From cb63d6de3d3e8b747bf1b178190a183b9ab4a506 Mon Sep 17 00:00:00 2001
From: Mistivia <i@mistivia.com>
Date: Tue, 4 Nov 2025 21:30:24 +0800
Subject: url title bot

---
 ircbot/main.py | 58 +++++++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 55 insertions(+), 3 deletions(-)

diff --git a/ircbot/main.py b/ircbot/main.py
index a7c8c3a..3d5b4e8 100644
--- a/ircbot/main.py
+++ b/ircbot/main.py
@@ -7,6 +7,8 @@ import os
 import datetime
 import urllib.parse
 import hashlib
+import re
+import requests
 
 config = None
 with open('./config.json', 'r', encoding='utf-8') as f:
@@ -227,6 +229,53 @@ def roll_command(chan, sender, args):
 
 # ========================================================================
 
+url_pattern = re.compile(
+    r'(\bhttps?:\/\/[-A-Z0-9+&@#/%?=~_|!:,.;]*[-A-Z0-9+&@#/%?=~_|])',
+    re.IGNORECASE
+)
+
+title_regex = re.compile(
+    r'<title[^>]*>([^>]*?)</title>', 
+    re.IGNORECASE | re.DOTALL
+)
+
+def url_titles(text):
+    found_urls = url_pattern.findall(text)
+    unique_urls = []
+    if len(found_urls) > 0:
+        url = found_urls[0]
+        unique_urls = [url]
+    results = []
+    MAX_CONTENT_SIZE = 5 * 1024 * 1024
+    for url in unique_urls:
+        try:
+            with requests.get(
+                url, 
+                timeout=10, 
+                allow_redirects=True,
+                stream=True
+            ) as response:
+                if response.status_code != requests.codes.ok:
+                    continue
+                content_type = response.headers.get('Content-Type', '').lower()
+                if 'text/html' not in content_type:
+                    continue
+                content = b''
+                for chunk in response.iter_content(chunk_size=8192):
+                    content += chunk
+                    if len(content) >= MAX_CONTENT_SIZE:
+                        continue
+                encoding = 'utf-8'
+                html_doc = content.decode(encoding)
+                match = title_regex.search(html_doc)
+                if match:
+                    title_content = match.group(1).strip()
+                    if title_content:
+                        results.append(title_content)
+        except Exception as e:
+            print(e)
+    return results
+
 def cut_string(text, chunk_size=420):
     chunks = []
     current_chunk = []
@@ -430,13 +479,13 @@ class IRCBot:
             
             print(f"[{target}] <{sender_nick}>: {message}")
             write_log(target, sender_nick, message)
+            reply_target = target if target.startswith('#') else sender_nick
             
             if message.startswith("!") or message.startswith("！"):
                 try:
                     cmd_parts = message[1:].split()
                     cmd = cmd_parts[0].lower()
                     args = cmd_parts[1:]
-                    reply_target = target if target.startswith('#') else sender_nick
                     self.handle_command(sender_nick, reply_target, cmd, args)
                 except IndexError:
                     pass
@@ -451,11 +500,14 @@ class IRCBot:
                         cmd = cmd_parts[0].lower()
                         args = cmd_parts[1:]
                         if target.startswith('#'):
-                            reply_target = target 
                             self.handle_command(nick, reply_target, cmd, args)
                     except IndexError:
                         pass
-
+            else:
+                titles = url_titles(message)
+                if len(titles) > 0:
+                    for t in titles:
+                        self.send_message(reply_target, '⤷ ' + t)
         elif command == "JOIN":
             args = params
             if len(params) >= 1:
-- 
cgit v1.0