Added Mike Adriano scraper (True Anal, All Anal, Swallowed, Nympho). Updated README.
This commit is contained in:
256
src/scrapers/mikeadriano.js
Normal file
256
src/scrapers/mikeadriano.js
Normal file
@@ -0,0 +1,256 @@
|
||||
'use strict';
|
||||
|
||||
/* eslint-disable newline-per-chained-call */
|
||||
const bhttp = require('bhttp');
|
||||
const { JSDOM } = require('jsdom');
|
||||
const cheerio = require('cheerio');
|
||||
const moment = require('moment');
|
||||
|
||||
const { matchTags } = require('../tags');
|
||||
|
||||
const defaultTags = {
|
||||
swallowed: ['blowjob', 'deepthroat', 'facefuck'],
|
||||
trueanal: ['anal'],
|
||||
allanal: ['anal', 'fmf'],
|
||||
nympho: [],
|
||||
};
|
||||
|
||||
const descriptionTags = {
|
||||
'anal cream pie': 'anal creampie',
|
||||
'ass to mouth': 'ass to mouth',
|
||||
'cream pie in her ass': 'anal creampie',
|
||||
'eats ass': 'ass eating',
|
||||
facial: 'facial',
|
||||
gaped: 'gaping',
|
||||
gapes: 'gaping',
|
||||
gape: 'gaping',
|
||||
'rectal cream pie': 'anal creampie',
|
||||
rimming: 'ass eating',
|
||||
};
|
||||
|
||||
function deriveTagsFromDescription(description) {
|
||||
const matches = (description || '').toLowerCase().match(new RegExp(Object.keys(descriptionTags).join('|'), 'g'));
|
||||
|
||||
return matches
|
||||
? matches.map(match => descriptionTags[match])
|
||||
: [];
|
||||
}
|
||||
|
||||
async function scrapeLatestA(html, site) {
|
||||
const { document } = new JSDOM(html).window;
|
||||
const sceneElements = document.querySelectorAll('.content-item-large, .content-item');
|
||||
|
||||
return Promise.all(Array.from(sceneElements, async (element) => {
|
||||
const $ = cheerio.load(element.innerHTML, { normalizeWhitespace: true });
|
||||
|
||||
const titleElement = element.querySelector('h3.title a');
|
||||
const title = titleElement.textContent;
|
||||
const url = titleElement.href;
|
||||
const entryId = url.split('/').slice(-2)[0];
|
||||
|
||||
const descriptionElement = element.querySelector('.desc');
|
||||
const description = descriptionElement && descriptionElement.textContent.trim();
|
||||
const date = moment(element.querySelector('.date, time').textContent, 'Do MMM YYYY').toDate();
|
||||
|
||||
const actors = Array.from(element.querySelectorAll('h4.models a'), actorElement => actorElement.textContent);
|
||||
|
||||
const durationString = element.querySelector('.total-time').textContent.trim();
|
||||
// timestamp is somethines 00:00, sometimes 0:00:00
|
||||
const duration = durationString.split(':').length === 3
|
||||
? moment.duration(durationString).asSeconds()
|
||||
: moment.duration(`00:${durationString}`).asSeconds();
|
||||
|
||||
const ratingElement = element.querySelector('.rating');
|
||||
const stars = ratingElement && ratingElement.dataset.rating;
|
||||
|
||||
const [poster, ...primaryPhotos] = Array.from(element.querySelectorAll('img'), imageElement => imageElement.src);
|
||||
const secondaryPhotos = $('.thumb-top, .thumb-bottom')
|
||||
.map((photoIndex, photoElement) => $(photoElement).css()['background-image'])
|
||||
.toArray()
|
||||
.map(photoUrl => photoUrl.slice(photoUrl.indexOf('http'), photoUrl.indexOf('.jpg') + 4));
|
||||
|
||||
const photos = [...primaryPhotos, ...secondaryPhotos];
|
||||
const tags = await matchTags([...defaultTags[site.slug], ...deriveTagsFromDescription(description)]);
|
||||
|
||||
const scene = {
|
||||
url,
|
||||
entryId,
|
||||
title,
|
||||
description,
|
||||
actors,
|
||||
director: 'Mike Adriano',
|
||||
date,
|
||||
duration,
|
||||
tags,
|
||||
poster,
|
||||
photos,
|
||||
rating: {
|
||||
stars,
|
||||
},
|
||||
site,
|
||||
};
|
||||
|
||||
return scene;
|
||||
}));
|
||||
}
|
||||
|
||||
async function scrapeLatestB(html, site) {
|
||||
const { document } = new JSDOM(html).window;
|
||||
const sceneElements = document.querySelectorAll('.content-border');
|
||||
|
||||
return Promise.all(Array.from(sceneElements, async (element) => {
|
||||
const $ = cheerio.load(element.innerHTML, { normalizeWhitespace: true });
|
||||
|
||||
const titleElement = element.querySelector('.content-title-wrap a');
|
||||
const title = titleElement.title || titleElement.textContent.trim();
|
||||
const url = titleElement.href;
|
||||
const entryId = url.split('/').slice(-2)[0];
|
||||
|
||||
const description = element.querySelector('.content-description').textContent.trim();
|
||||
const date = (moment(element.querySelector('.mobile-date').textContent, 'MM/DD/YYYY')
|
||||
|| moment(element.querySelector('.date').textContent, 'Do MMM YYYY')).toDate();
|
||||
const actors = Array.from(element.querySelectorAll('.content-models a'), actorElement => actorElement.textContent);
|
||||
|
||||
const durationString = element.querySelector('.total-time').textContent.trim();
|
||||
// timestamp is somethines 00:00, sometimes 0:00:00
|
||||
const duration = durationString.split(':').length === 3
|
||||
? moment.duration(durationString).asSeconds()
|
||||
: moment.duration(`00:${durationString}`).asSeconds();
|
||||
|
||||
const [poster, ...primaryPhotos] = Array.from(element.querySelectorAll('a img'), imageElement => imageElement.src);
|
||||
const secondaryPhotos = $('.thumb-mouseover')
|
||||
.map((photoIndex, photoElement) => $(photoElement).css()['background-image'])
|
||||
.toArray()
|
||||
.map(photoUrl => photoUrl.slice(photoUrl.indexOf('http'), photoUrl.indexOf('.jpg') + 4));
|
||||
|
||||
const photos = [...primaryPhotos, ...secondaryPhotos];
|
||||
const tags = await matchTags([...defaultTags[site.slug], ...deriveTagsFromDescription(description)]);
|
||||
|
||||
return {
|
||||
url,
|
||||
entryId,
|
||||
title,
|
||||
description,
|
||||
actors,
|
||||
director: 'Mike Adriano',
|
||||
date,
|
||||
duration,
|
||||
tags,
|
||||
poster,
|
||||
photos,
|
||||
site,
|
||||
};
|
||||
}));
|
||||
}
|
||||
|
||||
async function scrapeSceneA(html, url, site) {
|
||||
const { document } = new JSDOM(html).window;
|
||||
const element = document.querySelector('.content-page-info');
|
||||
|
||||
const entryId = url.split('/').slice(-2)[0];
|
||||
const title = element.querySelector('.title').textContent.trim();
|
||||
const description = element.querySelector('.desc').textContent.trim();
|
||||
const date = moment(element.querySelector('.post-date').textContent.trim(), 'Do MMM YYYY').toDate();
|
||||
|
||||
const actors = Array.from(element.querySelectorAll('.models a'), actorElement => actorElement.textContent);
|
||||
|
||||
const durationString = element.querySelector('.total-time').textContent.trim();
|
||||
// timestamp is somethines 00:00, sometimes 0:00:00
|
||||
const duration = durationString.split(':').length === 3
|
||||
? moment.duration(durationString).asSeconds()
|
||||
: moment.duration(`00:${durationString}`).asSeconds();
|
||||
|
||||
const { poster } = document.querySelector('.content-page-header video');
|
||||
const { src, type } = document.querySelector('.content-page-header source');
|
||||
|
||||
const tags = await matchTags([...defaultTags[site.slug], ...deriveTagsFromDescription(description)]);
|
||||
|
||||
return {
|
||||
url,
|
||||
entryId,
|
||||
title,
|
||||
description,
|
||||
actors,
|
||||
director: 'Mike Adriano',
|
||||
date,
|
||||
duration,
|
||||
tags,
|
||||
poster,
|
||||
trailer: {
|
||||
src,
|
||||
type,
|
||||
},
|
||||
site,
|
||||
};
|
||||
}
|
||||
|
||||
async function scrapeSceneB(html, url, site) {
|
||||
const { document } = new JSDOM(html).window;
|
||||
const element = document.querySelector('.content-page-info');
|
||||
|
||||
const entryId = url.split('/').slice(-2)[0];
|
||||
const title = element.querySelector('.title').textContent.trim();
|
||||
const description = element.querySelector('.desc').textContent.trim();
|
||||
const date = moment(element.querySelector('.date').textContent.trim(), 'Do MMM YYYY').toDate();
|
||||
|
||||
const actors = Array.from(element.querySelectorAll('.models a'), actorElement => actorElement.textContent);
|
||||
|
||||
const durationString = element.querySelector('.total-time').textContent.trim();
|
||||
// timestamp is somethines 00:00, sometimes 0:00:00
|
||||
const duration = durationString.split(':').length === 3
|
||||
? moment.duration(durationString).asSeconds()
|
||||
: moment.duration(`00:${durationString}`).asSeconds();
|
||||
|
||||
const { poster } = document.querySelector('.content-page-header-inner video');
|
||||
const { src, type } = document.querySelector('.content-page-header-inner source');
|
||||
|
||||
const tags = await matchTags([...defaultTags[site.slug], ...deriveTagsFromDescription(description)]);
|
||||
|
||||
const scene = {
|
||||
url,
|
||||
entryId,
|
||||
title,
|
||||
description,
|
||||
actors,
|
||||
director: 'Mike Adriano',
|
||||
date,
|
||||
duration,
|
||||
tags,
|
||||
poster,
|
||||
trailer: {
|
||||
src,
|
||||
type,
|
||||
},
|
||||
site,
|
||||
};
|
||||
|
||||
return scene;
|
||||
}
|
||||
|
||||
async function fetchLatest(site, page = 1) {
|
||||
const { host } = new URL(site.url);
|
||||
|
||||
const res = await bhttp.get(`https://tour.${host}/videos?page=${page}`);
|
||||
|
||||
if (host === 'trueanal.com' || host === 'swallowed.com') {
|
||||
return scrapeLatestA(res.body.toString(), site);
|
||||
}
|
||||
|
||||
return scrapeLatestB(res.body.toString(), site);
|
||||
}
|
||||
|
||||
async function fetchScene(url, site) {
|
||||
const { host } = new URL(site.url);
|
||||
const res = await bhttp.get(url);
|
||||
|
||||
if (host === 'trueanal.com' || host === 'swallowed.com') {
|
||||
return scrapeSceneA(res.body.toString(), url, site);
|
||||
}
|
||||
|
||||
return scrapeSceneB(res.body.toString(), url, site);
|
||||
}
|
||||
|
||||
module.exports = {
|
||||
fetchLatest,
|
||||
fetchScene,
|
||||
};
|
||||
Reference in New Issue
Block a user