Handle UnicodeDecodeError.

[plomlombot-irc.git] / plomlombot.py

diff --git a/plomlombot.py b/plomlombot.py
index d6feb9377b4e36a1c5af96adb078f480c1c6f5fa..7d0f5355a1f70eb1cc946249d1d5e76154b33b49 100755 (executable)
--- a/plomlombot.py
+++ b/plomlombot.py
@@ -103,10 +103,14 @@ def lineparser_loop(io, nickname):
             matches = re.findall("(https?://[^\s>]+)", msg)
             for i in range(len(matches)):
                 url = matches[i]
+                request = urllib.request.Request(url, headers={
+                    "User-Agent": "plomlombot"
+                })
                 try:
-                    webpage = urllib.request.urlopen(url, timeout=15)
+                    webpage = urllib.request.urlopen(request, timeout=15)
                 except (urllib.error.HTTPError, urllib.error.URLError,
-                        UnicodeError, http.client.BadStatusLine) as error:
+                        UnicodeError, http.client.BadStatusLine,
+                        UnicodeDecodeError) as error:
                     print("TROUBLE FOLLOWING URL: " + str(error))
                     continue
                 charset = webpage.info().get_content_charset()
@@ -121,7 +125,7 @@ def lineparser_loop(io, nickname):
                 content = webpage.read().decode(charset)
                 title = str(content).split('<title>')[1].split('</title>')[0]
                 title = html.unescape(title)
-                io.send_line("PRIVMSG " + target + " :page title for url: "
+                io.send_line("NOTICE " + target + " :page title for url: "
                              + title)
 
         sender = ""