From ea9c2dfe677297bb760880ded98f130e6caad3e5 Mon Sep 17 00:00:00 2001
From: Niels Simenon <niels.simenon@gmail.com>
Date: Fri, 7 Feb 2020 01:48:21 +0100
Subject: [PATCH] Scraping all actor release pages for Gamma. Improved actor
 matching for Gamma API.

---
 src/scrapers/blowpass.js | 10 +++++++++-
 src/scrapers/gamma.js    | 43 +++++++++++++++++++++++++++-------------
 src/scrapers/xempire.js  | 10 +++++++++-
 3 files changed, 47 insertions(+), 16 deletions(-)

diff --git a/src/scrapers/blowpass.js b/src/scrapers/blowpass.js
index d89fd9de..c2f835a3 100644
--- a/src/scrapers/blowpass.js
+++ b/src/scrapers/blowpass.js
@@ -21,9 +21,17 @@ async function fetchScene(url, site) {
     return release;
 }
 
+function getActorReleasesUrl(actorPath, page = 1) {
+    return `https://www.blowpass.com/en/videos/blowpass/latest/All-Categories/0${actorPath}/${page}`;
+}
+
+async function networkFetchProfile(actorName, siteSlug) {
+    return fetchProfile(actorName, siteSlug, null, getActorReleasesUrl);
+}
+
 module.exports = {
     fetchLatest,
-    fetchProfile,
+    fetchProfile: networkFetchProfile,
     fetchUpcoming,
     fetchScene,
 };
diff --git a/src/scrapers/gamma.js b/src/scrapers/gamma.js
index 1a35e0c4..7131215a 100644
--- a/src/scrapers/gamma.js
+++ b/src/scrapers/gamma.js
@@ -6,7 +6,8 @@ const { JSDOM } = require('jsdom');
 const cheerio = require('cheerio');
 const moment = require('moment');
 
-const { ex } = require('../utils/q');
+const argv = require('../argv');
+const { ex, get } = require('../utils/q');
 const slugify = require('../utils/slugify');
 
 async function fetchPhotos(url) {
@@ -109,7 +110,7 @@ async function scrapeApiReleases(json, site) {
     });
 }
 
-function scrapeAll(html, site, useNetworkUrl) {
+function scrapeAll(html, site, networkUrl) {
     const $ = cheerio.load(html, { normalizeWhitespace: true });
     const scenesElements = $('li[data-itemtype=scene]').toArray();
 
@@ -118,7 +119,9 @@ function scrapeAll(html, site, useNetworkUrl) {
 
         const sceneLinkElement = $(element).find('.sceneTitle a');
 
-        release.url = `${useNetworkUrl ? site.network.url : site.url}${sceneLinkElement.attr('href')}`;
+        if (site) release.url = `${networkUrl ? site.network.url : site.url}${sceneLinkElement.attr('href')}`;
+        else release.url = `${networkUrl}${sceneLinkElement.attr('href')}`;
+
         release.title = sceneLinkElement.attr('title');
 
         release.entryId = $(element).attr('data-itemid');
@@ -241,7 +244,24 @@ function scrapeActorSearch(html, url, actorName) {
     return actorLink ? actorLink.href : null;
 }
 
-function scrapeProfile(html, url, actorName, _siteSlug) {
+async function fetchActorReleases(profileUrl, getActorReleasesUrl, page = 1, accReleases = []) {
+    const { origin, pathname } = new URL(profileUrl);
+    const profilePath = `/${pathname.split('/').slice(-2).join('/')}`;
+
+    const url = getActorReleasesUrl(profilePath, page);
+    const { html, qu } = await get(url);
+
+    const releases = scrapeAll(html, null, origin);
+    const nextPage = qu('.Gamma_Paginator a.next');
+
+    if (nextPage) {
+        return fetchActorReleases(profileUrl, getActorReleasesUrl, page + 1, accReleases.concat(releases));
+    }
+
+    return accReleases.concat(releases);
+}
+
+async function scrapeProfile(html, url, actorName, _siteSlug, getActorReleasesUrl) {
     const { q } = ex(html);
 
     const avatar = q('img.actorPicture');
@@ -275,12 +295,9 @@ function scrapeProfile(html, url, actorName, _siteSlug) {
     if (alias) profile.aliases = alias.split(':')[1].trim().split(', ');
     if (nationality) profile.nationality = nationality.split(':')[1].trim();
 
-    /* not fetching all releases
-    profile.releases = Array.from(document.querySelectorAll('.sceneList .scene a.imgLink'), el => `https://${siteSlug}.com${el.href}`);
-    const moreReleases = qu('.seeAllTop a');
-
-    console.log(moreReleases);
-    */
+    if (getActorReleasesUrl && argv.withReleases) {
+        profile.releases = await fetchActorReleases(url, getActorReleasesUrl);
+    }
 
     return profile;
 }
@@ -365,8 +382,6 @@ async function fetchLatest(site, page = 1) {
     const url = `${site.url}${site.parameters?.latest || '/en/videos/AllCategories/0/'}${page}`;
     const res = await bhttp.get(url);
 
-    console.log(url);
-
     return scrapeAll(res.body.toString(), site);
 }
 
@@ -405,7 +420,7 @@ async function fetchActorScenes(actorName, apiUrl, siteSlug) {
     return [];
 }
 
-async function fetchProfile(actorName, siteSlug, altSearchUrl) {
+async function fetchProfile(actorName, siteSlug, altSearchUrl, getActorReleasesUrl) {
     const actorSlug = actorName.toLowerCase().replace(/\s+/, '+');
     const searchUrl = altSearchUrl
         ? `https://www.${siteSlug}.com/en/search/${actorSlug}/1/actor`
@@ -426,7 +441,7 @@ async function fetchProfile(actorName, siteSlug, altSearchUrl) {
             return null;
         }
 
-        return scrapeProfile(actorRes.body.toString(), url, actorName, siteSlug);
+        return scrapeProfile(actorRes.body.toString(), url, actorName, siteSlug, getActorReleasesUrl);
     }
 
     return null;
diff --git a/src/scrapers/xempire.js b/src/scrapers/xempire.js
index 99237194..0a8e89c2 100644
--- a/src/scrapers/xempire.js
+++ b/src/scrapers/xempire.js
@@ -19,9 +19,17 @@ async function fetchScene(url, site) {
     return release;
 }
 
+function getActorReleasesUrl(actorPath, page = 1) {
+    return `https://www.xempire.com/en/videos/xempire/latest/${page}/All-Categories/0${actorPath}`;
+}
+
+async function networkFetchProfile(actorName, siteSlug) {
+    return fetchProfile(actorName, siteSlug, null, getActorReleasesUrl);
+}
+
 module.exports = {
     fetchLatest,
-    fetchProfile,
+    fetchProfile: networkFetchProfile,
     fetchUpcoming,
     fetchScene,
 };