traxxx/src/scrapers/vixen.js

91 lines
2.2 KiB
JavaScript
Raw Normal View History

'use strict';
/* eslint-disable */
const bhttp = require('bhttp');
const cheerio = require('cheerio');
const moment = require('moment');
const { matchTags } = require('../tags');
function scrapeLatest(html, site) {
const $ = cheerio.load(html, { normalizeWhitespace: true });
const stateObject = $('script:contains("INITIAL_STATE")');
const { videos: scenes } = JSON.parse(stateObject.html().trim().slice(27, -1));
return scenes.map((scene) => {
const shootId = scene.newId;
const title = scene.title;
const url = `${site.url}${scene.targetUrl}`;
const date = moment.utc(scene.releaseDateFormatted, 'MMMM DD, YYYY').toDate();
const actors = scene.models;
const stars = Number(scene.textRating) / 2;
return {
url,
shootId,
title,
actors,
date,
rating: {
stars,
},
site,
};
});
}
async function scrapeScene(html, url, site) {
const $ = cheerio.load(html, { normalizeWhitespace: true });
const { pathname, search } = new URL(url);
const stateObject = $('script:contains("INITIAL_STATE")');
const data = JSON.parse(stateObject.html().trim().slice(27, -1));
const scene = data.page.data[`${pathname}${search}`].data.video;
const shootId = scene.newId;
const title = scene.title;
const date = new Date(scene.releaseDate);
const actors = scene.models;
const stars = scene.totalRateVal;
const rawTags = scene.tags;
const tags = await matchTags(rawTags);
const duration = scene.runLength;
const director = scene.directorNames;
return {
url,
shootId,
title,
actors,
director,
date,
duration,
tags,
rating: {
stars,
},
site,
};
}
async function fetchLatest(site) {
const res = await bhttp.get(`${site.url}/videos`);
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,
};