DebaucheryLibrarian/traxxx
2
1
Fork 1
Code Issues 39 Pull Requests 1 Releases Wiki Activity

Added Gaywire, modified Bang Bros scraper to accomodate.

Browse Source
This commit is contained in:
DebaucheryLibrarian
2021-01-17 01:43:55 +01:00
parent 8387f676fc
commit 251bb9476d
44 changed files with 228 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

135
src/scrapers/bangbros.js
View File

@@ -7,66 +7,57 @@ const moment = require('moment');
const logger = require('../logger')(__filename);
const slugify = require('../utils/slugify');
const http = require('../utils/http');
const { get, getAll, ex } = require('../utils/q');
const qu = require('../utils/qu');
function scrape(html, site) {
const $ = cheerio.load(html, { normalizeWhitespace: true });
const sceneElements = $('.echThumb').toArray();
return sceneElements.map((element) => {
const sceneLinkElement = $(element).find('.thmb_lnk');
const title = sceneLinkElement.attr('title');
const url = site.parameters?.legacy
? `https://${site.url}{sceneLinkElement.attr('href')}`
: `https://bangbros.com${sceneLinkElement.attr('href')}`;
const shootId = sceneLinkElement.attr('id') && sceneLinkElement.attr('id').split('-')[1];
const entryId = url.split('/')[3].slice(5);
const release = {};
const date = moment.utc($(element).find('.thmb_mr_2 span.faTxt').text(), 'MMM D, YYYY').toDate();
const actors = $(element).find('.cast-wrapper a.cast').map((actorIndex, actorElement) => $(actorElement).text().trim()).toArray();
const sceneLinkElement = $(element).find('.thmb_lnk');
release.title = sceneLinkElement.attr('title');
release.url = site.parameters?.legacy
? `${site.url}{sceneLinkElement.attr('href')}`
: `${site.parent.url}${sceneLinkElement.attr('href')}`;
release.shootId = sceneLinkElement.attr('id') && sceneLinkElement.attr('id').split('-')[1];
release.entryId = new URL(release.url).pathname.match(/video(\d+)/)?.[1];
release.date = moment.utc($(element).find('.thmb_mr_2 span.faTxt').text(), 'MMM D, YYYY').toDate();
release.actors = $(element).find('.cast-wrapper a.cast').map((actorIndex, actorElement) => $(actorElement).text().trim()).toArray();
const photoElement = $(element).find('.rollover-image');
const poster = `https:${photoElement.attr('data-original')}`;
const photosUrl = photoElement.attr('data-rollover-url');
const photosMaxIndex = photoElement.attr('data-rollover-max-index');
const photos = Array.from({ length: photosMaxIndex }, (val, index) => `https:${photosUrl}big${index + 1}.jpg`);
const duration = moment.duration(`0:${$(element).find('.thmb_pic b.tTm').text()}`).asSeconds();
const channel = $(element).find('a[href*="/websites"]').attr('href').split('/').slice(-1)[0];
release.poster = `https:${photoElement.attr('data-original')}`;
release.photos = Array.from({ length: photosMaxIndex }, (val, index) => `https:${photosUrl}big${index + 1}.jpg`);
return {
url,
entryId,
shootId,
title,
actors,
date,
duration,
poster,
photos,
rating: null,
site,
channel,
};
release.duration = moment.duration(`0:${$(element).find('.thmb_pic b.tTm').text()}`).asSeconds();
release.channel = $(element).find('a[href*="/websites"]').attr('href').split('/').slice(-1)[0];
return release;
});
}
function scrapeLegacy(scenes, site) {
return scenes.map(({ qu }) => {
return scenes.map(({ query }) => {
const release = {};
const pathname = qu.url('.mainplayer a, .palyer a'); // sic
const pathname = query.url('.mainplayer a, .palyer a'); // sic
release.url = `${site.url}${pathname}`;
release.entryId = pathname.match(/video\d+/)?.[0];
release.entryId = pathname.match(/video(\d+)/)?.[1];
release.title = qu.q('h2', true);
release.date = qu.date('div:not(.videoDisc)', 'MMM DD, YYYY', /\w+ \d{1,2}, \d{4}/);
release.description = qu.q('div + .videoDisc p', true);
release.duration = qu.dur('.videoTag .title');
release.title = query.q('h2', true);
release.date = query.date('div:not(.videoDisc)', 'MMM DD, YYYY', /\w+ \d{1,2}, \d{4}/);
release.description = query.q('div + .videoDisc p', true);
release.duration = query.dur('.videoTag .title');
release.poster = qu.img('.mainplayer img, .palyer img'); // sic
release.photos = qu.imgs('article img').concat(qu.imgs('article img', 'data-original')).filter(Boolean);
release.poster = query.img('.mainplayer img, .palyer img'); // sic
release.photos = query.imgs('article img').concat(qu.imgs('article img', 'data-original')).filter(Boolean);
return release;
});
@@ -102,32 +93,38 @@ function scrapeUpcoming(html, site) {
*/
function scrapeScene(html, url, _site) {
const { qu } = ex(html, '.playerSection');
const { query } = qu.ex(html, '.playerSection');
const release = {};
[release.shootId] = qu.q('.vdoTags + .vdoCast', true).match(/\w+$/);
[release.entryId] = url.split('/')[3].match(/\d+$/);
release.title = qu.q('.ps-vdoHdd h1', true);
release.description = qu.q('.vdoDesc', true);
const { pathname, hostname } = new URL(url);
release.actors = qu.all('a[href*="/model"]', true);
release.tags = qu.all('.vdoTags a', true);
[release.shootId] = query.cnt('.vdoTags + .vdoCast')?.match(/\w+$/) || [];
release.entryId = pathname.match(/video(\d+)/)?.[1];
release.stars = Number(qu.q('div[class*="like"]', true).match(/^\d+/)[0]) / 20;
release.title = query.cnt('.ps-vdoHdd h1');
release.description = query.cnt('.vdoDesc');
const poster = qu.img('img#player-overlay-image');
release.poster = [
poster,
poster.replace('/big_trailer', '/members/450x340'), // load error fallback
];
release.actors = query.all('a[href*="/model"]', true);
release.tags = query.all('.vdoTags a', true);
release.trailer = { src: qu.trailer() };
release.stars = Number(query.q('div[class*="like"]', true).match(/^\d+/)[0]) / 20;
const poster = query.img('img#player-overlay-image, img.playerPic');
if (poster) {
release.poster = [
poster,
poster.replace('/big_trailer', '/members/450x340'), // load error fallback
];
}
release.trailer = query.trailer() || qu.prefixUrl(html.match(/'(\/\/trailers.*mp4)'/)?.[1], hostname);
// all scenes seem to have 12 album photos available, not always included on the page
const firstPhotoUrl = ex(html).qu.img('img[data-slider-index="1"]');
const firstPhotoUrl = qu.ex(html).query.img('img[data-slider-index="1"]');
release.photos = Array.from({ length: 12 }, (val, index) => firstPhotoUrl.replace(/big\d+/, `big${index + 1}`));
const [channel] = qu.url('a[href*="/websites"]').match(/\w+$/);
const [channel] = query.url('a[href*="/websites"]').match(/\w+$/);
if (channel === 'bangcasting') release.channel = 'bangbroscasting';
if (channel === 'remaster') release.channel = 'bangbrosremastered';
@@ -136,25 +133,25 @@ function scrapeScene(html, url, _site) {
return release;
}
function scrapeSceneLegacy({ qu }, url) {
function scrapeSceneLegacy({ query }, url) {
const release = {};
release.entryId = new URL(url).pathname.match(/video\d+/)?.[0];
release.title = qu.q('h1', true);
release.description = qu.q('.videoDetail', true);
release.duration = qu.dur('.tags p span');
release.title = query.q('h1', true);
release.description = query.q('.videoDetail', true);
release.duration = query.dur('.tags p span');
release.poster = qu.img('#video_container + div img, .videoOverlay img');
release.poster = query.img('#video_container + div img, .videoOverlay img');
return release;
}
function scrapeProfile(html, scope) {
const { q } = ex(html);
const { query } = qu.ex(html);
const profile = {};
const avatar = q('.profilePic img', 'src');
const avatar = query.q('.profilePic img', 'src');
if (avatar) profile.avatar = `https:${avatar}`;
profile.releases = scrape(html, scope.network);
@@ -163,16 +160,16 @@ function scrapeProfile(html, scope) {
}
function scrapeProfileSearch(html, actorName) {
const { qu } = ex(html);
const actorLink = qu.url(`a[title="${actorName}" i][href*="model"]`);
const { query } = qu.ex(html);
const actorLink = query.url(`a[title="${actorName}" i][href*="model"]`);
return actorLink ? `https://bangbros.com${actorLink}` : null;
}
async function fetchLatest(site, page = 1) {
if (site.parameters?.legacy) {
const url = `${site.url}/videos/${page}`;
const res = await getAll(url, '.videoList');
const url = `${site.parameters?.latest || site.url}/videos/${page}`;
const res = await qu.getAll(url, '.videoList');
if (res.ok) {
return scrapeLegacy(res.items, site);
@@ -181,7 +178,7 @@ async function fetchLatest(site, page = 1) {
return res.status;
}
const res = await get(`${site.url}/${page}`);
const res = await qu.get(`${site.parameters?.latest || site.url}/${page}`);
if (res.ok) {
return scrape(res.item.html, site);
@@ -204,7 +201,7 @@ async function fetchScene(url, site, release) {
}
const { origin } = new URL(url);
const res = await get(url);
const res = await qu.get(url);
if (!res.ok) {
return res.status;
@@ -214,8 +211,8 @@ async function fetchScene(url, site, release) {
return scrapeSceneLegacy(res.item, url, site);
}
if (!/https?:\/\/(www.)?bangbros.com\/?$/.test(origin)) {
throw new Error('Cannot fetch from this URL. Please find the scene on https://bangbros.com and try again.');
if (!/https?:\/\/(www.)?(bangbros|gaywire).com\/?$/.test(origin)) {
throw new Error('Cannot fetch from this URL. Please find the scene on Bang Bros or Gaywire and try again.');
}
return scrapeScene(res.item.html, url, site);

28
src/scrapers/gaywire.js Normal file
View File

@@ -0,0 +1,28 @@
'use strict';
const qu = require('../utils/qu');
function scrapeAll(scenes) {
return scenes.map(({ query }) => {
const release = {};
release.title = query.cnt('.thmb_ttl');
console.log(release);
return release;
});
}
async function fetchLatest(channel, page) {
const res = await qu.getAll(`https://gaywire.com/h1/websites/${channel.slug}/${page}`);
if (res.ok) {
return scrapeAll(res.items, '.echThumb');
}
return res.status;
}
module.exports = {
fetchLatest,
};

2
src/scrapers/scrapers.js
View File

@@ -25,6 +25,7 @@ const fantasymassage = require('./fantasymassage');
const firstanalquest = require('./firstanalquest');
const fcuk = require('./fcuk');
const fullpornnetwork = require('./fullpornnetwork');
const gaywire = require('./gaywire');
const girlsway = require('./girlsway');
const hitzefrei = require('./hitzefrei');
const hookuphotshot = require('./hookuphotshot');
@@ -117,6 +118,7 @@ const scrapers = {
firstanalquest,
forbondage: porndoe,
fullpornnetwork,
gaywire: bangbros,
girlsway,
girlgirl: julesjordan,
hitzefrei,