Refactored Dogfart scraper to use qu and return unextracted scenes.

This commit is contained in:
DebaucheryLibrarian 2022-04-03 00:49:39 +02:00
parent d59a57f311
commit 574c117ab0
1 changed files with 62 additions and 102 deletions

View File

@ -1,20 +1,16 @@
'use strict';
/* eslint-disable newline-per-chained-call */
// const Promise = require('bluebird');
const { JSDOM } = require('jsdom');
const moment = require('moment');
const http = require('../utils/http');
const slugify = require('../utils/slugify');
const qu = require('../utils/qu');
async function getPhotos(albumUrl) {
const res = await http.get(albumUrl);
const html = res.body.toString();
const { document } = new JSDOM(html).window;
const res = await qu.get(albumUrl);
const lastPhotoPage = Array.from(document.querySelectorAll('.preview-image-container a')).slice(-1)[0].href;
if (!res.ok) {
return [];
}
const lastPhotoPage = res.item.query.urls('.preview-image-container a').at(-1);
const lastPhotoIndex = parseInt(lastPhotoPage.match(/\d+.jpg/)[0], 10);
const photoUrls = Array.from({ length: lastPhotoIndex }, (value, index) => {
@ -29,124 +25,88 @@ async function getPhotos(albumUrl) {
return photoUrls;
}
function scrapeLatest(html, site, filter = true) {
const { document } = new JSDOM(html).window;
const sceneElements = Array.from(document.querySelectorAll('.recent-updates'));
function scrapeLatest(scenes, site, filter = true) {
return scenes.reduce((acc, { query }) => {
const release = {};
return sceneElements.map((element) => {
const siteUrl = element.querySelector('.recent-details-title .help-block, .model-details-title .site-name').textContent;
const siteUrl = query.cnt('.recent-details-title .help-block, .model-details-title .site-name');
release.url = query.url('.thumbnail', 'href', { origin: site.type === 'network' ? site.url : site.parent.url });
release.entryId = `${site.slug}_${new URL(release.url).pathname.split('/')[4]}`;
release.title = query.cnt('.scene-title');
release.actors = release.title.split(/[,&]|\band\b/).map((actor) => actor.replace(/BTS/i, '').trim());
// release.poster = `https:${element.querySelector('img').src}`;
release.poster = query.img();
release.teaser = query.el('.thumbnail', 'data-preview_clip_url');
release.channel = siteUrl?.match(/(.*).com/)?.[1].toLowerCase();
if (filter && `www.${siteUrl.toLowerCase()}` !== new URL(site.url).host) {
// different dogfart site
return null;
return { ...acc, unextracted: [...acc.unextracted, release] };
}
const sceneLinkElement = element.querySelector('.thumbnail');
const url = qu.prefixUrl(sceneLinkElement.href, 'https://dogfartnetwork.com');
const { pathname } = new URL(url);
const entryId = `${site.slug}_${pathname.split('/')[4]}`;
const title = element.querySelector('.scene-title').textContent;
const actors = title.split(/[,&]|\band\b/).map((actor) => actor.replace(/BTS/i, '').trim());
const poster = `https:${element.querySelector('img').src}`;
const teaser = sceneLinkElement.dataset.preview_clip_url;
const channel = siteUrl?.match(/(.*).com/)?.[1].toLowerCase();
return {
url,
entryId,
title,
actors,
poster,
teaser: {
src: teaser,
},
site,
channel,
};
}).filter(Boolean);
return { ...acc, scenes: [...acc.scenes, release] };
}, {
scenes: [],
unextracted: [],
});
}
async function scrapeScene(html, url, site) {
const { document } = new JSDOM(html).window;
const title = document.querySelector('.description-title').textContent;
const actors = Array.from(document.querySelectorAll('.more-scenes a')).map(({ textContent }) => textContent);
const metaDescription = document.querySelector('meta[itemprop="description"]').content;
const description = metaDescription
? metaDescription.content
: document.querySelector('.description')
.textContent
.replace(/[ \t\n]{2,}/g, ' ')
.replace('...read more', '')
.trim();
const channel = document.querySelector('.site-name').textContent.split('.')[0].toLowerCase();
async function scrapeScene({ query }, url, channel, baseScene, parameters) {
const release = {};
const { origin, pathname } = new URL(url);
const entryId = `${channel}_${pathname.split('/').slice(-2)[0]}`;
const date = new Date(document.querySelector('meta[itemprop="uploadDate"]').content);
const duration = moment
.duration(`00:${document
.querySelectorAll('.extra-info p')[1]
.textContent
.match(/\d+:\d+$/)[0]}`)
.asSeconds();
release.channel = query.cnt('.site-name').split('.')[0].toLowerCase();
release.entryId = `${release.channel}_${pathname.split('/').slice(-2)[0]}`;
const trailerElement = document.querySelector('.html5-video');
const poster = `https:${trailerElement.dataset.poster}`;
const { trailer } = trailerElement.dataset;
release.title = query.cnt('.description-title');
release.actors = query.all('.more-scenes a').map((actorEl) => ({
name: query.cnt(actorEl),
url: query.url(actorEl, null, 'href', { origin: channel.url }),
}));
const lastPhotosUrl = Array.from(document.querySelectorAll('.pagination a')).slice(-1)[0]?.href;
const photos = lastPhotosUrl ? await getPhotos(`${origin}${pathname}${lastPhotosUrl}`, site, url) : [];
release.description = query.meta('meta[itemprop="description"]') || qu.cnt('.description').replace(/[ \t\n]{2,}/g, ' ').replace('...read more', '').trim();
const stars = Math.floor(Number(document.querySelector('span[itemprop="average"]')?.textContent || document.querySelector('span[itemprop="ratingValue"]')?.textContent) / 2);
const tags = Array.from(document.querySelectorAll('.scene-details .categories a')).map(({ textContent }) => textContent);
release.date = query.date('meta[itemprop="uploadDate"]', null, null, 'content');
release.duration = query.duration('.extra-info p:nth-child(2)');
return {
entryId,
url: `${origin}${pathname}`,
title,
description,
actors,
date,
duration,
poster,
photos,
trailer: {
src: trailer,
},
tags,
rating: {
stars,
},
site,
channel,
};
release.tags = query.cnts('.scene-details .categories a');
release.trailer = query.video('.html5-video', 'data-trailer');
release.poster = query.poster('.html5-video', 'data-poster');
const lastPhotosUrl = query.urls('.pagination a').at(-1);
if (lastPhotosUrl && parameters.includePhotos) {
release.photos = await getPhotos(`${origin}${pathname}${lastPhotosUrl}`, channel, url);
}
release.stars = Number(((query.number('span[itemprop="average"]') || query.number('span[itemprop="ratingValue"]')) / 2).toFixed(2));
return release;
}
async function fetchLatest(site, page = 1) {
const res = await http.get(`https://dogfartnetwork.com/tour/scenes/?p=${page}`);
const res = await qu.getAll(`https://dogfartnetwork.com/tour/scenes/?p=${page}`, '.recent-updates');
return scrapeLatest(res.body.toString(), site);
}
if (res.ok) {
return scrapeLatest(res.items, site);
}
async function fetchScene(url, site) {
const res = await http.get(url);
return scrapeScene(res.body.toString(), url, site);
return res.status;
}
async function fetchProfile(baseActor, entity) {
const slug = slugify(baseActor.name, '+');
const url = `https://www.dogfartnetwork.com/tour/girls/${slug}/`;
const res = await http.get(url);
const res = await qu.getAll(url, '.recent-updates');
if (res.ok) {
const scenes = scrapeLatest(res.body, entity, false);
const scenes = scrapeLatest(res.items, entity, false);
return { scenes };
}
@ -156,6 +116,6 @@ async function fetchProfile(baseActor, entity) {
module.exports = {
fetchLatest,
fetchScene,
fetchProfile,
scrapeScene,
};