B
� f9E � @ s� d Z ddlZddlZddlZddlmZ dgZe�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--\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 comma
)?(?:\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� Zd9dd�Zdd � Zd d � Zd d � Zd!d"� Zd#d$� Zd%d&� Zd'd(� Zd)d*� Zd+d,� Zd-d.� Zd/d0� Zd1d2� Zd3d4� Z d5d6� Z d7d8� Z d
S ):r aE Find tags and other markup and call handler functions.
Usage:
p = HTMLParser()
p.feed(data)
...
p.close()
Start tags are handled by calling self.handle_starttag() or
self.handle_startendtag(); end tags by self.handle_endtag(). The
data between tags is passed from the parser to the derived class
by calling self.handle_data() with the data as argument (the data
may be split up in arbitrary chunks). If convert_charrefs is
True the character references are converted automatically to the
corresponding Unicode character (and self.handle_data() is no
longer split in chunks), otherwise they are passed by calling
self.handle_entityref() or self.handle_charref() with the string
containing respectively the named or numeric reference as the
argument.
)ZscriptZstyleT)�convert_charrefsc C s || _ | �� dS )z�Initialize and reset this instance.
If convert_charrefs is True (the default), all character references
are automatically converted to the corresponding Unicode characters.
N)r �reset)�selfr � r �0/opt/alt/python37/lib64/python3.7/html/parser.py�__init__W s zHTMLParser.__init__c C s( d| _ d| _t| _d| _tj�| � dS )z1Reset this instance. Loses all unprocessed data.� z???N)�rawdata�lasttag�interesting_normal� interesting�
cdata_elem� _markupbase�
ParserBaser )r r r r r ` s
zHTMLParser.resetc C s | j | | _ | �d� dS )z�Feed data to the parser.
Call this as often as you want, with as little or as much text
as you want (may include '\n').
r N)r �goahead)r �datar r r �feedh s zHTMLParser.feedc C s | � d� dS )zHandle any buffered data.� N)r )r r r r �closeq s zHTMLParser.closeNc C s | j S )z)Return full source of start tag: '<...>'.)�_HTMLParser__starttag_text)r r r r �get_starttag_textw s z HTMLParser.get_starttag_textc C s$ |� � | _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 sN | j }d}t|�}�x�||k �r�| jrx| jsx|�d|�}|dk r�|�dt||d ��}|dkrrt�d�� ||�srP |}n(| j
� ||�}|r�|� � }n | jr�P |}||k r�| jr�| js�| � t
|||� �� n| � |||� � | �||�}||kr�P |j}|d|��rDt�||��r | �|�} n�|d|��r8| �|�} nl|d|��rP| �|�} nT|d|��rh| �|�} n<|d |��r�| �|�} n$|d
|k �r�| � d� |d
} nP | dk �r6|�s�P |�d |d
�} | dk �r�|�d|d
�} | dk �r�|d
} n| d
7 } | j�r$| j�s$| � t
||| � �� n| � ||| � � | �|| �}q|d |��r�t�||�}|�r�|�� d
d� }
| �|
� |�� } |d| d
��s�| d
} | �|| �}qn:d||d � k�r�| � |||d
� � | �||d
�}P q|d|��r�t�||�}|�rH|�d
�}
| � |
� |�� } |d| d
��s:| d
} | �|| �}qt �||�}|�r�|�r�|�� ||d � k�r�|�� } | |k�r�|} | �||d
�}P n,|d
|k �r�| � d� | �||d
�}nP qdst d��qW |�r<||k �r<| j�s<| j�r | j�s | � t
|||� �� n| � |||� � | �||�}||d � | _ d S )Nr �<�&�" z[\s;]z</z<!--z<?z<!r r z&#� ����;zinteresting.search() lied) r �lenr r �find�rfind�maxr r �searchr �start� handle_datar Z updatepos�
startswith� starttagopen�match�parse_starttag� parse_endtag�
parse_comment�parse_pi�parse_html_declaration�charref�group�handle_charref�end� entityref�handle_entityref�
incomplete�AssertionError) r r9 r �i�n�jZampposr0 r. �k�namer r r r � s�
zHTMLParser.goaheadc C s� | j }|||d � dks"td��|||d � dkr@| �|�S |||d � dkr^| �|�S |||d � �� d kr�|�d
|d �}|d kr�d S | �||d |� � |d S | �|�S d S )
Nr$ z<!z+unexpected call to parse_html_declaration()� z<!--� z<![� z <!doctyper r% r )r r= r3 Zparse_marked_sectionr r( � handle_decl�parse_bogus_comment)r r> r �gtposr r r r5 s
z!HTMLParser.parse_html_declarationr c C s` | j }|||d � dks"td��|�d|d �}|dkr>dS |rX| �||d |� � |d S )Nr$ )z<!z</z"unexpected call to parse_comment()r r% r )r r= r( �handle_comment)r r> Zreportr �posr r r rG s z HTMLParser.parse_bogus_commentc C sd | j }|||d � dks"td��t�||d �}|s:dS |�� }| �||d |� � |�� }|S )Nr$ z<?z unexpected call to parse_pi()r% )r r= �picloser+ r, � handle_pir9 )r r> r r0 r@ r r r r4 ! s zHTMLParser.parse_pic C s� d | _ | �|�}|dk r |S | j}|||� | _ g }t�||d �}|sPtd��|�� }|�d��� | _ }x�||k �r.t
�||�}|s�P |�ddd�\} }
} |
s�d } n\| d d� d kr�| dd � ks�n | d d� d kr�| dd � k�rn n | dd� } | �rt | �} |� | �� | f� |�� }qnW |||� �
� } | d k�r�| �� \}
}d
| j k�r�|
| j �d
� }
t| j �| j �d
� }n|t| j � }| �|||� � |S | �d ��r�| �||� n"| �||� || jk�r�| �|� |S ) Nr r z#unexpected call to parse_starttag()r$ rD �'r% �")r z/>�
z/>)r �check_for_whole_start_tagr �tagfind_tolerantr0 r= r9 r7 r r
�attrfind_tolerantr �append�stripZgetpos�countr' r) r- �endswith�handle_startendtag�handle_starttag�CDATA_CONTENT_ELEMENTSr )r r> �endposr �attrsr0 rA �tag�mZattrname�restZ attrvaluer9 �lineno�offsetr r r r1 - sR
&*
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 �/z/>r$ r% r z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!)r �locatestarttagend_tolerantr0 r9 r. r= )r r> r r] r@ �nextr r r rP ` s. z$HTMLParser.check_for_whole_start_tagc C s. | j }|||d � dks"td��t�||d �}|s:dS |�� }t�||�}|s�| jd k rr| �|||� � |S t �||d �}|s�|||d � dkr�|d S | �
|�S |� d�� � }|�
d|�� �}| �|� |d S |� d�� � }| jd k �r|| jk�r| �|||� � |S | �|� | �� |S ) Nr$ z</z unexpected call to parse_endtagr r% rD z</>r )r r= � endendtagr+ r9 �
endtagfindr0 r r- rQ rG r7 r r( �
handle_endtagr )r r> r r0 rH Z namematchZtagnamer r r r r2 � s8
zHTMLParser.parse_endtagc C s | � ||� | �|� d S )N)rX rf )r r\ r[ r r r rW � s z HTMLParser.handle_startendtagc C s d S )Nr )r r\ r[ r r r rX � s zHTMLParser.handle_starttagc C s d S )Nr )r r\ r r r rf � s zHTMLParser.handle_endtagc C s d S )Nr )r rB r r r r8 � s zHTMLParser.handle_charrefc C s d S )Nr )r rB r r r r; � s zHTMLParser.handle_entityrefc C s d S )Nr )r r r r r r- � s zHTMLParser.handle_datac C s d S )Nr )r r r r r rI � s zHTMLParser.handle_commentc C s d S )Nr )r Zdeclr r r rF � s zHTMLParser.handle_declc C s d S )Nr )r r r r r rL � s zHTMLParser.handle_pic C s d S )Nr )r r r r r � unknown_decl� 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.r$ )�
stacklevel)�warnings�warn�DeprecationWarningr )r �sr r r r � s
zHTMLParser.unescape)r ) �__name__�
__module__� __qualname__�__doc__rY r
r r r r r r r r r5 rG r4 r1 rP r2 rW rX rf r8 r; r- rI rF rL rg r r r r r r ? s8 z
3"()rp r ri r Zhtmlr �__all__r r r< r: r6 r/ rK Z commentcloserQ rR �VERBOSErb rd re r r r r r r �<module> s(