CasperSecurity
o
`�wi�G � @ s� d Z ddlZddlZddlmZ dgZe�d�Ze�d�Ze�d�Z e�d�Z
e�d �Z e�d
�Z e�d �Z
e�d �Ze�d
�Ze�d�Ze�dej�Ze�d �Ze�d�ZG dd� dej�ZdS )z A parser for HTML and XHTML.� N)�unescape�
HTMLParserz[&<]z
&[a-zA-Z#]z%&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]z)&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]z <[a-zA-Z]z
</[a-zA-Z]�>z--\s*>z+([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*z]((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*aF
<[a-zA-Z][^\t\n\r\f />\x00]* # tag name
(?:[\s/]* # optional whitespace before attribute name
(?:(?<=['"\s/])[^\s/>][^\s/=>]* # attribute name
(?:\s*=+\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|"[^"]*" # LIT-enclosed value
|(?!['"])[^>\s]* # bare value
)
\s* # possibly followed by a space
)?(?:\s|/(?!>))*
)*
)?
\s* # trailing whitespace
z#</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>c @ s� e Zd ZdZdZdd�dd�Zdd� Zd d
� Zd d � Zd
Z dd� Z
dd� Z dd� Z dd� Z
dd� Zd7dd�Zdd � Zd d � Zd d � Zd!d"� Zd#d$� Zd%d&� Zd'd(� Zd)d*� Zd+d,� Zd-d.� Zd/d0� Zd1d2� Zd3d4� Z d5d6� Z d
S )8r aE Find tags and other markup and call handler functions.
Usage:
p = HTMLParser()
p.feed(data)
...
p.close()
Start tags are handled by calling self.handle_starttag() or
self.handle_startendtag(); end tags by self.handle_endtag(). The
data between tags is passed from the parser to the derived class
by calling self.handle_data() with the data as argument (the data
may be split up in arbitrary chunks). If convert_charrefs is
True the character references are converted automatically to the
corresponding Unicode character (and self.handle_data() is no
longer split in chunks), otherwise they are passed by calling
self.handle_entityref() or self.handle_charref() with the string
containing respectively the named or numeric reference as the
argument.
)�script�styleT)�convert_charrefsc C s || _ | �� dS )z�Initialize and reset this instance.
If convert_charrefs is True (the default), all character references
are automatically converted to the corresponding Unicode characters.
N)r �reset)�selfr � r
�"/usr/lib/python3.10/html/parser.py�__init__W s zHTMLParser.__init__c C s( d| _ d| _t| _d| _tj�| � dS )z1Reset this instance. Loses all unprocessed data.� z???N)�rawdata�lasttag�interesting_normal� interesting�
cdata_elem� _markupbase�
ParserBaser �r r
r
r r ` s
zHTMLParser.resetc C s | j | | _ | �d� dS )z�Feed data to the parser.
Call this as often as you want, with as little or as much text
as you want (may include '\n').
r N)r �goahead�r �datar
r
r �feedh s zHTMLParser.feedc C s | � d� dS )zHandle any buffered data.� N)r r r
r
r �closeq s zHTMLParser.closeNc C s | j S )z)Return full source of start tag: '<...>'.)�_HTMLParser__starttag_textr r
r
r �get_starttag_textw s z HTMLParser.get_starttag_textc C s$ |� � | _t�d| j tj�| _d S )Nz </\s*%s\s*>)�lowerr �re�compile�Ir )r �elemr
r
r �set_cdata_mode{ s
zHTMLParser.set_cdata_modec C s t | _d | _d S �N)r r r r r
r
r �clear_cdata_mode s
zHTMLParser.clear_cdata_modec C s | j }d}t|�}||k �rU| jr;| js;|�d|�}|dk r:|�dt||d ��}|dkr8t�d�� ||�s8�n |}n| j
� ||�}|rI|� � }n| jrN�n|}||k ro| jrf| jsf| � t
|||� �� n | � |||� � | �||�}||kr{�n�|j}|d|��r�t�||�r�| �|�} n@|d|�r�| �|�} n5|d|�r�| �|�} n*|d|�r�| �|�} n |d |�r�| �|�} n|d
|k s�|r�| � d� |d
} n�n�| dk �r�|sِn|t�||�r�n�|d|��r|d |kr�| � d� n�t�||�r�n�| �||d d � � n~|d|��r0|}d D ]}
|�|
|d
��r"|t|
�8 } n�q| �||d
|� � nS|d|��rB| �||d d � � nA|||d � �� dk�r[| � ||d d � � n(|d |��rm| �||d d � � n|d|��r| � ||d d � � nt d��|} | �|| �}n�|d|��r�t �||�}|�r�|� � d d� } | �!| � |�"� } |d| d
��s�| d
} | �|| �}q d||d � v �r�| � |||d � � | �||d �}ny|d|��rMt#�||�}|�r |� d
�} | �$| � |�"� } |d| d
��s| d
} | �|| �}q t%�||�}|�r7|�r6|� � ||d � k�r6|�"� } | |k�r.|} | �||d
�}n |d
|k �rL| � d� | �||d
�}nnJ d��||k s|�r�||k �r�| j�s�| j�ru| j�su| � t
|||� �� n | � |||� � | �||�}||d � | _ d S )Nr �<�&�" z[\s;]�</�<!--�<?�<!r � )z--!z--�-� z <![CDATA[� � � <!doctype�we should not get here!z&#����;zinteresting.search() lied)&r �lenr r �find�rfind�maxr r �searchr �start� handle_datar � updatepos�
startswith� starttagopen�match�parse_starttag� parse_endtag�
parse_comment�parse_pi�parse_html_declaration�
endtagopen�handle_comment�endswith� unknown_declr � handle_decl� handle_pi�AssertionError�charref�group�handle_charref�end� entityref�handle_entityref�
incomplete) r rP r �i�n�j�ampposr@ r> �k�suffix�namer
r
r r � s�
��
�
�} zHTMLParser.goaheadc C s� | j }|||d � dksJ d��|||d � dkr | �|�S |||d � dkr/| �|�S |||d � �� d krX|�d
|d �}|d krId S | �||d |� � |d S | �|�S )
Nr- r, z+unexpected call to parse_html_declaration()r/ r* r0 z<![r1 r2 r r4 r )r rC �parse_marked_sectionr r7 rJ �parse_bogus_comment)r rT r �gtposr
r
r rE s
z!HTMLParser.parse_html_declarationr c C s` | j }|||d � dv sJ d��|�d|d �}|dkr dS |r,| �||d |� � |d S )Nr- )r, r) z"unexpected call to parse_comment()r r4 r )r r7 rG )r rT �reportr �posr
r
r r\ ' s z HTMLParser.parse_bogus_commentc C sd | j }|||d � dksJ d��t�||d �}|s dS |�� }| �||d |� � |�� }|S )Nr- r+ z unexpected call to parse_pi()r4 )r �picloser: r; rK rP )r rT r r@ rV r
r
r rD 3 s zHTMLParser.parse_pic C s� d | _ | �|�}|dk r|S | j}|||� | _ g }t�||d �}|s(J d��|�� }|�d��� | _}||k r�t �||�}|sCnS|�ddd�\} }
} |
sRd } n-| d d� d krd| dd � ksyn | d d� d krw| dd � krn n| dd� } | r�t
| �} |� | �� | f� |�� }||k s:|||� � � } | d vr�| �
� \}
}d
| j v r�|
| j �d
� }
t| j �| j �d
� }n|t| j � }| �|||� � |S | �d �r�| �||� |S | �||� || jv r�| �|� |S ) Nr r z#unexpected call to parse_starttag()r- r0 �'r4 �")r �/>�
rc )r �check_for_whole_start_tagr �tagfind_tolerantr@ rP rN r r �attrfind_tolerantr �append�strip�getpos�countr6 r8 r< rH �handle_startendtag�handle_starttag�CDATA_CONTENT_ELEMENTSr# )r rT �endposr �attrsr@ rX �tag�m�attrname�rest� attrvaluerP �lineno�offsetr
r
r rA ? sX
&( �
�
�
zHTMLParser.parse_starttagc C s� | j }t�||�}|rU|�� }|||d � }|dkr |d S |dkr?|�d|�r-|d S |�d|�r5dS ||kr;|S |d S |dkrEdS |dv rKdS ||krQ|S |d S td ��)
Nr r �/rc r- r4 r
z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZr3 )r �locatestarttagend_tolerantr@ rP r> rL )r rT r rr rV �nextr
r
r re r s. z$HTMLParser.check_for_whole_start_tagc C s* | j }|||d � dksJ d��t�||d �}|s dS |�� }t�||�}|sn| jd ur9| �|||� � |S t�||d �}|sV|||d � dkrQ|d S | � |�S |�
d�� � }|� d|�� �}| �
|� |d S |�
d�� � }| jd ur�|| jkr�| �|||� � |S | �
|� | �� |S ) Nr- r) z unexpected call to parse_endtagr r4 r0 z</>r )r � endendtagr: rP �
endtagfindr@ r r< rf r\ rN r r7 �
handle_endtagr% )r rT r r@ r] � namematch�tagnamer" r
r
r rB � s8
zHTMLParser.parse_endtagc C s | � ||� | �|� d S r$ )rm r} �r rq rp r
r
r rl � s z HTMLParser.handle_startendtagc C � d S r$ r
r� r
r
r rm � � zHTMLParser.handle_starttagc C r� r$ r
)r rq r
r
r r} � r� zHTMLParser.handle_endtagc C r� r$ r
�r rZ r
r
r rO � r� zHTMLParser.handle_charrefc C r� r$ r
r� r
r
r rR � r� zHTMLParser.handle_entityrefc C r� r$ r
r r
r
r r< � r� zHTMLParser.handle_datac C r� r$ r
r r
r
r rG � r� zHTMLParser.handle_commentc C r� r$ r
)r �declr
r
r rJ � r� zHTMLParser.handle_declc C r� r$ r
r r
r
r rK � r� zHTMLParser.handle_pic C r� r$ r
r r
r
r rI � r� zHTMLParser.unknown_decl)r ) �__name__�
__module__� __qualname__�__doc__rn r r r r r r r# r% r rE r\ rD rA re rB rl rm r} rO rR r< rG rJ rK rI r
r
r
r r ? s:
3"( )r� r r �htmlr �__all__r r rS rQ rM r? rF r` � commentcloserf rg �VERBOSEry r{ r| r r r
r
r
r �<module> s.
��