Spaces:

JPLTedCas
/

MarkCitrus

Sleeping

JPLTedCas commited on Jul 13, 2023

Commit

18aab9e

1 Parent(s): bedcf36

Update RemoveHTMLtags.py

Files changed (1) hide show

RemoveHTMLtags.py CHANGED Viewed

@@ -1,8 +1,5 @@
-# Import Module
-from bs4 import BeautifulSoup
-# HTML Document
-HTML_DOC = """
               <html>
                 <head>
                     <title> Geeksforgeeks </title>
@@ -14,21 +11,10 @@ HTML_DOC = """
                     <div>Computer Science portal.</div>
                 </body>
               </html>
-            """
-# Function to remove tags
-def remove_tags(html):
-    # parse html content
-    soup = BeautifulSoup(html, "html.parser")
-    for data in soup(['style', 'script']):
-        # Remove tags
-        data.decompose()
-    # return data by retrieving the tag content
-    return ' '.join(soup.stripped_strings)
-# Print the extracted data
-print(remove_tags(HTML_DOC))

+from bs4 import BeautifulSoup #line:2
+HTML_DOC ="""
               <html>
                 <head>
                     <title> Geeksforgeeks </title>
                     <div>Computer Science portal.</div>
                 </body>
               </html>
+            """#line:17
+def remove_tags (O0OOO0OO000O0O00O ):#line:20
+    OOOO000O000OOOO00 =BeautifulSoup (O0OOO0OO000O0O00O ,"html.parser")#line:23
+    for OOO00O000O00O0O0O in OOOO000O000OOOO00 (['style','script']):#line:25
+        OOO00O000O00O0O0O .decompose ()#line:27
+    return ' '.join (OOOO000O000OOOO00 .stripped_strings )#line:30
+print (remove_tags (HTML_DOC ))