DebaucheryLibrarian/traxxx
2
1
Fork 1
Code Issues 40 Pull Requests 1 Releases Wiki Activity

Updated Jules Jordan scraper for new site, changed entryId to always use URLs (upcoming WIP).

Browse Source
This commit is contained in:
DebaucheryLibrarian
2026-04-16 01:15:58 +02:00
parent f96e938417
commit 946afcb229
1 changed files with 44 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

107
src/scrapers/julesjordan.js
View File

@@ -1,44 +1,38 @@
'use strict'; 'use strict';
const util = require('util'); const util = require('util');
const Promise = require('bluebird');
const unprint = require('unprint'); const unprint = require('unprint');
const argv = require('../argv'); const argv = require('../argv');
const { heightToCm } = require('../utils/convert'); const { heightToCm } = require('../utils/convert');
const slugify = require('../utils/slugify'); const slugify = require('../utils/slugify');
const tryUrls = require('../utils/try-urls');
function getEntryId(html) { function getEntryId(url) {
const entryId = html.match(/showtagform\((\d+)\)/); if (!url) {
return null;
if (entryId) {
return entryId[1];
} }
const setIdIndex = html.indexOf('setid:"'); const entryId = new URL(url).pathname.split('/').at(-1).match('(.*?)_vids.html');
if (setIdIndex) { if (entryId) {
return html.slice(setIdIndex, html.indexOf(',', setIdIndex)).match(/\d+/)?.[0]; return slugify(entryId[1]);
} }
return null; return null;
} }
function getEntryIdFromTitle(release) { function scrapeAll(scenes, site) {
// return slugify([release.title, release.date && unprint.formatDate(release.date, 'YYYY-MM-DD')]); // date not shown on updates page return scenes.map(({ query }) => {
// return slugify(release.title);
return slugify([release.title, ...(release.actors?.map((actor) => actor.name || actor).toSorted() || [])]);
}
function scrapeAll(scenes, site, entryIdFromTitle) {
return scenes.map(({ element, query }) => {
const release = {}; const release = {};
const title = query.content('.content_img div, .dvd_info > a, a.update_title, .update_title a, a[title] + a[title], .overlay-text') const title = query.content('.jj-card-title, .content_img div, .dvd_info > a, a.update_title, .update_title a, a[title] + a[title], .overlay-text')
|| query.content('a[title*=" "]'); || query.content('a[title*=" "]');
release.title = title?.slice(0, title.match(/starring:/i)?.index || Infinity).trim(); release.title = title?.slice(0, title.match(/starring:/i)?.index || Infinity).trim();
release.url = query.url('.content_img a, .dvd_info > a, a.update_title, .update_title a, a[title]'); release.url = query.url('.jj-card-thumb, .content_img a, .dvd_info > a, a.update_title, .update_title a, a[title]');
release.date = query.date('.update_date', ['MM/DD/YYYY', 'YYYY-MM-DD']); release.date = query.date('.jj-card-date, .update_date', ['MM/DD/YYYY', 'YYYY-MM-DD', 'MMMM D, YYYY']);
release.entryId = getEntryId(release.url);
release.actors = query.all('.content_img .update_models a, .update_models a').map((actorEl) => ({ release.actors = query.all('.content_img .update_models a, .update_models a').map((actorEl) => ({
name: unprint.query.content(actorEl), name: unprint.query.content(actorEl),
@@ -70,17 +64,16 @@ function scrapeAll(scenes, site, entryIdFromTitle) {
return null; return null;
}).filter(Boolean); }).filter(Boolean);
const teaserScript = query.html('script'); release.teaser = query.video('.jj-card-video', { attribute: 'data-src' });
if (teaserScript) { if (!release.teaser) {
release.teaser = teaserScript.slice(teaserScript.indexOf('http'), teaserScript.indexOf('.mp4') + 4); const teaserScript = query.html('script');
if (teaserScript) {
release.teaser = teaserScript.slice(teaserScript.indexOf('http'), teaserScript.indexOf('.mp4') + 4);
}
} }
release.entryId = (entryIdFromTitle && getEntryIdFromTitle(release))
|| element.dataset.setid
|| query.element('.rating_box')?.dataset.id
|| query.attribute('a img', 'id')?.match(/set-target-(\d+)/)?.[1];
return release; return release;
}); });
} }
@@ -91,7 +84,7 @@ async function fetchLatest(site, page = 1, include, preData, entryIdFromTitle =
: `${site.url}/trial/categories/movies_${page}_d.html`; : `${site.url}/trial/categories/movies_${page}_d.html`;
// const res = await http.get(url); // const res = await http.get(url);
const res = await unprint.get(url, { selectAll: '.update_details, .grid-item' }); const res = await unprint.get(url, { selectAll: '.scenes-listing-grid .jj-content-card' });
if (res.ok) { if (res.ok) {
return scrapeAll(res.context, site, typeof site.parameters?.entryIdFromTitle === 'boolean' ? site.parameters.entryIdFromTitle : entryIdFromTitle); return scrapeAll(res.context, site, typeof site.parameters?.entryIdFromTitle === 'boolean' ? site.parameters.entryIdFromTitle : entryIdFromTitle);
@@ -100,7 +93,8 @@ async function fetchLatest(site, page = 1, include, preData, entryIdFromTitle =
return res.status; return res.status;
} }
function scrapeUpcoming(scenes, channel) { /* disable until we have entryId solution
function scrapeUpcoming(scenes, _channel) {
return scenes.map(({ query, html }) => { return scenes.map(({ query, html }) => {
const release = {}; const release = {};
@@ -135,6 +129,7 @@ async function fetchUpcoming(site) {
return res.status; return res.status;
} }
*/
function extractLegacyTrailer(html, context) { function extractLegacyTrailer(html, context) {
const trailerLines = html.split('\n').filter((line) => /movie\["trailer\w*"\]\[/i.test(line)); const trailerLines = html.split('\n').filter((line) => /movie\["trailer\w*"\]\[/i.test(line));
@@ -194,17 +189,19 @@ function getPhotos(query, release, context) {
async function scrapeScene({ html, query }, context) { async function scrapeScene({ html, query }, context) {
const release = {}; const release = {};
release.title = query.content('.title_bar_hilite, .movie_title'); release.entryId = getEntryId(context.url);
release.description = query.content('.update_description') || query.text('//div[./span[contains(text(), "Description")]]');
release.date = query.date(['.update_date', '//div[./span[contains(text(), "Date")]]'], ['MM/DD/YYYY', 'YYYY-MM-DD']); release.title = query.content('.scene-title, .title_bar_hilite, .movie_title');
release.description = query.content('.scene-desc, .update_description') || query.text('//div[./span[contains(text(), "Description")]]');
release.actors = query.all('.backgroundcolor_info > .update_models a, .item .update_models a, .player-scene-description .update_models a').map((actorEl) => ({ release.date = query.date(['.meta-item:nth-child(2) .val, .update_date', '//div[./span[contains(text(), "Date")]]'], ['MM/DD/YYYY', 'YYYY-MM-DD', 'MMMM D, YYYY']);
release.actors = query.all('.meta-item .update_models a, .backgroundcolor_info > .update_models a, .item .update_models a, .player-scene-description .update_models a').map((actorEl) => ({
name: unprint.query.content(actorEl), name: unprint.query.content(actorEl),
url: unprint.query.url(actorEl, null), url: unprint.query.url(actorEl, null),
})); }));
release.tags = query.contents('.update_tags a, .player-scene-description a[href*="/categories"]'); release.tags = query.contents('.scene-cats a, .update_tags a, .player-scene-description a[href*="/categories"]');
release.director = release.tags?.find((tag) => ['mike john', 'van styles'].includes(tag?.trim().toLowerCase())); release.director = release.tags?.find((tag) => ['mike john', 'van styles'].includes(tag?.trim().toLowerCase()));
const posterPath = query.poster('#video-player', { forceGetAttribute: true }) // without getAttribute, missing poster is returned as page URL const posterPath = query.poster('#video-player', { forceGetAttribute: true }) // without getAttribute, missing poster is returned as page URL
@@ -245,7 +242,7 @@ async function scrapeScene({ html, query }, context) {
// #images img selects a list of images that is present on every page; the JJ website removes the ones that failed to load with JS (lol) // #images img selects a list of images that is present on every page; the JJ website removes the ones that failed to load with JS (lol)
release.photos = [ release.photos = [
...context.baseRelease?.photos?.map((sources) => sources.at(-1).src) || [], ...context.baseRelease?.photos?.map((sources) => sources.at(-1).src) || [],
...query.imgs('#images img'), ...query.imgs('.tp-photos-strip img, #images img'),
...query.imgs('img.update_thumb', { attribute: 'src0_1x' }), ...query.imgs('img.update_thumb', { attribute: 'src0_1x' }),
].filter(Boolean).map((source) => Array.from(new Set([ ].filter(Boolean).map((source) => Array.from(new Set([
source.replace(/.jpg$/, '-full.jpg'), source.replace(/.jpg$/, '-full.jpg'),
@@ -270,9 +267,7 @@ async function scrapeScene({ html, query }, context) {
release.stars = query.number('.avg_rating'); release.stars = query.number('.avg_rating');
release.entryId = context.entity.parameters?.entryIdFromTitle release.qualities = query.contents('.res-item .res-lbl').map((resolution) => Number(resolution.match(/\d+$/)?.[0])).filter(Boolean);
? getEntryIdFromTitle(release)
: getEntryId(html);
return release; return release;
} }
@@ -296,7 +291,7 @@ function scrapeMovie({ query }, { url }) {
scene.date = unprint.query.date(sceneEl, '//span[contains(@class, "dvd-scene-description") and span[contains(text(), "Date")]]', 'MM/DD/YYYY'); scene.date = unprint.query.date(sceneEl, '//span[contains(@class, "dvd-scene-description") and span[contains(text(), "Date")]]', 'MM/DD/YYYY');
scene.actors = unprint.query.contents(sceneEl, '.update_models a'); scene.actors = unprint.query.contents(sceneEl, '.update_models a');
scene.entryId = getEntryIdFromTitle(scene); scene.entryId = getEntryId(scene.url);
return scene; return scene;
}); });
@@ -339,48 +334,34 @@ function scrapeProfile({ query }, url, entity) {
verifyType: 'image', verifyType: 'image',
})); }));
profile.scenes = scrapeAll(unprint.initAll(query.all('.grid-item')), entity, true); profile.scenes = scrapeAll(unprint.initAll(query.all('.mbp-scenes-grid .jj-content-card, .grid-item')), entity, true);
return profile; return profile;
} }
async function fetchProfile({ name: actorName, url }, entity) { async function fetchProfile({ name: actorName, url: actorUrl }, entity) {
const actorSlugA = slugify(actorName, ''); const actorSlugA = slugify(actorName, '');
const actorSlugB = slugify(actorName, '-'); const actorSlugB = slugify(actorName, '-');
const urls = [ const urls = [
url, actorUrl,
`${entity.parameters?.profile || `${entity.url}/trial/models`}/${actorSlugA}.html`, `${entity.parameters?.profile || `${entity.url}/trial/models`}/${actorSlugA}.html`,
`${entity.parameters?.profile || `${entity.url}/trial/models`}/${actorSlugB}.html`, `${entity.parameters?.profile || `${entity.url}/trial/models`}/${actorSlugB}.html`,
]; ];
return urls.reduce(async (chain, profileUrl) => { const { res, url } = await tryUrls(urls);
const profile = await chain;
if (profile) { if (res.ok) {
return profile; return scrapeProfile(res.context, url, entity);
} }
if (!profileUrl) { return res.status;
return null;
}
const res = await unprint.get(profileUrl, {
followRedirects: false,
});
if (res.ok) {
return scrapeProfile(res.context, profileUrl, entity);
}
return null;
}, Promise.resolve());
} }
module.exports = { module.exports = {
fetchLatest, fetchLatest,
fetchProfile, fetchProfile,
fetchUpcoming, // fetchUpcoming,
scrapeScene, scrapeScene,
scrapeMovie, scrapeMovie,
}; };