moved strip_html from http to text

plugins/util/text.py

@@ -6,6 +6,35 @@
 
 import re
 
+from HTMLParser import HTMLParser
+import htmlentitydefs
+
+
+class HTMLTextExtractor(HTMLParser):
+    def __init__(self):
+        HTMLParser.__init__(self)
+        self.result = []
+
+    def handle_data(self, d):
+        self.result.append(d)
+
+    def handle_charref(self, number):
+        codepoint = int(number[1:], 16) if number[0] in (u'x', u'X') else int(number)
+        self.result.append(unichr(codepoint))
+
+    def handle_entityref(self, name):
+        codepoint = htmlentitydefs.name2codepoint[name]
+        self.result.append(unichr(codepoint))
+
+    def get_text(self):
+        return u''.join(self.result)
+
+
+def strip_html(html):
+    s = HTMLTextExtractor()
+    s.feed(html)
+    return s.get_text()
+
 
 def munge(text, munge_count=0):
     """munges up text."""