Added support for Family Strokes.

src/scrapers/mikeadriano.js

@@ -6,15 +6,6 @@ const { JSDOM } = require('jsdom');
 const cheerio = require('cheerio');
 const moment = require('moment');
 
-const { matchTags } = require('../tags');
-
-const defaultTags = {
-    swallowed: ['blowjob', 'deepthroat', 'facefuck'],
-    trueanal: ['anal'],
-    allanal: ['anal', 'fmf'],
-    nympho: [],
-};
-
 const descriptionTags = {
     'anal cream pie': 'anal creampie',
     'ass to mouth': 'ass to mouth',
@@ -55,7 +46,7 @@ async function scrapeLatestA(html, site) {
         const actors = Array.from(element.querySelectorAll('h4.models a'), actorElement => actorElement.textContent);
 
         const durationString = element.querySelector('.total-time').textContent.trim();
-        // timestamp is somethines 00:00, sometimes 0:00:00
+        // timestamp is sometimes 00:00, sometimes 0:00:00
         const duration = durationString.split(':').length === 3
             ? moment.duration(durationString).asSeconds()
             : moment.duration(`00:${durationString}`).asSeconds();
@@ -70,7 +61,7 @@ async function scrapeLatestA(html, site) {
             .map(photoUrl => photoUrl.slice(photoUrl.indexOf('http'), photoUrl.indexOf('.jpg') + 4));
 
         const photos = [...primaryPhotos, ...secondaryPhotos];
-        const tags = await matchTags([...defaultTags[site.slug], ...deriveTagsFromDescription(description)]);
+        const tags = deriveTagsFromDescription(description);
 
         const scene = {
             url,
@@ -124,7 +115,7 @@ async function scrapeLatestB(html, site) {
             .map(photoUrl => photoUrl.slice(photoUrl.indexOf('http'), photoUrl.indexOf('.jpg') + 4));
 
         const photos = [...primaryPhotos, ...secondaryPhotos];
-        const tags = await matchTags([...defaultTags[site.slug], ...deriveTagsFromDescription(description)]);
+        const tags = deriveTagsFromDescription(description);
 
         return {
             url,
@@ -155,7 +146,7 @@ async function scrapeSceneA(html, url, site) {
     const actors = Array.from(element.querySelectorAll('.models a'), actorElement => actorElement.textContent);
 
     const durationString = element.querySelector('.total-time').textContent.trim();
-    // timestamp is somethines 00:00, sometimes 0:00:00
+    // timestamp is sometimes 00:00, sometimes 0:00:00
     const duration = durationString.split(':').length === 3
         ? moment.duration(durationString).asSeconds()
         : moment.duration(`00:${durationString}`).asSeconds();
@@ -163,7 +154,7 @@ async function scrapeSceneA(html, url, site) {
     const { poster } = document.querySelector('.content-page-header video');
     const { src, type } = document.querySelector('.content-page-header source');
 
-    const tags = await matchTags([...defaultTags[site.slug], ...deriveTagsFromDescription(description)]);
+    const tags = deriveTagsFromDescription(description);
 
     return {
         url,
@@ -204,7 +195,7 @@ async function scrapeSceneB(html, url, site) {
     const { poster } = document.querySelector('.content-page-header-inner video');
     const { src, type } = document.querySelector('.content-page-header-inner source');
 
-    const tags = await matchTags([...defaultTags[site.slug], ...deriveTagsFromDescription(description)]);
+    const tags = deriveTagsFromDescription(description);
 
     const scene = {
         url,

src/scrapers/pornhub.js

@@ -30,7 +30,7 @@ async function scrapeProfile(html, _url, actorName) {
 
     if (descriptionString) profile.description = descriptionString.textContent;
 
-    if (bio.Birthday) profile.birthdate = moment.utc(bio.Birthday, 'MMM D, YYYY').toDate();
+    if (bio.Birthday && !/-0001/.test(bio.Birthday)) profile.birthdate = moment.utc(bio.Birthday, 'MMM D, YYYY').toDate(); // birthyear sometimes -0001, see Spencer Bradley as of january 2020
     if (bio.Born) profile.birthdate = moment.utc(bio.Born, 'YYYY-MM-DD').toDate();
 
     profile.birthPlace = bio['Birth Place'] || bio.Birthplace;

src/scrapers/teamskeet.js

@@ -15,7 +15,7 @@ function extractTitle(pathname) {
 
 function extractActors(str) {
     return str
-        .split(/,|\band/)
+        .split(/,|\band\b/ig)
         .filter(actor => !/\.{3}/.test(actor))
         .map(actor => actor.trim())
         .filter(actor => actor.length > 0);
@@ -81,7 +81,54 @@ function scrapeScene(html, site) {
     return release;
 }
 
-async function fetchLatest(site, page = 1) {
+function scrapeSceneA(html, site, sceneX, url) {
+    const scene = sceneX || new JSDOM(html).window.document;
+    const release = { site };
+
+    release.description = scene.querySelector('.scene-story').textContent.replace('...read more', '...').trim();
+
+    release.date = moment.utc(scene.querySelector('.scene-date').textContent, 'MM/DD/YYYY').toDate();
+    release.actors = Array.from(scene.querySelectorAll('.starring span'), el => extractActors(el.textContent)).flat();
+
+    const durationString = scene.querySelector('.time').textContent.trim();
+    const duration = ['00'].concat(durationString.split(':')).slice(-3).join(':'); // ensure hh:mm:ss
+    release.duration = moment.duration(duration).asSeconds();
+
+    if (sceneX) {
+        const titleEl = scene.querySelector(':scope > a');
+
+        release.url = titleEl.href;
+        release.entryId = titleEl.id;
+        release.title = titleEl.title;
+
+        const [poster, ...photos] = Array.from(scene.querySelectorAll('.scene img'), el => el.src);
+        release.poster = [poster.replace('bio_big', 'video'), poster];
+        release.photos = photos;
+    }
+
+    if (!sceneX) {
+        release.title = scene.querySelector('.title span').textContent;
+        release.url = url;
+
+        release.poster = scene.querySelector('video').poster;
+        release.photos = [release.poster.replace('video', 'bio_small'), release.poster.replace('video', 'bio_small2')];
+    }
+
+    const [, entryIdA, entryIdB] = new URL(release.url).pathname.split('/');
+    release.entryId = entryIdA === 'scenes' ? entryIdB : entryIdA;
+
+    return release;
+}
+
+function scrapeLatestA(html, site) {
+    const { document } = new JSDOM(html).window;
+
+    const scenes = Array.from(document.querySelectorAll('.scenewrapper'));
+
+    return scenes.map(scene => scrapeSceneA(null, site, scene));
+}
+
+async function fetchLatestTeamSkeet(site, page = 1) {
     const url = `https://www.teamskeet.com/t1/updates/load?fltrs[site]=${site.parameters.id}&page=${page}&view=newest&fltrs[time]=ALL&order=DESC`;
     const res = await bhttp.get(url);
 
@@ -92,10 +139,37 @@ async function fetchLatest(site, page = 1) {
     return null;
 }
 
+async function fetchLatestA(site) {
+    const url = `${site.url}/scenes`;
+    const res = await bhttp.get(url);
+
+    if (res.statusCode === 200) {
+        return scrapeLatestA(res.body.toString(), site);
+    }
+
+    return null;
+}
+
+async function fetchLatest(site, page = 1) {
+    if (site.parameters.id) {
+        return fetchLatestTeamSkeet(site, page);
+    }
+
+    if (site.parameters.scraper === 'A') {
+        return fetchLatestA(site, page);
+    }
+
+    return null;
+}
+
 async function fetchScene(url, site) {
     const session = bhttp.session(); // resolve redirects
     const res = await session.get(url);
 
+    if (site.parameters.scraper === 'A') {
+        return scrapeSceneA(res.body.toString(), site, null, url);
+    }
+
     return scrapeScene(res.body.toString(), site);
 }