boiii/traxxx
1
0
Fork 0
forked from DebaucheryLibrarian/traxxx
Code Issues Pull Requests Projects Releases Wiki Activity

Added Sperm Swallowers and The Ass Factory to Jules Jordan scraper. Added photo source.

Browse Source
This commit is contained in:
ThePendulum
2019-12-12 05:18:43 +01:00
parent ad1a0376e7
commit a03a00f5d9
8 changed files with 43 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
src/scrapers/julesjordan.js
View File

@@ -22,8 +22,12 @@ function scrapePhotos(html) {
.map((photoElement) => {
const src = $(photoElement).attr('src');
// high res often available in photos/ directory, but not always, provide original as fallback
return [src.replace('thumbs/', 'photos/'), src];
// high res often available in alternative directories, but not always, provide original as fallback
return [
src.replace('thumbs/', 'photos/'),
src.replace('thumbs/', '1024watermarked/'),
src,
];
});
return photos;
@@ -60,7 +64,14 @@ function scrapeLatest(html, site) {
return scenesElements.map((element) => {
const photoElement = $(element).find('a img.thumbs');
const photoCount = Number(photoElement.attr('cnt'));
const [poster, ...photos] = Array.from({ length: photoCount }, (value, index) => photoElement.attr(`src${index}_1x`)).filter(photoUrl => photoUrl !== undefined);
const [poster, ...photos] = Array.from({ length: photoCount }, (value, index) => {
const src = photoElement.attr(`src${index}_1x`) || photoElement.attr(`src${index}`);
if (!src) return null;
if (src.match(/^http/)) return src;
return `${site.url}${src}`;
}).filter(photoUrl => photoUrl);
const sceneLinkElement = $(element).children('a').eq(1);
const url = sceneLinkElement.attr('href');
@@ -116,7 +127,8 @@ function scrapeUpcoming(html, site) {
.toDate();
const photoElement = $(element).find('a img.thumbs');
const poster = photoElement.attr('src');
const posterPath = photoElement.attr('src');
const poster = posterPath.match(/^http/) ? posterPath : `${site.url}${posterPath}`;
const videoClass = $(element).find('.update_thumbnail div').attr('class');
const videoScript = $(element).find(`script:contains(${videoClass})`).html();
@@ -159,7 +171,8 @@ async function scrapeScene(html, url, site) {
.html()
.split('\n');
const poster = infoLines.find(line => line.match('useimage')).replace('useimage = "', '').slice(0, -2);
const posterPath = infoLines.find(line => line.match('useimage')).replace('useimage = "', '').slice(0, -2);
const poster = posterPath.match(/^http/) ? posterPath : `${site.url}${posterPath}`;
const trailerLine = infoLines.find(line => line.match('movie["Trailer_720"]'));
const trailer = trailerLine.slice(trailerLine.indexOf('path:"') + 6, trailerLine.indexOf('",movie'));
@@ -167,7 +180,7 @@ async function scrapeScene(html, url, site) {
const photos = await getPhotos(entryId, site);
const tags = $('.update_tags a').map((tagIndex, tagElement) => $(tagElement).text()).toArray();
const movie = $('.update_dvds a').href;
const movie = $('.update_dvds a').attr('href');
return {
url,