(8:15 d Z ddlZddlZddlmZ ddlmZ ddlm Z ddl
m Z m Z m
Z
eZn# e$ r eefZY nw xY w ddlmZ n# e$ r ddlmZ Y nw xY w ddlmZ n# e$ r ddlmZ Y nw xY w G d d
e Z dd lmZ G d d
e Z e Zn # e$ r Y nw xY wd Z ddZ ddZ ddZ ddZ ddZ!d Z" e Z#dS )z?
An interface to html5lib that mimics the lxml.html interface.
N)
HTMLParser) TreeBuilder)etree)ElementXHTML_NAMESPACE_contains_block_level_tag)urlopen)urlparsec e Zd ZdZddZdS )r z*An html5lib HTML parser with lxml as tree.Fc : t j | f|t d| d S N)stricttree) _HTMLParser__init__r selfr kwargss w/builddir/build/BUILD/imunify360-venv-2.6.2/opt/imunify360/venv/lib64/python3.11/site-packages/lxml/html/html5parser.pyr zHTMLParser.__init__ s( TM&{MMfMMMMM NF__name__
__module__ __qualname____doc__r r r r r s4 44N N N N N Nr r ) XHTMLParserc e Zd ZdZddZdS )r z+An html5lib XHTML Parser with lxml as tree.Fc : t j | f|t d| d S r
) _XHTMLParserr r r s r r zXHTMLParser.__init__* s( !$ RvK R R6 R R R R Rr Nr r r r r r r ' s4 99 S S S S S Sr r c t | | }||S | dt d| S )N{})findr )r tagelems r _find_tagr( 0 s; 99S>>D 999 ##6 7 77r c t | t st d |t }i }|t | t rd}|||d< |j | fi | S )z
Parse a whole document into a string.
If `guess_charset` is true, or if the input is not Unicode but a
byte string, the `chardet` library will perform charset guessing
on the string.
string requiredNT
useChardet)
isinstance_strings TypeError html_parserbytesparsegetroot)html
guess_charsetparseroptionss r document_fromstringr7 7 s dH % % +)***
~ G D%!8!8
- 6< ( ( ( ( 0 0 2 22r Fc t t | t st d |t }i }|t | t rd}|||d< |j | dfi |}|rWt |d t r<|r:|d r t j d|d z |d= |S )a` Parses several HTML elements, returning a list of elements.
The first item in the list may be a string. If no_leading_text is true,
then it will be an error if there is leading text, and it will always be
a list of only elements.
If `guess_charset` is true, the `chardet` library will perform charset
guessing on the string.
r* NFr+ divr zThere is leading text: %r) r, r- r. r/ r0
parseFragmentstripr ParserError)r3 no_leading_textr4 r5 r6 childrens r fragments_fromstringr? O s dH % % +)***
~ G D%!8!8
- #v#D%;;7;;H Jx{H55 { ""
5'(C(0 )4 5 5 5 Or c | t | t st d t | }t | ||| }|rjt |t sd}t | }|r@t |d t r|d |_ |d= | | |S |st j d t | dk rt j d |d }|j r5|j r t j d|j z d |_ |S )
a Parses a single HTML element; it is an error if there is more than
one element, or if anything but whitespace precedes or follows the
element.
If 'create_parent' is true (or is a tag name) then a parent node
will be created to encapsulate the HTML in a single element. In
this case, leading or trailing text is allowed.
If `guess_charset` is true, the `chardet` library will perform charset
guessing on the string.
r* )r4 r5 r= r9 r zNo elements found zMultiple elements foundz Element followed by text: %rN)
r, r- r. boolr? r textextendr r< lentailr; )r3
create_parentr4 r5 accept_leading_textelementsnew_rootresults r fragment_fromstringrL q sU dH % % +)*** }--# M& //1 1 1H -22 " !M=)) &(1+x00
(
QK OOH % % % 5 3444
8}}q 9:::
a[F
{ Nv{((** N > LMMMFK Mr c t | t st d t | || }| dd }t |t r| dd }| }| d s| d r|S t |d }t | r|S t |d
}t | d k rT|j r|j s4|d j
r |d j
s|d
S t | rd|_ nd|_ |S )a Parse the html, returning a single element/document.
This tries to minimally parse the chunk of text, without knowing if it
is a fragment or a document.
'base_url' will set the document's base_url attribute (and the tree's
docinfo.URL)
If `guess_charset` is true, or if the input is not Unicode but a
byte string, the `chardet` library will perform charset guessing
on the string.
r* )r5 r4 N2 asciireplacezru s
. . . . . . 8 8 8 8 8 8 I I I I I I I I I I HH s|HHH ' ' ' '&&&&&&&&'&!!!!!!! & & &%%%%%%%%&N N N N N N N N !444444S S S S Sl S S S ;==LL D 8 8 83 3 3 30 0548 D -237) ) ) )X3 3 3 3l!' !' !' !'H
jll sA + 77A AAA A)(A);B B"!B"