JezK
Edit File: parser.cpython-39.pyc
a �i�R � @ 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�dej�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--!?>z-?>z0([a-zA-Z][^\t\n\r\f />]*)(?:[\t\n\r\f ]|/(?!>))*a{ ( (?<=['"\t\n\r\f /])[^\t\n\r\f />][^\t\n\r\f /=>]* # attribute name ) ([\t\n\r\f ]*=[\t\n\r\f ]* # value indicator ('[^']*' # LITA-enclosed value |"[^"]*" # LIT-enclosed value |(?!['"])[^>\t\n\r\f ]* # bare value ) )? (?:[\t\n\r\f ]|/(?!>))* # possibly followed by a space a [a-zA-Z][^\t\n\r\f />]* # tag name [\t\n\r\f /]* # optional whitespace before attribute name (?:(?<=['"\t\n\r\f /])[^\t\n\r\f />][^\t\n\r\f /=>]* # attribute name (?:[\t\n\r\f ]*=[\t\n\r\f ]* # value indicator (?:'[^']*' # LITA-enclosed value |"[^"]*" # LIT-enclosed value |(?!['"])[^>\t\n\r\f ]* # bare value ) )? [\t\n\r\f /]* # possibly followed by a space )* >? 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 ZdZdZdZddd�dd�Zd d � Zd d � Zd d� Z dZ dd� Z dd�dd�Z dd� Z d>dd�Zdd� Zdd � Zd?d d �Zd@d d!�Zd"d#� Zd$d%� Zd&d'� Zd(d)� Zd*d+� Zd,d-� Zd.d/� Zd0d1� Zd2d3� Zd4d5� Z d6d7� Z d8d9� Z d:d;� Z d<d=� Z dS )Ar 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. )Zscript�styleZxmpZiframeZnoembedZnoframes)Ztextarea�titleTF)�convert_charrefs� scriptingc C s || _ || _| �� dS )az Initialize and reset this instance. If convert_charrefs is true (the default), all character references are automatically converted to the corresponding Unicode characters. If *scripting* is false (the default), the content of the ``noscript`` element is parsed normally; if it's true, it's returned as is without being parsed. N)r r �reset)�selfr r � r �#/usr/lib64/python3.9/html/parser.py�__init__v s zHTMLParser.__init__c C s4 d| _ d| _t| _d| _d| _d| _tj� | � dS )z1Reset this instance. Loses all unprocessed data.� z???NT) �rawdata�lasttag�interesting_normal� interesting� cdata_elem�_support_cdata� _escapable� _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 �feed� s zHTMLParser.feedc C s | � d� dS )zHandle any buffered data.� N)r r r r r �close� s zHTMLParser.closeNc C s | j S )z)Return full source of start tag: '<...>'.)�_HTMLParser__starttag_textr r r r �get_starttag_text� s z HTMLParser.get_starttag_text�� escapablec C sp |� � | _|| _| jdkr(t�d�| _nD|rP| jsPt�d| j tjtjB �| _n t�d| j tjtjB �| _d S )N� plaintextz\Zz&|</%s(?=[\t\n\r\f />])z</%s(?=[\t\n\r\f />])) �lowerr r �re�compiler r � IGNORECASE�ASCII)r �elemr" r r r �set_cdata_mode� s � �zHTMLParser.set_cdata_modec C s t | _d | _d| _d S )NT)r r r r r r r r �clear_cdata_mode� s zHTMLParser.clear_cdata_modec C s || _ dS )a Enable or disable support of the CDATA sections. If enabled, "<[CDATA[" starts a CDATA section which ends with "]]>". If disabled, "<[CDATA[" starts a bogus comments which ends with ">". This method is not called by default. Its purpose is to be called in custom handle_starttag() and handle_endtag() methods, with value that depends on the adjusted current node. See https://html.spec.whatwg.org/multipage/parsing.html#markup-declaration-open-state for details. N)r )r �flagr r r �_set_support_cdata� s z HTMLParser._set_support_cdatac C sB | 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�| j r�| � t|||� �� n| � |||� � | �||�}||kr��q�|j}|d|��r<t�||��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�||��rԐnV|d|��r$|d |k�r�| � d� n&t�||��r n| �||d d � � �n|d|��r||}d D ]*} |�| |d ��r8|t| �8 } �qd�q8| �||d |� � n�|d|��r�| j�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� } | �#| � |�$� } |d| d ��s�| d } | �|| �}qn<d||d � v �r�| � |||d � � | �||d �}�q�q|d|��r�t%�||�}|�rB|�"d �} | �&| � |�$� } |d| d ��s4| d } | �|| �}qt'�||�}|�r�|�r�|�"� ||d � k�r�|�$� } | |k�r�|} | �||d �}�q�n.|d |k �r�| � d� | �||d �}n�q�qdsJ d��q|�r0||k �r0| j�r| j �r| � t|||� �� n| � |||� � | �||�}||d � | _ d S )Nr �<�&�" z [\t\n\r\f ;]�</�<!--�<?�<!r � )z--!z--�-� � <![CDATA[� � � <!doctypezwe should not get here!z&#����;zinteresting.search() lied)(r �lenr r �find�rfind�maxr% r& �searchr �startr � handle_datar Z updatepos� startswith� starttagopen�match�parse_starttag� parse_endtag� parse_comment�parse_pi�parse_html_declaration� endtagopen�handle_comment�endswithr � unknown_declr$ � handle_decl� handle_pi�AssertionError�charref�group�handle_charref�end� entityref�handle_entityref� incomplete) r rW r �i�n�jZampposrG rE �k�suffix�namer r r r � s� � zHTMLParser.goaheadc C st | j }|||d � dks"J d��|||d � dkr@| �|�S |||d � dkr�| jr�|�d|d �}|d k rvd S | �||d |� � |d S |||d � �� d kr�|�d |d �}|d kr�d S | �||d |� � |d S |||d � dk�rf|�d |d �}|d k �rd S ||d dk�rH| �||d |d � � n| �||d |� � |d S | �|�S d S )Nr5 r4 z+unexpected call to parse_html_declaration()r7 r2 r: r8 z]]>r r< r9 r; r r z<![�]) r rJ r r? rP r$ rQ rN �parse_bogus_comment)r r[ r r] Zgtposr r r rL N s2 z!HTMLParser.parse_html_declarationc C sp | j }|�d|�sJ d��t�||d �}|sFt�||d �}|sFdS |rh|�� }| �||d |� � |�� S )Nr2 �"unexpected call to parse_comment()r7 r< ) r rE � commentcloserB �commentabruptcloserG rC rN rW )r r[ �reportr rG r] r r r rJ p s zHTMLParser.parse_commentr c C s` | j }|||d � dv s"J d��|�d|d �}|dkr>dS |rX| �||d |� � |d S )Nr5 )r4 r1 rc r r< r )r r? rN )r r[ rf r �posr r r rb s z HTMLParser.parse_bogus_commentc C sd | j }|||d � dks"J d��t�||d �}|s:dS |�� }| �||d |� � |�� }|S )Nr5 r3 z unexpected call to parse_pi()r< )r �picloserB rC rR rW �r r[ r rG r] r r r rK � s zHTMLParser.parse_pic C s( d | _ | �|�}|dk r |S | j}|||� | _ g }t�||d �}|sPJ d��|�� }|�d��� | _}||k �r.t �||�}|s��q.|�ddd�\} } } | s�d } n\| d d� d kr�| dd � ks�n | d d� d kr�| dd � k�rn n | dd� } | �rt | �} |� | �� | f� |�� }ql|||� � � } | d v�r�| � � \} }d | j v �r�| | j �d � } t| j �| j �d � }n|t| j � }| �|||� � |S | �d ��r�| �||� n^| �||� || jv �s�| j�r�|d k�s�|d k�r | j|dd� n|| jv �r$| j|dd� |S )Nr r z#unexpected call to parse_starttag()r5 r9 �'r< �")r �/>� rl Znoscriptr# Fr! T)r �check_for_whole_start_tagr �tagfind_tolerantrG rW rU r$ r �attrfind_tolerantr �append�stripZgetpos�countr> r@ rD rO �handle_startendtag�handle_starttag�CDATA_CONTENT_ELEMENTSr r* �RCDATA_CONTENT_ELEMENTS)r r[ �endposr �attrsrG r^ �tag�m�attrname�restZ attrvaluerW �lineno�offsetr r r rH � sj & � � � ��� zHTMLParser.parse_starttagc C s> | j }t�||d �}|s J �|�� }||d dkr:dS |S )Nr r r< )r � locatetagendrG rW ri r r r rn � s z$HTMLParser.check_for_whole_start_tagc C s� | j }|||d � dks"J d��|�d|d �dk r:dS t�||�sp||d |d � dkrf|d S | �|�S t�||d �}|s�J �|�� }||d dkr�dS t�||d �}|s�J �|�d�� � }| � |� | � � |S ) Nr5 r1 z unexpected call to parse_endtagr r r< r9 r ) r r? rM rG rb r� rW ro rU r$ � handle_endtagr+ )r r[ r rG r] rz r r r rI � s& zHTMLParser.parse_endtagc C s | � ||� | �|� d S �N)ru r� �r rz ry r r r rt � s z HTMLParser.handle_startendtagc C s d S r� r r� r r r ru � s zHTMLParser.handle_starttagc C s d S r� r )r rz r r r r� s zHTMLParser.handle_endtagc C s d S r� r �r r` r r r rV s zHTMLParser.handle_charrefc C s d S r� r r� r r r rY s zHTMLParser.handle_entityrefc C s d S r� r r r r r rD s zHTMLParser.handle_datac C s d S r� r r r r r rN s zHTMLParser.handle_commentc C s d S r� r )r Zdeclr r r rQ s zHTMLParser.handle_declc C s d S r� r r r r r rR s zHTMLParser.handle_pic C s d S r� r r r r r rP s zHTMLParser.unknown_decl)T)T)r )!�__name__� __module__� __qualname__�__doc__rv rw r r r r r r r* r+ r- r rL rJ rb rK rH rn rI rt ru r� rV rY rD rN rQ rR rP r r r r r Z s> " 9 )r� r% r Zhtmlr �__all__r& r rZ rX rT rF rM rh rd re ro �VERBOSErp r� Zlocatestarttagend_tolerantZ endendtagZ endtagfindr r r r r r �<module> s4 � ��