a |%bœnã@s¶dZddlmZddlZddlZddlZzddlmZddlm Z Wn"e yfddl mZm Z Yn0ddl m Z ddlmZdd lmZmZdd lmZmZzeWney¾eZYn0zeWneyÞeZYn0zeWneyeefZYn0gd ¢Ze d ejejB¡jZ e d ej¡jZ!ejdgej"ddkrTej#fnd¢RŽj$Z%e dej¡j&Z'e dej¡j&Z(e dej¡j$Z)dd„Z*e d¡jZ+e dejejB¡Z,e  -d¡Z.e j-ddeidZ/Gdd„de0ƒZ1e1ƒZ2e2j3Z3e dej¡e dej¡gZ4gd ¢Z5e d!ej¡e d"ej¡e d#¡gZ6d$gZ7e4e5e6e7fd%d&„Z8d'd(„Z9d)d*„Z:e8je:_gd+¢Z;d,gZd3d4„Z?e d5ej¡Z@d6d7„ZAdS)8zcA cleanup tool for HTML. Removes unwanted tags and content. See the `Cleaner` class for details. é)Úabsolute_importN)Úurlsplit)Ú unquote_plus)rr)Úetree)Údefs)Ú fromstringÚXHTML_NAMESPACE)Ú xhtml_to_htmlÚ_transform_result)Ú clean_htmlÚcleanÚCleanerÚautolinkÚ autolink_htmlÚ word_breakÚword_break_htmlzexpression\s*\(.*?\)z @\s*importzzdescendant-or-self::*[@style]zÂdescendant-or-self::a [normalize-space(@href) and substring(normalize-space(@href),1,1) != '#'] |descendant-or-self::x:a[normalize-space(@href) and substring(normalize-space(@href),1,1) != '#']Úx)Z namespacesc @sêeZdZdZdZdZdZdZdZdZ dZ dZ dZ dZ dZdZdZdZdZdZdZdZejZdZdZddhZdd „Zed d d d gd d d d dZdd„Zdd„Zdd„Z dd„Z!dd„Z"d"dd„Z#dd„Z$e% &de%j'¡j(Z)dd„Z*d d!„Z+dS)#r a Instances cleans the document of each of the possible offending elements. The cleaning is controlled by attributes; you can override attributes in a subclass, or set them in the constructor. ``scripts``: Removes any ``