Handle URLs for too large websites / files.

[plomlombot-irc.git] / plomlombot.py

diff --git a/plomlombot.py b/plomlombot.py
index 66b902f672e978ad0ff5e01961c7fdd94e5e196a..aa7061cac656f3f6b5f768e40787ccb6fbc475c4 100755 (executable)
--- a/plomlombot.py
+++ b/plomlombot.py
@@ -180,9 +180,11 @@ def handle_command(command, argument, notice, target, session):
             if len(results) == 0:
                 notice("NO QUOTES MATCHING QUERY")
             else:
-                for result in results:
-                    notice("QUOTE #" + str(result[0] + 1) + " : "
-                           + result[1][-1])
+                if len(results) > 3:
+                    notice("SHOWING 3 OF " + str(len(results)) + " QUOTES")
+                for result in results[:3]:
+                    notice("QUOTE #" + str(result[0] + 1) + ": "
+                           + result[1][:-1])
             return
         else:
             i = random.randrange(len(lines))
@@ -337,17 +339,22 @@ def handle_url(url, notice, show_url=False):
             return True
 
     try:
-        r = requests.get(url, timeout=15)
+        r = requests.get(url, timeout=5, stream=True)
+        r.raw.decode_content = True
+        text = r.raw.read(10000000+1)
+        if len(text) > 10000000:
+            raise ValueError('Too large a response')
     except (requests.exceptions.TooManyRedirects,
             requests.exceptions.ConnectionError,
             requests.exceptions.InvalidURL,
             UnicodeError,
+            ValueError,
             requests.exceptions.InvalidSchema) as error:
         notice("TROUBLE FOLLOWING URL: " + str(error))
         return
     if mobile_twitter_hack(url):
         return
-    title = bs4.BeautifulSoup(r.text, "html5lib").title
+    title = bs4.BeautifulSoup(text, "html5lib").title
     if title and title.string:
         prefix = "PAGE TITLE: "
         if show_url: