traxxx/src/scrapers/legalporno.js

91 lines
2.7 KiB
JavaScript
Raw Normal View History

'use strict';
const bhttp = require('bhttp');
const cheerio = require('cheerio');
const moment = require('moment');
const { matchTags } = require('../tags');
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)\d+/); // detect studio prefixes
const shootId = sceneIdMatch ? sceneIdMatch[0] : null;
const title = sceneIdMatch ? titleComponents.slice(0, -1).join(' ') : originalTitle;
return { shootId, title };
}
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();
return {
url,
shootId,
entryId,
title,
date,
site,
};
});
}
async function scrapeScene(html, url, site) {
const $ = cheerio.load(html, { normalizeWhitespace: true });
const originalTitle = $('h1.watchpage-title').text().trim();
const { shootId, title } = extractTitle(originalTitle);
const entryId = new URL(url).pathname.split('/')[2];
const date = moment.utc($('span[title="Release date"] a').text(), 'YYYY-MM-DD').toDate();
const [actorsElement, tagsElement] = $('.scene-description__row').toArray();
const actors = $(actorsElement)
.find('a[href*="com/model"]')
.map((actorIndex, actorElement) => $(actorElement).text()).toArray();
const duration = moment.duration($('span[title="Runtime"]').text().trim()).asSeconds();
const rawTags = $(tagsElement).find('a').map((tagIndex, tagElement) => $(tagElement).text()).toArray();
const tags = await matchTags(rawTags);
return {
url,
shootId,
entryId,
title,
date,
actors,
duration,
tags,
site,
};
}
async function fetchLatest(site, page = 1) {
const res = await bhttp.get(`${site.url}/new-videos/${page}`);
return scrapeLatest(res.body.toString(), site);
}
async function fetchScene(url, site) {
const res = await bhttp.get(url);
return scrapeScene(res.body.toString(), url, site);
}
module.exports = {
fetchLatest,
fetchScene,
};