Added tag groups. Added MOFOS scraped. Improved entry ID handling.

src/fetch-releases.js

@@ -58,18 +58,18 @@ async function accumulateIncludedSites() {
 
 async function findDuplicateReleases(latestReleases, _siteId) {
     const latestReleasesShootIds = latestReleases.map(release => release.shootId).filter(release => release !== undefined);
-    const latestReleasesPageIds = latestReleases.map(release => release.pageId).filter(release => release !== undefined);
+    const latestReleasesEntryIds = latestReleases.map(release => release.entryId).filter(release => release !== undefined);
 
     return knex('releases')
         .whereIn('shoot_id', latestReleasesShootIds)
-        .orWhereIn('shoot_id', latestReleasesPageIds);
+        .orWhereIn('entry_id', latestReleasesEntryIds);
 }
 
 async function storeReleases(releases) {
     const curatedReleases = releases.map(release => ({
         site_id: release.site.id,
         shoot_id: release.shootId || null,
-        entry_id: release.entry_id || null,
+        entry_id: release.entryId || null,
         url: release.url,
         title: release.title,
         date: release.date,
@@ -97,13 +97,16 @@ async function fetchNewReleases(scraper, site, afterDate, accReleases = [], page
     const latestReleases = await scraper.fetchLatest(site, page);
 
     const duplicateReleases = await findDuplicateReleases(latestReleases, site.id);
-    const duplicateReleasesShootIds = new Set(
+    const duplicateReleasesIds = new Set(
         duplicateReleases
             .map(release => release.shoot_id)
             // exclude accumulated releases to prevent an infinite loop if the next page contains the same releases as the previous
+            .concat(duplicateReleases.map(release => release.entry_id))
             .concat(accReleases.map(release => release.shootId)),
     );
-    const uniqueReleases = latestReleases.filter(release => !duplicateReleasesShootIds.has(String(release.shootId)) && moment(release.date).isAfter(afterDate));
+    const uniqueReleases = latestReleases.filter(release => !duplicateReleasesIds.has(String(release.shootId))
+        && !duplicateReleasesIds.has(String(release.entryId))
+        && moment(release.date).isAfter(afterDate));
 
     console.log(`${site.name}: Scraped page ${page}, ${uniqueReleases.length} unique releases`);
 

src/scrapers/index.js

@@ -5,6 +5,7 @@ const brazzers = require('./brazzers');
 const julesjordan = require('./julesjordan');
 const kink = require('./kink');
 const legalporno = require('./legalporno');
+const mofos = require('./mofos');
 const pervcity = require('./pervcity');
 const privateNetwork = require('./private'); // reserved keyword
 const vixen = require('./vixen');
@@ -16,6 +17,7 @@ module.exports = {
     julesjordan,
     kink,
     legalporno,
+    mofos,
     pervcity,
     private: privateNetwork,
     vixen,

src/scrapers/mofos.js

@@ -0,0 +1,105 @@
+'use strict';
+
+/* eslint-disable */
+const bhttp = require('bhttp');
+const cheerio = require('cheerio');
+const moment = require('moment');
+
+const knex = require('../knex');
+const { matchTags } = require('../tags');
+
+function scrape(html, site) {
+    const $ = cheerio.load(html, { normalizeWhitespace: true });
+    const sceneElements = $('.widget-release-card').toArray();
+
+    return sceneElements.map((element) => {
+        const sceneLinkElement = $(element).find('.title a');
+
+        const title = sceneLinkElement.text().trim();
+        const url = `https://www.mofos.com${sceneLinkElement.attr('href')}`;
+        const entryId = url.split('/').slice(-2, -1)[0];
+
+        const date = moment.utc($(element).find('.date-added').text(), 'MMM DD, YYYY').toDate();
+        const actors = $(element).find('.girls-name a').map((actorIndex, actorElement) => $(actorElement).attr('title').replace(/\s+/g, ' ')).toArray();
+
+        const stars = Number($(element).find('.rating').text().slice(0, -1).trim()) / 20;
+
+        return {
+            url,
+            entryId,
+            title,
+            actors,
+            date,
+            rating: {
+                stars,
+            },
+            site,
+        };
+    });
+}
+
+async function scrapeScene(html, url, site) {
+    const $ = cheerio.load(html, { normalizeWhitespace: true });
+    const sceneElement = $('.video-info');
+
+    const entryId = url.split('/').slice(-2, -1)[0];
+    const title = sceneElement.find('.title').text();
+    const description = sceneElement.find('.desc').text();
+    const actors = sceneElement.find('.girls-site-box a.model-name').map((actorIndex, actorElement) => $(actorElement).text().trim()).toArray();
+
+    const siteElement = sceneElement.find('.site-name');
+    const sitename = siteElement.text().trim();
+    const siteId = sitename.replace(/\s+/g, '').toLowerCase();
+    const siteUrl = siteElement.attr('href').split('/').slice(0, 4).join('/');
+
+    const stars = Number(sceneElement.find('.rating-box .rating').text().slice(0, -1).trim()) / 20;
+
+    const rawTags = sceneElement.find('.categories a').map((tagIndex, tagElement) => $(tagElement).text().trim()).toArray();
+
+    const [channelSite, tags] = await Promise.all([
+        knex('sites')
+            .where({ id: siteId })
+            .orWhere({ url: `https://www.mofos.com${siteUrl}` })
+            .orWhere({ name: sitename })
+            .first(),
+        matchTags(rawTags),
+    ]);
+
+    return {
+        url,
+        entryId,
+        title,
+        actors,
+        tags,
+        rating: {
+            stars,
+        },
+        site,
+    };
+}
+
+async function fetchLatest(site, page = 1) {
+    const res = page > 1
+        ? await bhttp.get(`${site.url}/all-models/all-categories/alltime/bydate/${page}/`)
+        : await bhttp.get(`${site.url}/all-models/all-categories/alltime/bydate/`); // explicit page 1 redirects to homepage
+
+    return scrape(res.body.toString(), site);
+}
+
+async function fetchUpcoming(site) {
+    const res = await bhttp.get(`${site.url}/all-models/all-categories/upcoming/bydate/`);
+
+    return scrape(res.body.toString(), site);
+}
+
+async function fetchScene(url, site) {
+    const res = await bhttp.get(url);
+
+    return scrapeScene(res.body.toString(), url, site);
+}
+
+module.exports = {
+    fetchLatest,
+    fetchUpcoming,
+    fetchScene,
+};