davidcaste · August 8, 2012 11:13 · Aug 8, 2012
diff --git a/gistfile1.txt b/gistfile1.txt
@@ -0,0 +1,52 @@
+# Capture entire matched URL
+(
+    # Optional: only allow some network protocols
+    # URL protocol and a colon followed by 2 slashes
+    (?:
+        (?:
+            http|https|ftp
+        ):\\/\\/
+    )?
+
+    # Check if it is the beginning of a word
+    (?<=\\b)
+
+    # The URL must not start with the character '@'
+    (?<!\\@)
+
+    # The domain name must begin with a valid character
+    (?:[\w\d]
+
+        # Other characters allowed in the domain
+        (?:[\w\dñÑ()+,-.:=;$_!*'%?#])*
+    )
+
+    # A recognized domain is required
+    \\.
+    (?:
+        aero|arpa|asia|biz|cat|com|coop|edu|gov|inet|info|int|jobs|mil|
+        mobi|museum|name|net|org|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|
+        al|am|an|ao|aq|ar|as|at|au|aw|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|
+        bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cu|
+        cv|cx|cy|cz|de|dj|dk|dm|do|dz|ec|ee|eg|er|es|et|eu|fi|fj|fk|fm|fo|
+        fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|
+        hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|
+        km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|
+        mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|
+        ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|
+        py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|
+        st|su|sv|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|
+        ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|za|zm|zw
+    )
+
+    # Optional: Port number
+    (?::[0-9]+)?
+
+    # Characters allowed in a URL according to RF1738
+    (?:
+        \\/[\w\d()+,-.:=@;$_!*'%?#&|\\\\]*
+    )*
+
+    # Check if we have consumed all characters allowed in a URL
+    (?![\w\d()+,-./:=@;$_!*'%?#&|\\\\])
+)