patch 3a9740db19a230cfa53758a4d89dbe82ba024ff5
Author: E. Bosch <presidev@AT@gmail.com>
Date:   Sat Feb 19 02:10:00 CET 2022
  * telegram: Improve web media handling
diff -rN -u old-irgramd/telegram.py new-irgramd/telegram.py
--- old-irgramd/telegram.py	2024-10-23 08:19:40.712698427 +0200
+++ new-irgramd/telegram.py	2024-10-23 08:19:40.716698420 +0200
@@ -11,7 +11,7 @@
 
 from include import CHAN_MAX_LENGHT, NICK_MAX_LENGTH
 from irc import IRCUser
-from utils import sanitize_filename, remove_slash, remove_http_s, get_human_size, get_human_duration
+from utils import sanitize_filename, is_url_equiv, extract_url, get_human_size, get_human_duration
 
     # Telegram
 
@@ -410,12 +410,10 @@
     async def handle_webpage(self, webpage, message):
         media_type = 'web'
         logo = await self.download_telegram_media(message)
-        if webpage.url != webpage.display_url \
-           and remove_slash(webpage.url) != webpage.display_url \
-           and remove_http_s(webpage.url) != webpage.display_url:
-            media_url_or_data = '{} | {}'.format(webpage.url, webpage.display_url)
+        if is_url_equiv(webpage.url, webpage.display_url):
+            url_data = webpage.url
         else:
-            media_url_or_data = webpage.url
+            url_data = '{} | {}'.format(webpage.url, webpage.display_url)
         if message:
             # sometimes the 1st line of message contains the title, don't repeat it
             message_line = message.message.splitlines()[0]
@@ -423,8 +421,18 @@
                 title = webpage.title
             else:
                 title = ''
+            # extract the URL in the message, don't repeat it
+            message_url = extract_url(message.message)
+            if is_url_equiv(message_url, webpage.url):
+                if is_url_equiv(message_url, webpage.display_url):
+                    media_url_or_data = message.message
+                else:
+                    media_url_or_data = '{} | {}'.format(message.message, webpage.display_url)
+            else:
+                media_url_or_data = '{} | {}'.format(message.message, url_data)
         else:
             title = webpage.title
+            media_url_or_data = url_data
 
         if title and logo:
             caption = ' | {} | {}'.format(title, logo)
diff -rN -u old-irgramd/utils.py new-irgramd/utils.py
--- old-irgramd/utils.py	2024-10-23 08:19:40.712698427 +0200
+++ new-irgramd/utils.py	2024-10-23 08:19:40.716698420 +0200
@@ -6,6 +6,7 @@
 # Constants
 
 FILENAME_INVALID_CHARS = re.compile('[/{}<>()"\'\\|&]')
+SIMPLE_URL = re.compile('http(|s)://[^ ]+')
 
 # Utilities
 
@@ -62,6 +63,16 @@
         surl = url
     return remove_slash(surl)
 
+def is_url_equiv(url1, url2):
+    if url1 and url2:
+        return url1 == url2 or remove_slash(remove_http_s(url1)) == remove_slash(remove_http_s(url2))
+    else:
+        return False
+
+def extract_url(text):
+    url = SIMPLE_URL.search(text)
+    return url.group() if url else None
+
 def get_human_size(size):
     human_units = ('', 'K', 'M', 'G', 'T', 'P', 'E', 'Z', 'Y')