Jc @ s d Z d d k Z d d k Z y d d k l Z Wn# e j
o d d k l Z n Xd d k l Z d d k l
Z
d d k l Z l Z l
Z
d d k l Z l Z y e Wn# e j
o d d k l Z n Xy e d Z Wn e e f j
o
e Z n Xy e d
Z Wn e e f j
o
e Z n Xy e d Z Wn e e f j
o
e Z n Xy e d Z Wn% e e f j
o e e f Z n Xd
d d d d d d g Z e i d e i e i B Z e i d e i Z! e i d e i Z" e i d i# Z$ e i d e i e i B Z% e i& d Z' e i& d d h e
d 6Z( d e) f d YZ* e* Z+ e+ i, Z, e i d e i e i d e i g Z- d d! d" d# d$ d% g Z. e i d& e i e i d' e i e i d( g Z/ d) g Z0 e- e. e/ e0 d* Z1 d+ Z2 d, Z3 e1 i e3 _ d! d d" g Z4 d- g Z5 d. e4 e5 e d/ d0 Z6 d1 Z7 d2 Z8 e i d3 e i Z9 d4 Z: d S(5 sc A cleanup tool for HTML.
Removes unwanted tags and content. See the `Cleaner` class for
details.
iN( t urlsplit( t etree( t defs( t
fromstringt tostringt XHTML_NAMESPACE( t _nonst _transform_result( t Sett unichrt unicodet bytest
basestringt
clean_htmlt cleant Cleanert autolinkt
autolink_htmlt
word_breakt word_break_htmls expression\s*\(.*?\)s
@\s*imports: \s*(?:javascript|jscript|livescript|vbscript|about|mocha):s \s+s \[if[\s\n\r]+.*?][\s\n\r]*>s descendant-or-self::*[@style]s descendant-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) != '#']t
namespacest xc B s: e Z d Z e Z e Z e Z e Z e Z e Z
e Z e Z e Z
e Z e Z e Z d Z d Z e Z e Z e Z d Z e d d g Z d Z e d d d d d d d
g d d d d d d d d Z d
Z d Z d Z d Z d Z! d d Z" d Z# e$ i% d e$ i& i' Z( d Z) d Z* RS( s
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 ``