Retired unused Bang Bros scraper (now part of Aylo).

This commit is contained in:
DebaucheryLibrarian 2024-08-22 02:07:39 +02:00
parent 893a3be393
commit 80e5d7828a
3 changed files with 1 additions and 786 deletions

View File

@ -1,429 +0,0 @@
'use strict';
const http = require('../utils/http');
const qu = require('../utils/qu');
const { extractDate } = require('../utils/qu');
const { inchesToCm } = require('../utils/convert');
const slugify = require('../utils/slugify');
const capitalize = require('../utils/capitalize');
const clusterId = '617fb597b659459bafe6472470d9073a';
const authKey = 'YmFuZy1yZWFkOktqVDN0RzJacmQ1TFNRazI=';
const genderMap = {
M: 'male',
F: 'female',
};
function getScreenUrl(item, scene) {
if (!scene.dvd?.id || !item?.screenId) {
return null;
}
return `https://i.bang.com/screenshots/${scene.dvd.id}/${scene.type}/${scene.order}/${item.screenId}.jpg`;
}
function encodeId(id) {
return Buffer
.from(id, 'hex')
.toString('base64')
.replace(/\+/g, '-')
.replace(/\//g, '_')
.replace(/=/g, ',');
}
function decodeId(id) {
const restoredId = id
.replace(/-/g, '+')
.replace(/_/g, '/')
.replace(/,/g, '=');
return Buffer
.from(restoredId, 'base64')
.toString('hex');
}
async function fetchPhotos(scene) {
const photoPaths = Array.from({ length: scene.photos }, (value, index) => `/${scene.dvd.id}/${scene.identifier}/final/${String(index + 1).padStart(6, '0')}.jpg`);
const res = await http.post('https://www.bang.com/sign-images', {
images: photoPaths,
}, {
encodeJSON: false,
});
if (res.ok && res.body.images) {
return res.body.images.map((image) => qu.prefixUrl(image, 'https://photos.bang.com'));
}
return null;
}
async function scrapeScene(scene, entity, options) {
const release = {
entryId: scene.id,
title: scene.name || (scene.dvd?.name && scene.type === 'bonus' && capitalize(`${scene.dvd.name} - Bonus Scene ${scene.order || 1}`)) || null,
description: scene.description,
tags: scene.genres.concat(scene.actions).map((genre) => genre.name),
duration: scene.duration,
};
const slug = slugify(release.title);
release.url = `https://www.bang.com/video/${encodeId(release.entryId)}/${slug}`;
const date = new Date(scene.releaseDate);
release.date = new Date(Date.UTC(date.getUTCFullYear(), date.getUTCMonth(), date.getUTCDate()));
release.actors = scene.actors.map((actor) => ({ name: actor.name, gender: genderMap[actor.gender] }));
if (scene.is4k) release.tags.push('4k');
if (scene.gay) release.tags.push('gay');
const defaultPoster = scene.screenshots.find((photo) => photo.default === true);
const screens = scene.screenshots.filter((photo) => photo.default === false);
const remainingScreens = defaultPoster ? screens : screens.slice(1);
const poster = defaultPoster || screens[0];
release.poster = getScreenUrl(poster, scene);
release.photos = remainingScreens.map((photo) => getScreenUrl(photo, scene));
if (options?.includePhotos) {
const photos = await fetchPhotos(scene);
if (photos?.length > 0) {
release.photos = photos;
}
}
release.teaser = `https://i.bang.com/v/${scene.dvd.id}/${scene.identifier}/preview.mp4`;
release.channel = scene.series.name
.replace(/[! .]/g, '')
.replace('&', 'and');
return release;
}
function scrapeAll(scenes, entity) {
return Promise.all(scenes.map(({ _source: scene }) => scrapeScene(scene, entity)));
}
async function fetchActorReleases(actor, entity) {
const res = await http.post(`https://${clusterId}.us-east-1.aws.found.io/videos/video/_search`, {
size: 50,
query: {
bool: {
must: [
{
match: {
status: 'ok',
},
},
{
nested: {
path: 'actors',
query: {
bool: {
must: [
{
match: {
'actors.mongoId': {
operator: 'AND',
query: actor.id,
},
},
},
],
},
},
},
},
],
must_not: [
{
match: {
type: 'trailer',
},
},
],
},
},
sort: [
{
releaseDate: {
order: 'desc',
},
},
],
}, {
encodeJSON: true,
headers: {
Authorization: `Basic ${authKey}`,
},
});
return scrapeAll(res.body.hits.hits, entity);
}
async function scrapeProfile(actor, entity, include) {
const profile = {};
profile.aliases = actor.aliases;
profile.dateOfBirth = extractDate(actor.birthDate);
profile.gender = ({ F: 'female', M: 'male' })[actor.gender];
profile.ethnicity = actor.ethnicity;
profile.nationality = actor.nationality;
profile.birthPlace = `${actor.birthCity}, ${actor.birthCountry || ''}`;
profile.hair = actor.hairColor;
profile.eyes = actor.eyeColor;
profile.naturalBoobs = actor.naturalBreasts;
if (actor.measurements) {
const { cupSize, shoulder, chest, waist, height } = actor.measurements;
if (height) profile.height = inchesToCm(height);
if (cupSize) profile.cup = cupSize;
// [SIC]
if (shoulder) profile.bust = shoulder;
if (chest) profile.waist = chest;
if (waist) profile.hip = waist;
}
if (actor.twitter) profile.social = [`https://www.twitter.com/${actor.twitter}`];
if (actor.image) profile.avatar = `https://i.bang.com/pornstars/${actor.identifier}.jpg`;
if (include.releases) {
profile.releases = await fetchActorReleases(actor, entity);
}
return profile;
}
async function fetchLatest(site, page = 1) {
const res = await http.post(`https://${clusterId}.us-east-1.aws.found.io/videos/video/_search`, {
size: 50,
from: (page - 1) * 50,
query: {
bool: {
must: [
{
match: {
status: 'ok',
},
},
{
range: {
releaseDate: {
lte: 'now',
},
},
},
/*
* global fetch
{
nested: {
path: 'studio',
query: {
bool: {
must: [
{
match: {
'studio.name': {
operator: 'AND',
query: 'bang! originals',
},
},
},
],
},
},
},
},
*/
{
nested: {
path: 'series',
query: {
bool: {
must: [
{
match: {
'series.id': {
operator: 'AND',
query: site.parameters.siteId,
},
},
},
],
},
},
},
},
],
must_not: [
{
match: {
type: 'trailer',
},
},
],
},
},
sort: [
{
releaseDate: {
order: 'desc',
},
},
],
}, {
encodeJSON: true,
headers: {
Authorization: `Basic ${authKey}`,
},
});
return scrapeAll(res.body.hits.hits, site);
}
async function fetchUpcoming(site, page = 1) {
const res = await http.post(`https://${clusterId}.us-east-1.aws.found.io/videos/video/_search`, {
size: 50,
from: (page - 1) * 50,
query: {
bool: {
must: [
{
match: {
status: 'ok',
},
},
{
range: {
releaseDate: {
lte: 'now+7d',
},
},
},
{
nested: {
path: 'series',
query: {
bool: {
must: [
{
match: {
'series.id': {
operator: 'AND',
query: site.parameters.siteId,
},
},
},
],
},
},
},
},
],
must_not: [
{
match: {
type: 'trailer',
},
},
],
},
},
sort: [
{
releaseDate: {
order: 'desc',
},
},
],
}, {
encodeJSON: true,
headers: {
Authorization: `Basic ${authKey}`,
},
});
return scrapeAll(res.body.hits.hits, site);
}
async function fetchScene(url, entity, baseRelease, options) {
if (baseRelease?.entryId) {
// overview and deep data is the same, don't hit server unnecessarily
return baseRelease;
}
const encodedId = new URL(url).pathname.split('/')[2];
const entryId = decodeId(encodedId);
const res = await http.get(`https://${clusterId}.us-east-1.aws.found.io/videos/video/${entryId}`, {
headers: {
Authorization: `Basic ${authKey}`,
},
});
return scrapeScene(res.body._source, entity, options); // eslint-disable-line no-underscore-dangle
}
async function fetchProfile({ name: actorName }, context, include) {
const res = await http.post(`https://${clusterId}.us-east-1.aws.found.io/actors/actor/_search`, {
size: 5,
sort: [{
_score: {
order: 'desc',
},
}],
query: {
bool: {
must: [
{
match: {
name: {
query: actorName,
operator: 'and',
},
},
},
{
match: {
status: 'ok',
},
},
],
},
},
}, {
headers: {
Authorization: `Basic ${authKey}`,
},
encodeJSON: true,
});
if (res.ok) {
const actor = res.body.hits.hits.find((hit) => hit._source.name.toLowerCase() === actorName.toLowerCase());
if (actor) {
return scrapeProfile(actor._source, context.entity, include);
}
return null;
}
return res.status;
}
module.exports = {
fetchLatest,
fetchProfile,
fetchScene,
fetchUpcoming,
};

View File

@ -1,355 +0,0 @@
'use strict';
/* eslint-disable newline-per-chained-call */
const cheerio = require('cheerio');
const moment = require('moment');
const logger = require('../logger')(__filename);
const slugify = require('../utils/slugify');
const http = require('../utils/http');
const qu = require('../utils/qu');
const args = require('../argv');
function scrape(html, site) {
const $ = cheerio.load(html, { normalizeWhitespace: true });
const sceneElements = $('.echThumb').toArray();
return sceneElements.map((element) => {
const release = {};
const sceneLinkElement = $(element).find('.thmb_lnk');
release.title = sceneLinkElement.attr('title');
release.url = site.parameters?.legacy || !site.parent
? `${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 = $(element).find('.rollover-image');
const photosUrl = photoElement.attr('data-rollover-url');
const photosMaxIndex = photoElement.attr('data-rollover-max-index');
release.poster = `https:${photoElement.attr('data-original')}`;
release.photos = Array.from({ length: photosMaxIndex }, (val, index) => `https:${photosUrl}big${index + 1}.jpg`);
release.duration = moment.duration(`0:${$(element).find('.thmb_pic b.tTm').text()}`).asSeconds();
release.channel = $(element).find('a[href*="/websites"]').attr('href').split('/').slice(-1)[0];
return release;
});
}
function scrapeAllLegacy(scenes, site) {
return scenes.map(({ query }) => {
const release = {};
const pathname = query.url('.mainplayer a, .palyer a'); // sic
release.url = `${site.url}${pathname}`;
release.entryId = pathname.match(/video(\d+)/)?.[1];
release.title = query.q('h2', true);
release.date = query.date('div:not(.videoDisc)', 'MMM DD, YYYY', /\w+ \d{1,2}, \d{4}/);
release.description = query.q('div + .videoDisc p', true);
release.duration = query.dur('.videoTag .title');
release.poster = query.img('.mainplayer img, .palyer img'); // sic
release.photos = query.imgs('article img').concat(qu.imgs('article img', 'data-original')).filter(Boolean);
return release;
});
}
function scrapeAllMembers(scenes, _channel) {
return scenes.map(({ query, el }) => {
const release = {};
const data = JSON.parse(query.q(el, null, 'data-shoot'));
release.entryId = data?.id || query.url('a.etLnk')?.match(/\d+$/)?.[0];
release.shootId = data?.code;
release.url = data.url ? qu.prefixUrl(data.url, 'https://members.bangbros.com') : query.url('a.etLnk');
release.title = data?.title || query.cnt('.etl-hdd');
release.description = data?.description || query.cnt('.etl-desc');
release.date = query.date('.etl-dt', 'MMM DD, YYYY', /\w{3} \d{1,2}, \d{4}/);
release.actors = data?.model.map((actor) => ({
name: actor.name,
url: qu.prefixUrl(actor.url, 'https://members.bangbros.com'),
}));
const rolloverUrl = query.q('.rollover-image', 'data-rollover-url');
release.poster = data?.image || query.img('.rollover-image', 'data-initial-image-url');
if (rolloverUrl) {
release.photos = Array.from({ length: 15 }, (value, index) => `${rolloverUrl}${index + 1}.jpg`);
}
release.trailer = data?.trailer;
release.tags = data?.tag.map((tag) => tag.name);
return release;
});
}
/* no dates available, breaks database
function scrapeUpcoming(html, site) {
const { document } = ex(html);
return ctxa(document, 'a[id*="upcoming-videos"]').map(({ element, q }) => {
const release = {};
[release.shootId] = element.id.split('-').slice(-1);
const siteCode = release.shootId.match(/[a-z]+/)[0];
if (siteCode !== site.parameters.code) {
return null;
}
const posterEl = q('img');
[release.entryId] = element.href.split('/')[1].match(/\d+/);
release.url = `https://bangbros.com${element.href}`;
release.title = posterEl.alt;
release.poster = `https:${posterEl.src}`;
release.actors = q('.castName', true).split(/ in/g).slice(0, -1).map(actorName => actorName.trim());
console.log(release);
return release;
}).filter(Boolean);
}
*/
function scrapeScene(html, url, _site) {
const { query } = qu.ex(html, '.playerSection');
const release = {};
const { pathname } = new URL(url);
[release.shootId] = query.cnt('.vdoTags + .vdoCast')?.match(/\w+$/) || [];
release.entryId = pathname.match(/video(\d+)/)?.[1];
release.title = query.cnt('.ps-vdoHdd h1');
release.description = query.cnt('.vdoDesc');
release.actors = query.all('a[href*="/model"]', true);
release.tags = query.all('.vdoTags a', true);
release.stars = Number(query.q('div[class*="like"]', true).match(/^\d+/)[0]) / 20;
const poster = query.img('img#player-overlay-image, img.playerPic');
if (poster) {
release.poster = [
poster.replace('//big_trailer', '/big_trailer'),
poster.replace(/\/?\/big_trailer/, '/members/450x340'), // load error fallback
];
}
release.trailer = [
query.video('video source[type="video/mp4"]'),
query.video('video source[type="application/x-mpegURL"]'),
];
// all scenes seem to have 12 album photos available, not always included on the page
const firstPhotoUrl = qu.ex(html).query.img('img[data-slider-index="1"]');
release.photos = Array.from({ length: 12 }, (val, index) => firstPhotoUrl.replace(/big\d+/, `big${index + 1}`));
const [channel] = query.url('a[href*="/websites"]').match(/\w+$/);
if (channel === 'bangcasting') release.channel = 'bangbroscasting';
if (channel === 'remaster') release.channel = 'bangbrosremastered';
else release.channel = channel;
return release;
}
function scrapeSceneLegacy({ query }, url) {
const release = {};
release.entryId = new URL(url).pathname.match(/video\d+/)?.[0];
release.title = query.q('h1', true);
release.description = query.q('.videoDetail', true);
release.duration = query.dur('.tags p span');
release.poster = query.img('#video_container + div img, .videoOverlay img');
return release;
}
function scrapeSceneMembers({ query }, url) {
const release = {};
release.entryId = new URL(url).pathname.match(/(\d+)\/?$/)[1];
release.shootId = query.img('.player img')?.match(/\/shoots\/(\w+)\//)?.[1];
release.title = query.cnt('.vdo-hdd1');
release.description = query.cnt('.ndcp');
release.actors = query.all('.vdsc a[href*="/model"]').map((actorEl) => ({
name: query.cnt(actorEl, 'span'),
url: query.url(actorEl, null, 'href', { origin: 'https://members.bangbros.com' }),
avatar: query.img(actorEl, 'img'),
}));
release.date = query.date('.ran:nth-child(2)', 'MMM DD, YYYY', /\w{3} \d{1,2}, \d{4}/);
release.duration = query.duration('.ran:nth-child(3)');
release.tags = query.cnts('.tag a[href*="/tags"]');
release.channel = slugify(query.cnt('.tag a[href*="/site"]'), '');
return release;
}
function scrapeProfile(html, scope) {
const { query } = qu.ex(html);
const profile = {};
const avatar = query.q('.profilePic img', 'src');
if (avatar) profile.avatar = `https:${avatar}`;
profile.releases = scrape(html, scope.entity);
return profile;
}
function scrapeProfileSearch(html, actorName) {
const { query } = qu.ex(html);
const actorLink = query.url(`a[title="${actorName}" i][href*="model"]`);
return actorLink ? `https://bangbros.com${actorLink}` : null;
}
async function fetchLatest(site, page = 1) {
const res = await qu.get(`${site.parameters?.latest || site.url}/${page}`);
if (res.ok) {
return scrape(res.item.html, site);
}
return res.status;
}
async function fetchLatestMembers(channel, page = 1, { parameters }) {
if (!parameters.product) {
throw new Error(`No member area product ID known for '${channel.name}'`);
}
if (!args.cookie) {
throw new Error(`Please specifiy --cookie "PHPSESSID=xxx" to access the '${channel.name}' members area.`);
}
const url = `https://members.bangbros.com/product/${parameters.product}/videos/latest/${page}`;
const res = await qu.getAll(url, '.thumbHolder .echThumb', {
cookie: args.cookie,
});
if (res.ok) {
return scrapeAllMembers(res.items, channel);
}
return res.status;
}
async function fetchLatestLegacy(site, page = 1) {
const url = `${site.parameters?.latest || site.url}/videos/${page}`;
const res = await qu.getAll(url, '.videoList');
if (res.ok) {
return scrapeAllLegacy(res.items, site);
}
return res.status;
}
/*
async function fetchUpcoming(site) {
const res = await http.get('https://www.bangbros.com');
return scrapeUpcoming(res.body.toString(), site);
}
*/
async function fetchScene(url, site, release) {
if (!release?.date) {
logger.warn(`Scraping Bang Bros scene from URL without release date: ${url}`);
}
const { origin } = new URL(url);
const res = await qu.get(url);
if (!res.ok) {
return res.status;
}
if (site.parameters?.legacy) {
return scrapeSceneLegacy(res.item, url, site);
}
if (!/https?:\/\/(www.)?(bangbros|gaywire).com\/?$/.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);
}
async function fetchSceneMembers(url, baseRelease, channel, { parameters }) {
if (!parameters.product) {
throw new Error(`No member area product ID known for '${channel.name}'`);
}
if (!args.cookie) {
throw new Error(`Please specifiy --cookie "PHPSESSID=xxx" to access the '${channel.name}' members area.`);
}
const res = await qu.get(url, null, {
cookie: args.cookie,
});
if (res.ok) {
return scrapeSceneMembers(res.item, url, channel);
}
return res.status;
}
async function fetchProfile({ name: actorName }, scope) {
const actorSlug = slugify(actorName);
const url = `https://bangbros.com/search/${actorSlug}`;
const res = await http.get(url);
if (res.statusCode === 200) {
const actorUrl = scrapeProfileSearch(res.body.toString(), actorName);
if (actorUrl) {
const actorRes = await http.get(actorUrl);
if (actorRes.statusCode === 200) {
return scrapeProfile(actorRes.body.toString(), scope);
}
}
}
return null;
}
module.exports = {
fetchLatest,
fetchScene,
fetchProfile,
legacy: {
fetchLatest: fetchLatestLegacy,
},
members: {
fetchLatest: fetchLatestMembers,
fetchScene: fetchSceneMembers,
},
// fetchUpcoming, no dates available
};

View File

@ -9,7 +9,6 @@ const amnesiac = require('./amnesiac');
const badoink = require('./badoink'); const badoink = require('./badoink');
const bamvisions = require('./bamvisions'); const bamvisions = require('./bamvisions');
const bang = require('./bang'); const bang = require('./bang');
const bangbros = require('./bangbros');
const bradmontana = require('./bradmontana'); const bradmontana = require('./bradmontana');
const cherrypimps = require('./cherrypimps'); const cherrypimps = require('./cherrypimps');
const cliffmedia = require('./cliffmedia'); const cliffmedia = require('./cliffmedia');
@ -199,7 +198,7 @@ const scrapers = {
badoinkvr: badoink, badoinkvr: badoink,
bamvisions, bamvisions,
bang, bang,
bangbros, bangbros: aylo,
bjraw: radical, bjraw: radical,
blacked: vixen, blacked: vixen,
blackedraw: vixen, blackedraw: vixen,