From ffa2310630fd6dc35ea0616022be32f6219f1d73 Mon Sep 17 00:00:00 2001
From: Paul Pfeister <code@pfeister.dev>
Date: Mon, 6 May 2024 00:49:13 -0400
Subject: [PATCH] Add LinkedIn

LinkedIn requires users to be signed in for normal visitation, but certain high-trust crawlers are allowed as well. Here, we masquerade as Googlebot to get past the 999.
---
 removed_sites.json           |  7 -------
 removed_sites.md             |  7 -------
 sherlock/resources/data.json | 10 ++++++++++
 3 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/removed_sites.json b/removed_sites.json
index 87d10c5..365ea2b 100644
--- a/removed_sites.json
+++ b/removed_sites.json
@@ -87,13 +87,6 @@
     "urlMain": "https://kiwifarms.net/",
     "username_claimed": "blue"
   },
-  "Linkedin": {
-    "errorMsg": "could not be found",
-    "errorType": "message",
-    "url": "https://www.linkedin.com/in/{}",
-    "urlMain": "https://www.linkedin.com/",
-    "username_claimed": "alex"
-  },
   "NPM-Package": {
     "errorType": "status_code",
     "url": "https://www.npmjs.com/package/{}",
diff --git a/removed_sites.md b/removed_sites.md
index e946120..dcdddfb 100644
--- a/removed_sites.md
+++ b/removed_sites.md
@@ -339,13 +339,6 @@ user names were available.
   },
 ```
 
-## LinkedIn
-
-This was attempted to be added around 2019-08-26, but the pull request was never merged.
-It turns out that LinkedIn requires that you have an account before they will let you
-check for other account.  So, this site will not work with the current design of
-Sherlock.
-
 ## StreamMe
 
 On 2019-04-07, I get a Timed Out message from the website.  It has not
diff --git a/sherlock/resources/data.json b/sherlock/resources/data.json
index d698d52..4ff705b 100644
--- a/sherlock/resources/data.json
+++ b/sherlock/resources/data.json
@@ -90,6 +90,16 @@
     "urlMain": "https://www.airliners.net/",
     "username_claimed": "yushinlin"
   },
+  "LinkedIn": {
+    "url": "https://linkedin.com/in/{}",
+    "urlMain": "https://linkedin.com",
+    "request_method": "GET",
+    "errorType": "status_code",
+    "headers": {
+      "User-Agent": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Googlebot/2.1; +http://www.google.com/bot.html) Chrome/W.X.Y.Z Safari/537.36"
+    },
+    "username_claimed": "paulpfeister"
+  },
   "Alik.cz": {
     "errorType": "status_code",
     "url": "https://www.alik.cz/u/{}",