Sid Gifari From Gifari Industries - BD Cyber Security Team
Home
/
opt
/
alt
/
python38
/
lib64
/
python3.8
/
html
/
__pycache__
/
✏️
Editing: parser.cpython-38.opt-2.pyc
U "��j�M � @ s� d dl Z d dlZd dlZd dlmZ 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 �de j�Ze �d �Ze �d�ZG dd� dej�ZdS )� 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 ZdZdd�dd�Zdd� Zdd � Zd d � Zd Zd d� Z dd� Z dd� Z dd� Z dd� Z d8dd�Zdd� Zd d � Zd d � Zd d!� Zd"d#� Zd$d%� Zd&d'� Zd(d)� Zd*d+� Zd,d-� Zd.d/� Zd0d1� Zd2d3� Zd4d5� Z d6d7� Z d S )9r )ZscriptZstyleT)�convert_charrefsc C s || _ | �� d S �N)r �reset)�selfr � r �0/opt/alt/python38/lib64/python3.8/html/parser.py�__init__X s zHTMLParser.__init__c C s: d| _ d| _t| _d | _g | _d| _d| _tj � | � d S )N� z???r � ) �rawdata�lasttag�interesting_normal� interesting� cdata_elem�_pending� _pending_len�_parse_threshold� _markupbase� ParserBaser �r r r r r a s zHTMLParser.resetc C s� | j t|�7 _ | j | jk r,| j�|� n~| jsB| j|7 _n,| j�|� | jd�| j�7 _| j�� d| _ t| j�}| �d� t| j�|k r�d| _n t| j�| _d S �Nr r r ) r �lenr r �appendr �join�clear�goahead)r �data�nr r r �feedl s zHTMLParser.feedc C s: | j r,| jd�| j �7 _| j �� d| _| �d� d S r )r r r r r r r r r r �close� s zHTMLParser.closeNc C s | j S r )�_HTMLParser__starttag_textr r r r �get_starttag_text� s z HTMLParser.get_starttag_textc C s$ |� � | _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 r )r r r r r r r �clear_cdata_mode� s zHTMLParser.clear_cdata_modec C s2 | j }d}t|�}||k �r�| jrv| jsv|�d|�}|dk r�|�dt||d ��}|dkrpt�d�� ||�sp�q�|}n*| j � ||�}|r�|� � }n| jr��q�|}||k r�| jr�| js�| � t |||� �� n| � |||� � | �||�}||kr��q�|j}|d|��r2t�||��r"| �|�} n�|d|��r:| �|�} nt|d|��rR| �|�} n\|d|��rj| �|�} nD|d |��r�| �|�} n,|d |k �s�|�r�| � d� |d } n�q�| dk �r$|�sq�t�||��rԐnL|d|��r"|d |k�r�| � d� n&t�||��r n| �||d d � � n�|d|��rz|}d D ]*} |�| |d ��r6|t| �8 } �qb�q6| �||d |� � n�|d|��r�| �||d d � � n�|||d � �� dk�r�| � ||d d � � nP|d |��r�| �||d d � � n,|d|��r| � ||d d � � nt d��|} | �|| �}q|d|��r�t �||�}|�r�|� � d d� } | �!| � |�"� } |d| d ��s�| d } | �|| �}qn<d||d � k�r�| � |||d � � | �||d �}�q�q|d|�rt#�||�}|�r6|� d �} | �$| � |�"� } |d| d ��s(| d } | �|| �}qt%�||�}|�r�|�r�|� � ||d � k�r�|�"� } | |k�rz|} | �||d �}�q�n.|d |k �r�| � d� | �||d �}n�q�qq|�r ||k �r | j�s | j�r| j�s| � t |||� �� n| � |||� � | �||�}||d � | _ d S )Nr �<�&�" z[\s;]z</�<!--z<?z<!r � )z--!z--�-� z <![CDATA[� � � <!doctype�we should not get here!z&#����;)&r r r r �find�rfind�maxr& r' �searchr �start� handle_datar Z 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 rQ r �ir �jZampposrA r? �k�suffix�namer r r r � s� � zHTMLParser.goaheadc C s� | j }|||d � dkr$| �|�S |||d � dkrB| �|�S |||d � �� dkr�|�d|d �}|dkrvdS | �||d |� � |d S | �|�S d S ) Nr2 r/ r3 z<![r4 r5 r r7 r0 r )r rD Zparse_marked_sectionr% r9 rK �parse_bogus_comment)r rU r �gtposr r r rF / s z!HTMLParser.parse_html_declarationr c C sD | j }|�d|d �}|dkr"dS |r<| �||d |� � |d S )Nr r0 r7 r )r r9 rH )r rU Zreportr �posr r r rZ D s z HTMLParser.parse_bogus_commentc C sH | j }t�||d �}|s dS |�� }| �||d |� � |�� }|S )Nr0 r7 )r �picloser< r= rL rQ )r rU r rA rV r r r rE P s zHTMLParser.parse_pic C s� d | _ | �|�}|dk r |S | j}|||� | _ g }t�||d �}|�� }|�d��� | _}||k �r t �||�}|s~�q |�ddd�\} } } | s�d } nZ| d d� d kr�| dd � ks�n | d d� d kr�| dd � kr�n n | dd� } | �rt | �} |� | �� | f� |�� }q`|||� � � } | dk�r�| � � \} }d | j k�rz| | j �d � } t| j �| j �d � }n|t| j � }| �|||� � |S | �d ��r�| �||� n"| �||� || jk�r�| �|� |S ) Nr r r0 r3 �'r7 �")r �/>� r` )r# �check_for_whole_start_tagr �tagfind_tolerantrA rQ rO r% r �attrfind_tolerantr r �stripZgetpos�countr r: r> rI �handle_startendtag�handle_starttag�CDATA_CONTENT_ELEMENTSr* )r rU �endposr �attrsrA rW �tag�m�attrname�restZ attrvaluerQ �lineno�offsetr r r rB \ sZ & � � � zHTMLParser.parse_starttagc C s� | j }t�||�}|r�|�� }|||d � }|dkr>|d S |dkr~|�d|�rZ|d S |�d|�rjdS ||krv|S |d S |dkr�dS |dkr�dS ||kr�|S |d S td ��d S ) Nr r �/r` r0 r7 r z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZr6 )r �locatestarttagend_tolerantrA rQ r? rM )r rU r rm rV �nextr r r rb � s. z$HTMLParser.check_for_whole_start_tagc C s | j }t�||d �}|s dS |�� }t�||�}|s�| jd k rV| �|||� � |S t�||d �}|s�|||d � dkr�|d S | � |�S |� d�� � }|� d|�� �}| � |� |d S |� d�� � }| jd k r�|| jkr�| �|||� � |S | � |� | �� |S )Nr r7 r0 r3 z</>r )r � endendtagr< rQ � endtagfindrA r r> rc rZ rO r% r9 � handle_endtagr+ )r rU r rA r[ Z namematchZtagnamer) r r r rC � s6 zHTMLParser.parse_endtagc C s | � ||� | �|� d S r )rh rw �r rl rk r r r rg � s z HTMLParser.handle_startendtagc C s d S r r rx r r r rh � s zHTMLParser.handle_starttagc C s d S r r )r rl r r r rw � s zHTMLParser.handle_endtagc C s d S r r �r rY r r r rP � s zHTMLParser.handle_charrefc C s d S r r ry r r r rS � s zHTMLParser.handle_entityrefc C s d S r r �r r r r r r> � s zHTMLParser.handle_datac C s d S r r rz r r r rH � s zHTMLParser.handle_commentc C s d S r r )r Zdeclr r r rK � s zHTMLParser.handle_declc C s d S r r rz r r r rL � s zHTMLParser.handle_pic C s d S r r rz r r r rJ � s zHTMLParser.unknown_declc C s t jdtdd� t|�S )NzZThe unescape method is deprecated and will be removed in 3.5, use html.unescape() instead.r0 )� stacklevel)�warnings�warn�DeprecationWarningr )r �sr r r r s �zHTMLParser.unescape)r ) �__name__� __module__� __qualname__ri r r r! r" r# r$ r* r+ r rF rZ rE rB rb rC rg rh rw rP rS r> rH rK rL rJ r r r r r r @ s8 3"()r& r| r Zhtmlr �__all__r' r rT rR rN r@ rG r] Z commentcloserc rd �VERBOSErs ru rv r r r r r r �<module> s, ��
💾 Save
❌ Cancel
