traxxx/src/scrapers/legalporno.js

209 lines
6.5 KiB
JavaScript
Raw Normal View History

'use strict';
const bhttp = require('bhttp');
const { JSDOM } = require('jsdom');
const cheerio = require('cheerio');
const moment = require('moment');
2020-04-11 20:49:37 +00:00
const slugify = require('../utils/slugify');
function extractTitle(originalTitle) {
const titleComponents = originalTitle.split(' ');
const sceneIdMatch = titleComponents.slice(-1)[0].match(/(AB|AF|GP|SZ|IV|GIO|RS|TW|MA|FM|SAL|NR|AA|GL|BZ|FS|KS|OTS|NF)\d+/); // detect studio prefixes
const shootId = sceneIdMatch ? sceneIdMatch[0] : null;
const title = sceneIdMatch ? titleComponents.slice(0, -1).join(' ') : originalTitle;
return { shootId, title };
}
2019-10-29 00:47:16 +00:00
function getPoster(posterElement, sceneId) {
const posterStyle = posterElement.attr('style');
2019-10-29 00:47:16 +00:00
if (posterStyle) {
return posterStyle.slice(posterStyle.indexOf('(') + 1, -1);
}
2019-10-29 00:47:16 +00:00
const posterRange = posterElement.attr('data-casting');
const posterRangeData = posterRange ? JSON.parse(posterRange) : null;
const posterTimeRange = posterRangeData[Math.floor(Math.random() * posterRangeData.length)];
2019-10-29 00:47:16 +00:00
if (!posterTimeRange) {
return null;
}
if (typeof posterTimeRange === 'number') {
// poster time is already a single time value
return `https://legalporno.com/casting/${sceneId}/${posterTimeRange}`;
}
2019-10-29 00:47:16 +00:00
const [max, min] = posterTimeRange.split('-');
const posterTime = Math.floor(Math.random() * (Number(max) - Number(min) + 1) + Number(min));
2019-10-29 00:47:16 +00:00
return `https://legalporno.com/casting/${sceneId}/${posterTime}`;
2019-10-29 00:47:16 +00:00
}
function scrapeLatest(html, site) {
const $ = cheerio.load(html, { normalizeWhitespace: true });
const scenesElements = $('.thumbnails > div').toArray();
return scenesElements.map((element) => {
const sceneLinkElement = $(element).find('.thumbnail-title a');
const url = sceneLinkElement.attr('href');
const originalTitle = sceneLinkElement.text().trim(); // title attribute breaks when they use \\ escaping
const { shootId, title } = extractTitle(originalTitle);
const entryId = new URL(url).pathname.split('/')[2];
const date = moment.utc($(element).attr('release'), 'YYYY/MM/DD').toDate();
const sceneId = $(element).attr('data-content');
const posterElement = $(element).find('.thumbnail-avatar');
const poster = getPoster(posterElement, sceneId);
return {
url,
shootId,
entryId,
title,
date,
poster,
site,
};
});
}
2019-10-29 00:47:16 +00:00
async function scrapeScene(html, url, site, useGallery) {
const $ = cheerio.load(html, { normalizeWhitespace: true });
const playerObject = $('script:contains("new WatchPage")').html();
const playerData = playerObject && playerObject.slice(playerObject.indexOf('{"swf":'), playerObject.lastIndexOf('},') + 1);
const data = playerData && JSON.parse(playerData);
const release = { url };
const originalTitle = $('h1.watchpage-title').text().trim();
const { shootId, title } = extractTitle(originalTitle);
release.shootId = shootId;
release.entryId = new URL(url).pathname.split('/')[2];
release.title = title;
release.date = moment.utc($('span[title="Release date"] a').text(), 'YYYY-MM-DD').toDate();
const [actorsElement, tagsElement, descriptionElement] = $('.scene-description__row').toArray();
release.description = $('meta[name="description"]')?.attr('content')?.trim()
|| (descriptionElement && $(descriptionElement).find('dd').text().trim());
release.actors = $(actorsElement)
.find('a[href*="com/model"]')
.map((actorIndex, actorElement) => $(actorElement).text()).toArray();
release.duration = moment.duration($('span[title="Runtime"]').text().trim()).asSeconds();
release.tags = $(tagsElement).find('a').map((tagIndex, tagElement) => $(tagElement).text()).toArray();
2019-10-29 00:47:16 +00:00
const photos = useGallery
? $('.gallery a img').map((photoIndex, photoElement) => $(photoElement).attr('src')).toArray()
: $('.screenshots img').map((photoIndex, photoElement) => $(photoElement).attr('src')).toArray();
2019-10-29 00:47:16 +00:00
release.photos = photos.map((source) => {
// source without parameters sometimes serves larger preview photo
const { origin, pathname } = new URL(source);
return `${origin}${pathname}`;
/* disable thumbnail as fallback, usually enough high res photos available
return [
`${origin}${pathname}`,
source,
];
*/
});
const posterStyle = $('#player').attr('style');
const poster = posterStyle.slice(posterStyle.indexOf('(') + 1, -1);
release.poster = poster || release.photos.slice(Math.floor(release.photos.length / 3) * -1); // poster unavailable, try last 1/3rd of high res photos as fallback
if (data) {
const qualityMap = {
web: 240,
vga: 480,
hd: 720,
'1080p': 1080,
};
release.trailer = data.clip.qualities.map(trailer => ({
src: trailer.src,
type: trailer.type,
quality: qualityMap[trailer.quality] || trailer.quality,
}));
}
2019-10-29 00:47:16 +00:00
const studioName = $('.watchpage-studioname').first().text().trim();
release.studio = slugify(studioName, '');
return release;
}
async function scrapeProfile(html, _url, actorName) {
const { document } = new JSDOM(html).window;
const profile = {
name: actorName,
};
const avatarEl = document.querySelector('.model--avatar img[src^="http"]');
const entries = Array.from(document.querySelectorAll('.model--description tr'), el => el.textContent.replace(/\n/g, '').split(':'));
const bio = entries
.filter(entry => entry.length === 2) // ignore entries without ':' (About section, see Blanche Bradburry)
.reduce((acc, [key, value]) => ({ ...acc, [key.trim()]: value.trim() }), {});
profile.birthPlace = bio.Nationality;
if (bio.Age) profile.age = bio.Age;
if (avatarEl) profile.avatar = avatarEl.src;
return profile;
}
async function fetchLatest(site, page = 1) {
const res = await bhttp.get(`${site.url}/new-videos/${page}`);
return scrapeLatest(res.body.toString(), site);
}
async function fetchScene(url, site) {
const useGallery = true;
2019-10-29 00:47:16 +00:00
// TODO: fall back on screenshots when gallery is not available
const res = useGallery
? await bhttp.get(`${url}/gallery#gallery`)
: await bhttp.get(`${url}/screenshots#screenshots`);
return scrapeScene(res.body.toString(), url, site, useGallery);
}
async function fetchProfile(actorName) {
const res = await bhttp.get(`https://www.legalporno.com/api/autocomplete/search?q=${actorName.replace(' ', '+')}`);
const data = res.body;
const result = data.terms.find(item => item.type === 'model');
if (result) {
const bioRes = await bhttp.get(result.url);
const html = bioRes.body.toString();
return scrapeProfile(html, result.url, actorName);
}
return null;
}
module.exports = {
fetchLatest,
fetchProfile,
fetchScene,
};