DebaucheryLibrarian
/
traxxx
2
1
Fork 1
Code Issues 37 Pull Requests 1 Releases Wiki Activity

Fixed qu methods used with unprint in PornDoe scraper.

This commit is contained in:
DebaucheryLibrarian 2024-11-19 00:09:02 +01:00
parent 255775a019
commit e7c9b78827
1 changed files with 15 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
src/scrapers/porndoe.js
View File

@ -11,12 +11,12 @@ function scrapeAll(scenes) {
release.url = query.url('a'); release.url = query.url('a');
release.entryId = release.url.match(/\/watch\/(\d+)/)[1]; release.entryId = release.url.match(/\/watch\/(\d+)/)[1];
release.title = query.cnt('[class*="item-title"] a') || query.q('.bottom .link', 'title'); release.title = query.content('[class*="item-title"] a') || query.attribute('.bottom .link', 'title');
release.date = query.date('[class*="item-date"]', 'MMM DD, YYYY'); release.date = query.date('[class*="item-date"]', 'MMM DD, YYYY');
release.actors = query.all('[class*="item-actors"] a').map((el) => ({ release.actors = query.all('[class*="item-actors"] a').map((el) => ({
name: query.cnt(el), name: unprint.query.content(el),
url: query.url(el, null), url: unprint.query.url(el, null),
})); }));
// const poster = query.img('.thumb img'); // const poster = query.img('.thumb img');
@ -30,7 +30,7 @@ function scrapeAll(scenes) {
} }
release.teaser = query.video('video-preview'); release.teaser = query.video('video-preview');
release.channel = slugify(query.q('[class*="item-channel"] a', 'title'), ''); release.channel = slugify(query.attribute('[class*="item-channel"] a', 'title'), '');
return release; return release;
}); });
@ -39,30 +39,31 @@ function scrapeAll(scenes) {
function scrapeScene({ query }, url) { function scrapeScene({ query }, url) {
const release = {}; const release = {};
release.title = query.q('h1', true); release.title = query.content('h1');
release.entryId = url.match(/\/watch\/(\d+)/)[1]; release.entryId = url.match(/\/watch\/(\d+)/)[1];
release.description = query.meta('name=description') || query.q('read-even-more', true); release.description = query.content('.-mvd-description') || query.attribute('meta[name="description"]', 'content');
release.date = query.date('.-mvd-grid-stats', 'MMM DD, YYYY', /\w{3} \d{1,2}, \d{4}/); release.date = query.date('.-mvd-grid-stats', 'MMM DD, YYYY', /\w{3} \d{1,2}, \d{4}/)
|| query.date('meta[itemprop="uploadDate"]', 'YYYY-MM-DD', { attribute: 'content' });
release.actors = query.all('.video-top-details a[href*="/models"]').map((el) => ({ release.actors = query.all('.video-top-details a[href*="/models"]').map((el) => ({
name: query.cnt(el), name: unprint.query.content(el),
url: query.url(el, null), url: unprint.query.url(el, null),
})); }));
release.duration = query.dur('meta[itemprop="duration"]', null, 'content'); release.duration = query.duration('meta[itemprop="duration"]', { attribute: 'content' });
release.tags = query.all('.-vpta-bottom a[href*="/categories"], .-vpta-bottom a[href*="/tags"]', true); release.tags = query.contents('.-vpta-bottom a[href*="/categories"], .-vpta-bottom a[href*="/tags"]');
release.poster = query.img('.poster img') || query.meta('itemprop=thumbnailUrl'); release.poster = query.img('.poster img') || query.attribute('meta[itemprop="thumbnailUrl"]', 'content');
release.photos = query.imgs('#gallery-thumbs [class*="thumb"]', 'data-bg').slice(1).map((photo) => [ // first image is poster release.photos = query.imgs('#gallery-thumbs [class*="thumb"]', 'data-bg').slice(1).map((photo) => [ // first image is poster
photo.replace('512x288', '1472x828'), photo.replace('512x288', '1472x828'),
photo, photo,
]); ]);
release.trailer = query.meta('itemprop=contentURL'); release.trailer = query.attribute('meta[itemprop="contentURL"]', 'content');
release.channel = slugify(query.q('.video-top-details a[href*="/channels"]', true), ''); release.channel = slugify(query.content('.video-top-details a[href*="/channels"]'), '');
return release; return release;
} }