Fixed tags and photos in Bang scraper, added to default proxy list.

This commit is contained in:
DebaucheryLibrarian 2025-08-21 02:23:13 +02:00
parent 9a548a4767
commit 31abbb9ffe
5 changed files with 13 additions and 9 deletions

View File

@ -425,6 +425,10 @@ module.exports = {
'dpdiva.com', 'dpdiva.com',
'www.oraloverdose.com', 'www.oraloverdose.com',
'upherasshole.com', 'upherasshole.com',
// BANG
'www.bang.com',
'i.bang.com',
'photos.bngcdn.com',
], ],
}, },
bypass: { bypass: {

8
package-lock.json generated
View File

@ -89,7 +89,7 @@
"tunnel": "0.0.6", "tunnel": "0.0.6",
"ua-parser-js": "^1.0.37", "ua-parser-js": "^1.0.37",
"undici": "^5.28.1", "undici": "^5.28.1",
"unprint": "^0.15.6", "unprint": "^0.15.7",
"url-pattern": "^1.0.3", "url-pattern": "^1.0.3",
"v-tooltip": "^2.1.3", "v-tooltip": "^2.1.3",
"video.js": "^8.6.1", "video.js": "^8.6.1",
@ -18359,9 +18359,9 @@
} }
}, },
"node_modules/unprint": { "node_modules/unprint": {
"version": "0.15.6", "version": "0.15.7",
"resolved": "https://registry.npmjs.org/unprint/-/unprint-0.15.6.tgz", "resolved": "https://registry.npmjs.org/unprint/-/unprint-0.15.7.tgz",
"integrity": "sha512-ky79GyBuOJNAmreb73ryEDmPJzM+d8jOp9Sx3KxsW3iNDNJFCYKAf9BmK4j32aXNpWeNtiHFuwxJlsaUeDP2wA==", "integrity": "sha512-sR4HhdJbPxkcQlQem/Hl3N67Nhn47wiK71qvl+yCT1N31tknA+mhtD+aWW5MG5F9fnJpCTlr/s4mCLxalj6XEA==",
"dependencies": { "dependencies": {
"axios": "^0.27.2", "axios": "^0.27.2",
"bottleneck": "^2.19.5", "bottleneck": "^2.19.5",

View File

@ -148,7 +148,7 @@
"tunnel": "0.0.6", "tunnel": "0.0.6",
"ua-parser-js": "^1.0.37", "ua-parser-js": "^1.0.37",
"undici": "^5.28.1", "undici": "^5.28.1",
"unprint": "^0.15.6", "unprint": "^0.15.7",
"url-pattern": "^1.0.3", "url-pattern": "^1.0.3",
"v-tooltip": "^2.1.3", "v-tooltip": "^2.1.3",
"video.js": "^8.6.1", "video.js": "^8.6.1",

View File

@ -116,7 +116,7 @@ async function scrapeScene({ query }, { url, entity }) {
})); }));
} }
release.tags = query.contents('.actions .genres'); release.tags = query.contents('div[data-controller] .genres');
const sourcesData = query.json('.video-container [data-videopreview-sources-value]', { attribute: 'data-videopreview-sources-value' }); const sourcesData = query.json('.video-container [data-videopreview-sources-value]', { attribute: 'data-videopreview-sources-value' });
@ -131,7 +131,7 @@ async function scrapeScene({ query }, { url, entity }) {
|| query.attribute('meta[property="og:video"]') || query.attribute('meta[property="og:video"]')
|| query.video('video[data-videocontainer-target] source'); || query.video('video[data-videocontainer-target] source');
release.photos = query.sourceSets('.photo-set img'); release.photos = query.sourceSets('div[data-controller] a[href^="/photos"] img');
release.photoCount = query.number('//h2[contains(text(), "Photos")]/following-sibling::span'); release.photoCount = query.number('//h2[contains(text(), "Photos")]/following-sibling::span');
const channelName = query.content('.video-container + div a[href*="?in="]')?.trim(); const channelName = query.content('.video-container + div a[href*="?in="]')?.trim();

View File

@ -80,8 +80,8 @@ async function matchReleaseTags(releases) {
const casedTags = [...new Set( const casedTags = [...new Set(
rawTags rawTags
.concat(rawTags.map((tag) => tag.toLowerCase())) .concat(rawTags.map((tag) => tag.trim().toLowerCase()))
.concat(rawTags.map((tag) => tag.toUpperCase())), .concat(rawTags.map((tag) => tag.trim().toUpperCase())),
)]; )];
const tagEntries = await knex('tags') const tagEntries = await knex('tags')