Create remove_tags.py

pemagrg1 · web-flow · commit c0040c4390e2 · 2018-10-31T17:53:33.000+05:45
diff --git a/remove_tags.py b/remove_tags.py
@@ -0,0 +1,19 @@
+# coding: utf-8
+import nltk
+from nltk import word_tokenize
+
+def remove_Tags(text):
+    """
+    take string input and clean string without tags.
+    use regex to remove the html tags.
+    """
+    cleaned_text = re.sub('<[^<]+?>','', text)
+    return cleaned_text
+    
+def main():
+    text = """<head><body>hello world!</body></head>"""
+    print (remove_Tags(text))
+
+if __name__ == '__main__':
+    main()
+    
