From 3ca4479d8a9e03fe6578de7f9549f955435d510a Mon Sep 17 00:00:00 2001
From: TheBeastLT <pauliox@beyond.lt>
Date: Sat, 14 Mar 2020 22:54:44 +0100
Subject: [PATCH] [scraper] add html entities escape

---
 scraper/lib/metadata.js                                | 10 +++++++++-
 scraper/scrapers/1337x/1337x_api.js                    |  3 ++-
 .../scrapers/thepiratebay/thepiratebay_dump_scraper.js |  6 +++---
 3 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/scraper/lib/metadata.js b/scraper/lib/metadata.js
index 43042d6..f06177f 100644
--- a/scraper/lib/metadata.js
+++ b/scraper/lib/metadata.js
@@ -80,6 +80,14 @@ function escapeTitle(title) {
       .trim();
 }
 
+function escapeHTML(title) {
+  return title
+      .replace(/&#039;|&apos;/g, '\'')
+      .replace(/&#38;|&amp;/g, '&')
+      .replace(/&#33;/g, '!')
+      .replace(/&#37;/g, '%');
+}
+
 async function getImdbId(info, type) {
   const name = escapeTitle(info.title);
   const year = info.year || info.date && info.date.slice(0, 4);
@@ -121,4 +129,4 @@ async function getKitsuId(info) {
           }));
 }
 
-module.exports = { getMetadata, getImdbId, getKitsuId };
+module.exports = { getMetadata, getImdbId, getKitsuId, escapeHTML };
diff --git a/scraper/scrapers/1337x/1337x_api.js b/scraper/scrapers/1337x/1337x_api.js
index 61a544d..d58bb5b 100644
--- a/scraper/scrapers/1337x/1337x_api.js
+++ b/scraper/scrapers/1337x/1337x_api.js
@@ -3,6 +3,7 @@ const needle = require('needle');
 const Sugar = require('sugar-date');
 const decode = require('magnet-uri');
 const Promises = require('../../lib/promises');
+const { escapeHTML } = require('../../lib/metadata');
 
 const defaultProxies = [
   'https://1337x.to'
@@ -117,7 +118,7 @@ function parseTorrentPage(body) {
     const imdbIdMatch = details.find('div[id=\'description\']').html().match(/imdb\.com\/title\/(tt\d+)/i);
 
     const torrent = {
-      name: decode(magnetLink).name.replace(/\+/g, ' '),
+      name: escapeHTML(decode(magnetLink).name.replace(/\+/g, ' ')),
       infoHash: decode(magnetLink).infoHash,
       magnetLink: magnetLink,
       seeders: parseInt(details.find('strong:contains(\'Seeders\')').next().text(), 10),
diff --git a/scraper/scrapers/thepiratebay/thepiratebay_dump_scraper.js b/scraper/scrapers/thepiratebay/thepiratebay_dump_scraper.js
index 67eddd2..e72645d 100644
--- a/scraper/scrapers/thepiratebay/thepiratebay_dump_scraper.js
+++ b/scraper/scrapers/thepiratebay/thepiratebay_dump_scraper.js
@@ -8,6 +8,7 @@ const thepiratebay = require('./thepiratebay_api.js');
 const bing = require('nodejs-bing');
 const { Type } = require('../../lib/types');
 const repository = require('../../lib/repository');
+const { escapeHTML } = require('../../lib/metadata');
 const { createTorrentEntry, createSkipTorrentEntry, getStoredTorrentEntry } = require('../../lib/torrentEntries');
 
 const NAME = 'ThePirateBay';
@@ -42,10 +43,9 @@ async function scrape() {
       const torrent = {
         uploadDate: moment(row[0], 'YYYY-MMM-DD HH:mm:ss').toDate(),
         infoHash: Buffer.from(row[1], 'base64').toString('hex'),
-        title: row[2]
+        title: escapeHTML(row[2])
             .replace(/^"|"$/g, '')
-            .replace(/&amp;/g, '&')
-            .replace(/&\w{2,6};/g, ' ')
+            .replace(/&#?\w{2,6};/g, ' ')
             .replace(/\s+/g, ' ')
             .trim(),
         size: parseInt(row[3], 10)