From ba5dbfd061d328a2140f0a7541ef0fdb6acf5903 Mon Sep 17 00:00:00 2001
From: Lars-Dominik Braun <lars@6xq.net>
Date: Sun, 12 May 2019 15:37:48 +0300
Subject: behavior: Ignore invalid URLs when extracting links

Fixes #18.
---
 crocoite/behavior.py | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'crocoite/behavior.py')

diff --git a/crocoite/behavior.py b/crocoite/behavior.py
index dca9ea0..d079603 100644
--- a/crocoite/behavior.py
+++ b/crocoite/behavior.py
@@ -328,6 +328,13 @@ class ExtractLinksEvent:
     def __repr__ (self):
         return f'<ExtractLinksEvent {self.links!r}>'
 
+def mapOrIgnore (f, l):
+    for e in l:
+        try:
+            yield f (e)
+        except:
+            pass
+
 class ExtractLinks (Behavior):
     """
     Extract links from a page using JavaScript
@@ -348,7 +355,7 @@ class ExtractLinks (Behavior):
         tab = self.loader.tab
         yield self.script
         result = await tab.Runtime.evaluate (expression=str (self.script), returnByValue=True)
-        yield ExtractLinksEvent (list (set (map (URL, result['result']['value']))))
+        yield ExtractLinksEvent (list (set (mapOrIgnore (URL, result['result']['value']))))
 
 class Crash (Behavior):
     """ Crash the browser. For testing only. Obviously. """
-- 
cgit v1.2.3