Merge branch 'master' of prism:stockholm

2 files changed, 30 insertions, 10 deletions

diff --git a/krebs/5pkgs/simple/Reaktor/plugins.nix b/krebs/5pkgs/simple/Reaktor/plugins.nix
index bcfcbf76b..f3b771190 100644
--- a/krebs/5pkgs/simple/Reaktor/plugins.nix
+++ b/krebs/5pkgs/simple/Reaktor/plugins.nix
@@ -120,11 +120,24 @@ rec {
   url-title = (buildSimpleReaktorPlugin "url-title" {
     pattern = "^.*(?P<args>http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+).*$$";
     path = with pkgs; [ curl perl ];
-    script = pkgs.writeDash "lambda-pl" ''
-      if [ "$#" -gt 0 ]; then
-        curl -SsL --max-time 5 "$1" |
-          perl -l -0777 -ne 'print $1 if /<title.*?>\s*(.*?)\s*<\/title/si'
-      fi
+    script = pkgs.writePython3 [ "beautifulsoup4" "lxml" ] "url-title" ''
+      import sys
+      import urllib.request
+      from bs4 import BeautifulSoup
+
+      try:
+          soup = BeautifulSoup(urllib.request.urlopen(sys.argv[1]), "lxml")
+          title = soup.find('title').string
+
+          if title:
+              if len(title) > 512:
+                  print('message to long, skipped')
+              elif len(title.split('\n')) > 5:
+                  print('to many lines, skipped')
+              else:
+                  print(title)
+      except:  # noqa: E722
+          pass
     '';
   });
 
diff --git a/krebs/5pkgs/simple/Reaktor/scripts/sed-plugin.py b/krebs/5pkgs/simple/Reaktor/scripts/sed-plugin.py
index da8e2f726..51ac7a071 100644
--- a/krebs/5pkgs/simple/Reaktor/scripts/sed-plugin.py
+++ b/krebs/5pkgs/simple/Reaktor/scripts/sed-plugin.py
@@ -18,20 +18,27 @@ def is_regex(line):
     myre = re.compile(r'^s/(?:\\/|[^/])+/(?:\\/|[^/])*/[ig]?$')
     return myre.match(line)
 
+
 line = argv[1]
 
 if is_regex(line):
     last = d.get(usr, None)
     if last:
         from subprocess import Popen, PIPE
-        p = Popen(['sed', line], stdin=PIPE, stdout=PIPE)
+        p = Popen(['sed', line], stdin=PIPE, stdout=PIPE, stderr=PIPE)
         so, se = p.communicate(bytes("{}\n".format(last), "UTF-8"))
         if p.returncode:
-            print("something went wrong when trying to process your regex: {}".format(se.decode()))
+            print("something went wrong when trying to process your regex: {}".format(line.strip()))
         ret = so.decode()
-        print("\x1b[1m{}\x1b[0m meant: {}".format(usr, ret.strip()))
-        if ret:
-            d[usr] = ret
+        if len(ret) > 512:
+            print('message to long, skipped')
+        elif len(ret.split('\n')) > 5:
+            print('to many lines, skipped')
+        else:
+            if last.strip() != ret.strip():
+                print("\x1b[1m{}\x1b[0m meant: {}".format(usr, ret.strip()))
+                if ret:
+                    d[usr] = ret
 
     else:
         print("no last message")