Updated Jules Jordan scraper for new update page layout.

This commit is contained in:
DebaucheryLibrarian 2021-12-01 00:00:24 +01:00
parent 2018d5c298
commit b93a5715cb
1 changed files with 26 additions and 17 deletions

View File

@ -136,14 +136,18 @@ function getEntryId(html) {
function scrapeAll(scenes, site, entryIdFromTitle) {
return scenes.map(({ el, query }) => {
const release = {};
const title = query.cnt('.content_img div, .dvd_info > a, a ~ a');
release.url = query.url('.update_title a, .dvd_info > a, a ~ a');
release.title = query.q('.update_title a, .dvd_info > a, a ~ a', true);
release.title = title.slice(0, title.match(/starring:/i)?.index || Infinity).trim();
release.url = query.url('.content_img a, .dvd_info > a, a ~ a');
release.date = query.date('.update_date', 'MM/DD/YYYY');
release.entryId = (entryIdFromTitle && slugify(release.title)) || el.dataset.setid || query.q('.rating_box')?.dataset.id;
release.actors = query.all('.update_models a', true);
release.actors = query.all('.content_img .update_models a').map((actorEl) => ({
name: query.cnt(actorEl),
url: query.url(actorEl, null),
}));
const dvdPhotos = query.imgs('.dvd_preview_thumb');
const photoCount = Number(query.q('a img.thumbs', 'cnt')) || 1;
@ -183,9 +187,9 @@ function scrapeAll(scenes, site, entryIdFromTitle) {
}).filter(Boolean);
const teaserScript = query.html('script');
if (teaserScript) {
const src = teaserScript.slice(teaserScript.indexOf('http'), teaserScript.indexOf('.mp4') + 4);
if (src) release.teaser = { src };
release.teaser = teaserScript.slice(teaserScript.indexOf('http'), teaserScript.indexOf('.mp4') + 4);
}
return release;
@ -235,17 +239,21 @@ function scrapeUpcoming(html, site) {
});
}
async function scrapeScene({ html, query }, url, site, include) {
const release = { url, site };
async function scrapeScene({ html, query }, url, site, options) {
const release = {};
release.entryId = getEntryId(html);
release.title = query.q('.title_bar_hilite', true);
release.description = query.q('.update_description', true);
release.title = query.cnt('.title_bar_hilite');
release.description = query.cnt('.update_description');
release.date = query.date('.update_date', 'MM/DD/YYYY', null, 'innerHTML');
release.actors = query.all('.backgroundcolor_info > .update_models a, .item .update_models a', true);
release.tags = query.all('.update_tags a', true);
release.actors = query.all('.backgroundcolor_info > .update_models a, .item .update_models a').map((actorEl) => ({
name: query.cnt(actorEl),
url: query.url(actorEl, null),
}));
release.tags = query.cnts('.update_tags a');
const posterPath = html.match(/useimage = "(.*)"/)?.[1];
@ -260,7 +268,7 @@ async function scrapeScene({ html, query }, url, site, include) {
}
}
if (include.trailer && site.slug !== 'manuelferrara') {
if (options.includeTrailers && site.slug !== 'manuelferrara') {
const trailerLines = html.split('\n').filter((line) => /movie\["trailer\w*"\]\[/i.test(line));
if (trailerLines.length) {
@ -277,19 +285,20 @@ async function scrapeScene({ html, query }, url, site, include) {
}
}
if (include.photos) release.photos = await getPhotos(release.entryId, site);
if (options.includePhotos) {
release.photos = await getPhotos(release.entryId, site);
}
if (query.exists('.update_dvds a')) {
release.movie = {
url: query.url('.update_dvds a'),
title: query.q('.update_dvds a', true),
title: query.cnt('.update_dvds a'),
};
release.movie.entryId = new URL(release.movie.url).pathname.split('/').slice(-1)[0]?.replace('.html', '');
}
const stars = Number(query.q('.avg_rating', true)?.replace(/[\s|Avg Rating:]/g, ''));
if (stars) release.stars = stars;
release.stars = query.number('.avg_rating');
return release;
}
@ -298,7 +307,7 @@ function scrapeMovie({ el, query }, url, site) {
const movie = { url, site };
movie.entryId = new URL(url).pathname.split('/').slice(-1)[0]?.replace('.html', '');
movie.title = query.q('.title_bar span', true);
movie.title = query.cnt('.title_bar span');
movie.covers = query.urls('#dvd-cover-flip > a');
movie.channel = slugify(query.q('.update_date a', true), '');