KiB
JavaScript
371 lines
12 KiB
JavaScript
'use strict';
|
|
|
|
// const Promise = require('bluebird');
|
|
const bhttp = require('bhttp');
|
|
const cheerio = require('cheerio');
|
|
const { JSDOM } = require('jsdom');
|
|
const moment = require('moment');
|
|
|
|
const { heightToCm } = require('../utils/convert');
|
|
|
|
async function fetchPhotos(url) {
|
|
const res = await bhttp.get(url);
|
|
|
|
return res.body.toString();
|
|
}
|
|
|
|
function scrapePhotos(html, type) {
|
|
const $ = cheerio.load(html, { normalizeWhitespace: true });
|
|
|
|
const photos = $('.photo_gallery_thumbnail_wrapper .thumbs')
|
|
.toArray()
|
|
.map((photoElement) => {
|
|
const src = $(photoElement).attr('src');
|
|
|
|
// high res often available in alternative directories, but not always, provide original as fallback
|
|
if (type === 'caps') {
|
|
return [
|
|
src.replace('capthumbs/', 'caps/'),
|
|
src,
|
|
];
|
|
}
|
|
|
|
return [
|
|
src.replace('thumbs/', 'photos/'),
|
|
src.replace('thumbs/', '1600watermarked/'),
|
|
src.replace('thumbs/', '1280watermarked/'),
|
|
src.replace('thumbs/', '1024watermarked/'),
|
|
src,
|
|
];
|
|
});
|
|
|
|
return photos;
|
|
}
|
|
|
|
async function getPhotosLegacy(entryId, site, type = 'highres', page = 1) {
|
|
const albumUrl = `${site.url}/trial/gallery.php?id=${entryId}&type=${type}&page=${page}`;
|
|
|
|
console.warn(`Jules Jordan is using legacy photo scraper for ${albumUrl} (page ${page})`);
|
|
|
|
const html = await fetchPhotos(albumUrl);
|
|
const $ = cheerio.load(html, { normalizeWhitespace: true });
|
|
|
|
// don't add first URL to pages to prevent unnecessary duplicate request
|
|
const photos = scrapePhotos(html, type);
|
|
const pages = Array.from(new Set($('.page_numbers a').toArray().map(el => $(el).attr('href'))));
|
|
|
|
const otherPhotos = pages
|
|
? await Promise.map(pages, async (pageX) => {
|
|
const pageUrl = `https://www.julesjordan.com/trial/${pageX}`;
|
|
const pageHtml = await fetchPhotos(pageUrl);
|
|
|
|
return scrapePhotos(pageHtml, type);
|
|
}, {
|
|
concurrency: 2,
|
|
})
|
|
: [];
|
|
|
|
const allPhotos = photos.concat(otherPhotos.flat());
|
|
|
|
if (allPhotos.length === 0 && type === 'highres') {
|
|
// photos not available, try for screencaps instead
|
|
return getPhotosLegacy(entryId, site, 'caps', 1);
|
|
}
|
|
|
|
return allPhotos;
|
|
}
|
|
|
|
async function getPhotos(entryId, site, type = 'highres', page = 1) {
|
|
const albumUrl = `${site.url}/trial/gallery.php?id=${entryId}&type=${type}&page=${page}`;
|
|
|
|
const res = await bhttp.get(albumUrl);
|
|
const html = res.body.toString();
|
|
|
|
const sourceLines = html.split(/\n/).filter(line => line.match(/ptx\["\w+"\]/));
|
|
const sources = sourceLines.reduce((acc, sourceLine) => {
|
|
const quality = sourceLine.match(/\["\w+"\]/)[0].slice(2, -2);
|
|
const source = sourceLine.slice(sourceLine.indexOf('/trial'), sourceLine.indexOf('.jpg') + 4);
|
|
|
|
if (!source) return acc;
|
|
if (!acc[quality]) acc[quality] = [];
|
|
|
|
acc[quality].push(`${site.url}${source}`);
|
|
|
|
return acc;
|
|
}, {});
|
|
|
|
if (type === 'highres') {
|
|
if (sources['1600'] && sources['1600'].length > 0) return sources['1600'];
|
|
if (sources['1280'] && sources['1280'].length > 0) return sources['1280'];
|
|
if (sources['1024'] && sources['1024'].length > 0) return sources['1024'];
|
|
if (sources.Thumbs && sources.Thumbs.length > 0) return sources.Thumbs;
|
|
|
|
// no photos available, try for screencaps instead
|
|
return getPhotos(entryId, site, 'caps', 1);
|
|
}
|
|
|
|
if (sources.jpg && sources.jpg.length > 0) return sources.jpg;
|
|
if (sources['Video Cap Thumbs'] && sources['Video Cap Thumbs'].length > 0) return sources['Video Cap Thumbs'];
|
|
|
|
// no screencaps available either, try legacy scraper just in case
|
|
return getPhotosLegacy(entryId, site, 'highres', 1);
|
|
}
|
|
|
|
function scrapeLatest(html, site) {
|
|
const $ = cheerio.load(html, { normalizeWhitespace: true });
|
|
const scenesElements = $('.update_details').toArray();
|
|
|
|
return scenesElements.map((element) => {
|
|
const photoElement = $(element).find('a img.thumbs');
|
|
const photoCount = Number(photoElement.attr('cnt'));
|
|
const [poster, ...photos] = Array.from({ length: photoCount }, (value, index) => {
|
|
const src = photoElement.attr(`src${index}_1x`) || photoElement.attr(`src${index}`);
|
|
|
|
if (!src) return null;
|
|
if (src.match(/^http/)) return src;
|
|
|
|
return `${site.url}${src}`;
|
|
}).filter(photoUrl => photoUrl);
|
|
|
|
const sceneLinkElement = $(element).children('a').eq(1);
|
|
const url = sceneLinkElement.attr('href');
|
|
const title = sceneLinkElement.text();
|
|
|
|
const entryId = $(element).attr('data-setid');
|
|
|
|
const date = moment
|
|
.utc($(element).find('.update_date').text(), 'MM/DD/YYYY')
|
|
.toDate();
|
|
|
|
const actors = $(element).find('.update_models a')
|
|
.map((actorIndex, actorElement) => $(actorElement).text())
|
|
.toArray();
|
|
|
|
return {
|
|
url,
|
|
entryId,
|
|
title,
|
|
actors,
|
|
date,
|
|
poster,
|
|
photos,
|
|
site,
|
|
};
|
|
});
|
|
}
|
|
|
|
function scrapeUpcoming(html, site) {
|
|
const $ = cheerio.load(html, { normalizeWhitespace: true });
|
|
const scenesElements = $('#coming_soon_carousel').find('.table').toArray();
|
|
|
|
return scenesElements.map((element) => {
|
|
const entryId = $(element).find('.upcoming_updates_thumb').attr('id').match(/\d+/)[0];
|
|
|
|
const details = $(element).find('.update_details_comingsoon')
|
|
.eq(1)
|
|
.children()
|
|
.remove();
|
|
|
|
const title = details
|
|
.end()
|
|
.text()
|
|
.trim();
|
|
|
|
const actors = details
|
|
.text()
|
|
.trim()
|
|
.split(', ');
|
|
|
|
const date = moment
|
|
.utc($(element).find('.update_date_comingsoon').text().slice(7), 'MM/DD/YYYY')
|
|
.toDate();
|
|
|
|
const photoElement = $(element).find('a img.thumbs');
|
|
const posterPath = photoElement.attr('src');
|
|
const poster = posterPath.match(/^http/) ? posterPath : `${site.url}${posterPath}`;
|
|
|
|
const videoClass = $(element).find('.update_thumbnail div').attr('class');
|
|
const videoScript = $(element).find(`script:contains(${videoClass})`).html();
|
|
const trailer = videoScript.slice(videoScript.indexOf('https://'), videoScript.indexOf('.mp4') + 4);
|
|
|
|
return {
|
|
url: null,
|
|
entryId,
|
|
title,
|
|
date,
|
|
actors,
|
|
poster,
|
|
trailer: {
|
|
src: trailer,
|
|
},
|
|
rating: null,
|
|
site,
|
|
};
|
|
});
|
|
}
|
|
|
|
async function scrapeScene(html, url, site) {
|
|
const $ = cheerio.load(html, { normalizeWhitespace: true });
|
|
|
|
const release = { url, site };
|
|
|
|
release.title = $('.title_bar_hilite').text().trim();
|
|
[release.entryId] = $('.suggest_tags a').attr('href').match(/\d+/);
|
|
|
|
const dateElement = $('.update_date').text().trim();
|
|
const dateComment = $('*')
|
|
.contents()
|
|
.toArray()
|
|
.find(({ type, data }) => type === 'comment' && data.match('Date OFF'));
|
|
|
|
if (dateElement) {
|
|
release.date = moment
|
|
.utc($('.update_date').text(), 'MM/DD/YYYY')
|
|
.toDate();
|
|
}
|
|
|
|
if (dateComment) {
|
|
release.date = moment
|
|
.utc(dateComment.nodeValue.match(/\d{2}\/\d{2}\/\d{4}/), 'MM/DD/YYYY')
|
|
.toDate();
|
|
}
|
|
|
|
release.description = $('.update_description').text().trim();
|
|
|
|
release.actors = $('.backgroundcolor_info > .update_models a')
|
|
.map((_actorIndex, actorElement) => $(actorElement).text())
|
|
.toArray();
|
|
|
|
const infoLines = $('script:contains("useimage")')
|
|
.html()
|
|
.split('\n');
|
|
|
|
const posterPath = infoLines.find(line => line.match('useimage')).replace('useimage = "', '').slice(0, -2);
|
|
if (posterPath) release.poster = posterPath.match(/^http/) ? posterPath : `${site.url}${posterPath}`;
|
|
|
|
const trailerLine = infoLines.find(line => line.match('movie["Trailer_720"]'));
|
|
|
|
if (site.slug !== 'manuelferrara') {
|
|
release.trailer = {
|
|
src: trailerLine.slice(trailerLine.indexOf('path:"') + 6, trailerLine.indexOf('",movie')),
|
|
quality: 720,
|
|
};
|
|
}
|
|
|
|
release.photos = await getPhotos(release.entryId, site);
|
|
|
|
release.tags = $('.update_tags a').map((tagIndex, tagElement) => $(tagElement).text()).toArray();
|
|
release.movie = $('.update_dvds a').attr('href');
|
|
|
|
release.stars = Number($('.avg_rating').text().trim().replace(/[\s|Avg Rating:]/g, ''));
|
|
|
|
return release;
|
|
}
|
|
|
|
function scrapeMovie(html, url, site) {
|
|
const { document } = new JSDOM(html).window;
|
|
const movie = { url, site };
|
|
|
|
movie.entryId = document.querySelector('.dvd_details_overview .rating_box').dataset.id;
|
|
movie.title = document.querySelector('.title_bar span').textContent;
|
|
movie.covers = Array.from(document.querySelectorAll('#dvd-cover-flip > a'), el => el.href);
|
|
movie.channel = document.querySelector('.update_date a').textContent;
|
|
movie.date = new Date();
|
|
movie.releases = Array.from(document.querySelectorAll('.cell.dvd_info > a'), el => el.href);
|
|
|
|
return movie;
|
|
}
|
|
|
|
function scrapeProfile(html, url, actorName) {
|
|
const { document } = new JSDOM(html).window;
|
|
|
|
const bio = document.querySelector('.model_bio').textContent;
|
|
const avatarEl = document.querySelector('.model_bio_pic');
|
|
|
|
const profile = {
|
|
name: actorName,
|
|
};
|
|
|
|
const heightString = bio.match(/\d+ feet \d+ inches/);
|
|
const ageString = bio.match(/Age:\s*\d{2}/);
|
|
const measurementsString = bio.match(/\w+-\d+-\d+/);
|
|
|
|
if (heightString) profile.height = heightToCm(heightString[0]);
|
|
if (ageString) profile.age = Number(ageString[0].match(/\d{2}/)[0]);
|
|
if (measurementsString) [profile.bust, profile.waist, profile.hip] = measurementsString[0].split('-');
|
|
|
|
if (avatarEl) {
|
|
const src = avatarEl.innerHTML.slice(avatarEl.innerHTML.indexOf('src') + 5, avatarEl.innerHTML.indexOf('set.jpg') + 7).trim();
|
|
const src0 = avatarEl.innerHTML.slice(avatarEl.innerHTML.indexOf('src0') + 6, avatarEl.innerHTML.indexOf('set.jpg') + 7).trim();
|
|
const src1 = avatarEl.innerHTML.slice(avatarEl.innerHTML.indexOf('src0_1x') + 9, avatarEl.innerHTML.indexOf('1x.jpg') + 6).trim();
|
|
const src2 = avatarEl.innerHTML.slice(avatarEl.innerHTML.indexOf('src0_2x') + 9, avatarEl.innerHTML.indexOf('2x.jpg') + 6).trim();
|
|
const src3 = avatarEl.innerHTML.slice(avatarEl.innerHTML.indexOf('src0_3x') + 9, avatarEl.innerHTML.indexOf('3x.jpg') + 6).trim();
|
|
|
|
const avatar = src3 || src2 || src1 || src0 || src;
|
|
|
|
if (avatar) profile.avatar = avatar;
|
|
}
|
|
|
|
profile.releases = Array.from(document.querySelectorAll('.category_listing_block .update_details > a:first-child'), el => el.href);
|
|
|
|
return profile;
|
|
}
|
|
|
|
async function fetchLatest(site, page = 1) {
|
|
const res = await bhttp.get(`${site.url}/trial/categories/movies_${page}_d.html`);
|
|
|
|
return scrapeLatest(res.body.toString(), site);
|
|
}
|
|
|
|
async function fetchUpcoming(site) {
|
|
const res = await bhttp.get(`${site.url}/trial/index.php`);
|
|
|
|
return scrapeUpcoming(res.body.toString(), site);
|
|
}
|
|
|
|
async function fetchScene(url, site) {
|
|
const res = await bhttp.get(url);
|
|
|
|
return scrapeScene(res.body.toString(), url, site);
|
|
}
|
|
|
|
async function fetchMovie(url, site) {
|
|
const res = await bhttp.get(url);
|
|
|
|
return scrapeMovie(res.body.toString(), url, site);
|
|
}
|
|
|
|
async function fetchProfile(actorName) {
|
|
const actorSlugA = actorName.toLowerCase().replace(/\s+/g, '-');
|
|
const actorSlugB = actorName.toLowerCase().replace(/\s+/g, '');
|
|
|
|
const urlA = `https://julesjordan.com/trial/models/${actorSlugA}.html`;
|
|
const urlB = `https://julesjordan.com/trial/models/${actorSlugB}.html`;
|
|
|
|
const resA = await bhttp.get(urlA);
|
|
|
|
if (resA.statusCode === 200) {
|
|
const profile = scrapeProfile(resA.body.toString(), urlA, actorName);
|
|
|
|
return profile;
|
|
}
|
|
|
|
const resB = await bhttp.get(urlB);
|
|
|
|
if (resB.statusCode === 200) {
|
|
const profile = scrapeProfile(resB.body.toString(), urlB, actorName);
|
|
|
|
return profile;
|
|
}
|
|
|
|
return null;
|
|
}
|
|
|
|
module.exports = {
|
|
fetchLatest,
|
|
fetchMovie,
|
|
fetchProfile,
|
|
fetchUpcoming,
|
|
fetchScene,
|
|
};
|