forked from DebaucheryLibrarian/traxxx
109 lines
3.4 KiB
JavaScript
109 lines
3.4 KiB
JavaScript
|
'use strict';
|
||
|
|
||
|
/* eslint-disable newline-per-chained-call */
|
||
|
const bhttp = require('bhttp');
|
||
|
const cheerio = require('cheerio');
|
||
|
const moment = require('moment');
|
||
|
|
||
|
const knex = require('../knex');
|
||
|
const { matchTags } = require('../tags');
|
||
|
|
||
|
function titleExtractor(pathname) {
|
||
|
const components = pathname.split('/')[2].split('-');
|
||
|
const entryId = components.slice(-1)[0];
|
||
|
|
||
|
const title = components.slice(0, -1).reduce((accTitle, word, index) => `${accTitle}${index > 0 ? ' ' : ''}${word.slice(0, 1).toUpperCase()}${word.slice(1)}`, '');
|
||
|
|
||
|
return { title, entryId };
|
||
|
}
|
||
|
|
||
|
function scrapeLatest(html, site) {
|
||
|
const $ = cheerio.load(html, { normalizeWhitespace: true });
|
||
|
const sceneElements = $('.site-list .scene-item').toArray();
|
||
|
|
||
|
return sceneElements.map((item) => {
|
||
|
const element = $(item);
|
||
|
|
||
|
const sceneLinkElement = element.find('a').first();
|
||
|
const { protocol, hostname, pathname } = new URL(sceneLinkElement.attr('href'));
|
||
|
const url = `${protocol}//${hostname}${pathname}`;
|
||
|
const { title, entryId } = titleExtractor(pathname);
|
||
|
|
||
|
const date = moment.utc(element.find('.entry-date').text(), 'MMM D, YYYY').toDate();
|
||
|
const actors = element.find('.contain-actors a').map((actorIndex, actorElement) => $(actorElement).text()).toArray();
|
||
|
|
||
|
const duration = Number(element.find('.scene-runtime').text().slice(0, -4)) * 60;
|
||
|
|
||
|
return {
|
||
|
url,
|
||
|
entryId,
|
||
|
title,
|
||
|
actors,
|
||
|
date,
|
||
|
duration,
|
||
|
rating: null,
|
||
|
site,
|
||
|
};
|
||
|
});
|
||
|
}
|
||
|
|
||
|
async function scrapeScene(html, url, site) {
|
||
|
const $ = cheerio.load(html, { normalizeWhitespace: true });
|
||
|
const sceneElement = $('.scene-info');
|
||
|
|
||
|
const { protocol, hostname, pathname } = new URL(url);
|
||
|
const originalUrl = `${protocol}//${hostname}${pathname}`;
|
||
|
|
||
|
const entryId = originalUrl.split('-').slice(-1)[0];
|
||
|
const title = sceneElement.find('h1.scene-title.grey-text').text();
|
||
|
const description = sceneElement.find('.synopsis').contents().slice(2).text().replace(/[\s\n]+/g, ' ').trim();
|
||
|
|
||
|
const date = moment.utc(sceneElement.find('span.entry-date').text(), 'MMM D, YYYY').toDate();
|
||
|
const actors = $('a.scene-title.grey-text.link').map((actorIndex, actorElement) => $(actorElement).text()).toArray();
|
||
|
|
||
|
const duration = Number(sceneElement.find('.duration-ratings .duration').text().slice(10, -4)) * 60;
|
||
|
|
||
|
const siteName = sceneElement.find('a.site-title').text();
|
||
|
const siteId = siteName.replace(/[\s']+/g, '').toLowerCase();
|
||
|
|
||
|
const rawTags = $('.categories a.cat-tag').map((tagIndex, tagElement) => $(tagElement).text()).toArray();
|
||
|
|
||
|
const [channelSite, tags] = await Promise.all([
|
||
|
knex('sites')
|
||
|
.where({ id: siteId })
|
||
|
.orWhere({ name: siteName })
|
||
|
.first(),
|
||
|
matchTags(rawTags),
|
||
|
]);
|
||
|
|
||
|
return {
|
||
|
url,
|
||
|
entryId,
|
||
|
title,
|
||
|
description,
|
||
|
actors,
|
||
|
date,
|
||
|
duration,
|
||
|
tags,
|
||
|
rating: null,
|
||
|
site: channelSite || site,
|
||
|
};
|
||
|
}
|
||
|
|
||
|
async function fetchLatest(site, page = 1) {
|
||
|
const res = await bhttp.get(`${site.url}?page=${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,
|
||
|
};
|