From 832cb746454e5fe3c4ddd6f8a3645d41539b713b Mon Sep 17 00:00:00 2001
From: Context 77 <126421199+ctx77@users.noreply.github.com>
Date: Thu, 1 Aug 2024 02:33:04 +0200
Subject: [PATCH] Adding youtube-special-case handling to extract title

---
 FaustBot/Modules/TitleObserver.py | 51 ++++++++++++++++++++-----------
 1 file changed, 34 insertions(+), 17 deletions(-)

diff --git a/FaustBot/Modules/TitleObserver.py b/FaustBot/Modules/TitleObserver.py
index becb665..708c105 100644
--- a/FaustBot/Modules/TitleObserver.py
+++ b/FaustBot/Modules/TitleObserver.py
@@ -18,12 +18,14 @@ class TitleObserver(PrivMsgObserverPrototype):
 
     def update_on_priv_msg(self, data, connection: Connection):
         regex = "(?P<url>https?://[^\s]+)"
-        url = re.search(regex, data['messageCaseSensitive'])
+        url = re.search(regex, data["messageCaseSensitive"])
         if url is not None:
             url = url.group()
             print(url)
             try:
-                headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36'}
+                headers = {
+                    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36"
+                }
 
                 url = url
                 req = urllib.request.Request(url, None, headers)
@@ -35,20 +37,35 @@ class TitleObserver(PrivMsgObserverPrototype):
             except Exception as exc:
                 print(exc)
                 pass
-            
+
     def getTitle(self, resource):
-            encoding = resource.headers.get_content_charset()
-            # der erste Fall kann raus, wenn ein anderer Channel benutzt wird
-            if resource.geturl().find('rehakids.de') != -1:
-                encoding = 'windows-1252'
-            if not encoding:
-                encoding = 'utf-8'
-            content = resource.read().decode(encoding, errors='replace')
+        encoding = resource.headers.get_content_charset()
+        url = resource.geturl()
+        # der erste Fall kann raus, wenn ein anderer Channel benutzt wird
+        if url.find("rehakids.de") != -1:
+            encoding = "windows-1252"
+        if not encoding:
+            encoding = "utf-8"
+        content = resource.read().decode(encoding, errors="replace")
+
+        if re.search("http[s]+://[^/]*youtube.com/", url):
+            title_re = re.compile(
+                '''"results":{"contents":\[{"videoPrimaryInfoRenderer":{"title":{"runs":\[{"text":"([^"]*)"'''
+            )
+        else:
             title_re = re.compile("<title>(.+?)</title>")
-            title = title_re.search(content).group(1)
-            title = html.unescape(title)
-            title = title.replace('\n', ' ').replace('\r', '')
-            title = title.replace("&lt;", "<")
-            title = title.replace("&gt;", ">")
-            title = title.replace("&amp;", "&")
-            return title
+
+        title_matches = title_re.search(content)
+        if title_matches:
+            title = title_matches.group(1)
+        else:
+            return "Could not Parse Title"
+
+        title = html.unescape(title)
+        title = title.replace("\n", " ").replace("\r", "")
+        title = title.replace("&lt;", "<")
+        title = title.replace("&gt;", ">")
+        title = title.replace("&amp;", "&")
+        if title == "":
+            title = "Empty Title"
+        return title