3
\AE � @ s� d Z ddlZddlZddlZddlmZ dgZejd�Zejd�Z ejd�Z
ejd�Z ejd �Z ejd
�Z
ejd �Zejd �Zejd
�Zejdej�Zejd
�Zejd�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 ZdZd:Zdd�dd�Zdd � Zd
d � Zd d
� ZdZ dd� Z
dd� Z dd� Z dd� Z
dd� Zd;dd�Zd d � Zd d � Zd d!� Zd"d#� Zd$d%� Zd&d'� Zd(d)� Zd*d+� Zd,d-� Zd.d/� Zd0d1� Zd2d3� Zd4d5� Z d6d7� Z d8d9� Z dS )<r aE Find tags and other markup and call handler functions.
Usage:
p = HTMLParser()
p.feed(data)
...
p.close()
Start tags are handled by calling self.handle_starttag() or
self.handle_startendtag(); end tags by self.handle_endtag(). The
data between tags is passed from the parser to the derived class
by calling self.handle_data() with the data as argument (the data
may be split up in arbitrary chunks). If convert_charrefs is
True the character references are converted automatically to the
corresponding Unicode character (and self.handle_data() is no
longer split in chunks), otherwise they are passed by calling
self.handle_entityref() or self.handle_charref() with the string
containing respectively the named or numeric reference as the
argument.
�script�styleT)�convert_charrefsc C s || _ | j� dS )z�Initialize and reset this instance.
If convert_charrefs is True (the default), all character references
are automatically converted to the corresponding Unicode characters.
N)r �reset)�selfr � r
�#/usr/lib64/python3.6/html/parser.py�__init__W s zHTMLParser.__init__c C s( d| _ d| _t| _d| _tjj| � dS )z1Reset this instance. Loses all unprocessed data.� z???N)�rawdata�lasttag�interesting_normal� interesting�
cdata_elem� _markupbase�
ParserBaser )r r
r
r r ` s
zHTMLParser.resetc C s | j | | _ | jd� dS )z�Feed data to the parser.
Call this as often as you want, with as little or as much text
as you want (may include '\n').
r N)r �goahead)r �datar
r
r �feedh s zHTMLParser.feedc C s | j d� dS )zHandle any buffered data.� N)r )r r
r
r �closeq s zHTMLParser.closeNc C s | j S )z)Return full source of start tag: '<...>'.)�_HTMLParser__starttag_text)r r
r
r �get_starttag_textw s z HTMLParser.get_starttag_textc C s$ |j � | _tjd| 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 sZ | j }d}t|�}�x�||k �r�| jr|| j r||jd|�}|dk r�|jdt||d ��}|dkrvtjd�j ||� rvP |}n(| j
j ||�}|r�|j � }n | jr�P |}||k r�| jr�| j r�| j t
|||� �� n| j |||� � | j||�}||kr�P |j}|d|��rLtj||��r&| j|�} n�|d|��r>| j|�} nl|d|��rV| j|�} nT|d|��rn| j|�} n<|d |��r�| j|�} n$|d
|k �r�| j d� |d
} nP | dk �r>|�s�P |jd |d
�} | dk �r�|jd|d
�} | dk �r|d
} n| d
7 } | j�r,| j �r,| j t
||| � �� n| j ||| � � | j|| �}q|d |��r�tj||�}|�r�|j� d
d� }
| j|
� |j� } |d| d
��s�| d
} | j|| �}qn:d||d � k�r�| j |||d
� � | j||d
�}P q|d|��r�tj||�}|�rP|jd
�}
| j |
� |j� } |d| d
��sB| d
} | j|| �}qt j||�}|�r�|�r�|j� ||d � k�r�|j� } | |k�r�|} | j||d
�}P n,|d
|k �r�| j d� | j||d
�}nP qdst d��qW |�rH||k �rH| j �rH| j�r*| j �r*| j t
|||� �� n| j |||� � | j||�}||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 r; r �i�n�jZampposr2 r0 �k�namer
r
r r � s�
zHTMLParser.goaheadc C s� | j }|||d � dks"td��|||d � dkr@| j|�S |||d � dkr^| j|�S |||d � j� d kr�|jd
|d �}|d kr�d
S | j||d |� � |d S | j|�S d S )Nr& z<!z+unexpected call to parse_html_declaration()� z<!--� z<![� z <!doctyper r r( r( )r r? r5 Zparse_marked_sectionr r* � handle_decl�parse_bogus_comment)r r@ r �gtposr
r
r r7 s
z!HTMLParser.parse_html_declarationr c C s` | j }|||d � dks"td��|jd|d �}|dkr>d S |rX| j||d |� � |d S )
Nr& �<!�</z"unexpected call to parse_comment()r r )rK rL r( r( )r r? r* �handle_comment)r r@ Zreportr �posr
r
r rI s z HTMLParser.parse_bogus_commentc C sd | j }|||d � dks"td��tj||d �}|s:dS |j� }| j||d |� � |j� }|S )Nr& z<?z unexpected call to parse_pi()r r( )r r? �picloser- r. � handle_pir; )r r@ r r2 rB r
r
r r6 ! s zHTMLParser.parse_pic C s� d | _ | j|�}|dk r |S | j}|||� | _ g }tj||d �}|sPtd��|j� }|jd�j� | _ }x�||k �r0t
j||�}|s�P |jddd�\} }
} |
s�d } n^| d d� d ko�| d d � kn p�| d d� d ko�| d d � kn �r| dd
� } | �rt | �} |j | j� | f� |j� }qnW |||� j
� } | dk�r�| j� \}
}d
| j k�r�|
| j jd
� }
t| j �| j jd
� }n|t| j � }| j|||� � |S | jd ��r�| j||� n"| j||� || jk�r�| j|� |S )Nr r z#unexpected call to parse_starttag()r& rF �'�"r �/>�
r( r( r( )r rS )r �check_for_whole_start_tagr �tagfind_tolerantr2 r? r; r9 r r �attrfind_tolerantr �append�stripZgetpos�countr) r+ r/ �endswith�handle_startendtag�handle_starttag�CDATA_CONTENT_ELEMENTSr! )r r@ �endposr �attrsr2 rC �tag�mZattrname�restZ attrvaluer; �lineno�offsetr
r
r r3 - sR
(*
zHTMLParser.parse_starttagc C s� | j }tj||�}|r�|j� }|||d � }|dkr>|d S |dkr~|jd|�rZ|d S |jd|�rjd S ||krv|S |d S |dkr�d
S |dkr�d S ||kr�|S |d S td��d S ) Nr r �/z/>r& r
z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!r( r( r( )r �locatestarttagend_tolerantr2 r; r0 r? )r r@ r rb rB �nextr
r
r rU ` s. z$HTMLParser.check_for_whole_start_tagc C s2 | j }|||d � dks"td��tj||d �}|s:dS |j� }tj||�}|s�| jd k rr| j|||� � |S t j||d �}|s�|||d � dkr�|d S | j
|�S |j d�j � }|j
d|j� �}| j|� |d S |j d�j � }| jd k �r|| jk�r| j|||� � |S | j|j � � | j� |S ) Nr& z</z unexpected call to parse_endtagr rF z</>r r( )r r? � endendtagr- r; �
endtagfindr2 r r/ rV rI r9 r r* �
handle_endtagr" )r r@ r r2 rJ Z namematchZtagnamer r
r
r r4 � s8
zHTMLParser.parse_endtagc C s | j ||� | j|� d S )N)r] rk )r ra r` r
r
r r\ � s z HTMLParser.handle_startendtagc C s d S )Nr
)r ra r` r
r
r r] � s zHTMLParser.handle_starttagc C s d S )Nr
)r ra r
r
r rk � s zHTMLParser.handle_endtagc C s d S )Nr
)r rD r
r
r r: � s zHTMLParser.handle_charrefc C s d S )Nr
)r rD 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 rM � s zHTMLParser.handle_commentc C s d S )Nr
)r Zdeclr
r
r rH � s zHTMLParser.handle_declc C s d S )Nr
)r r r
r
r rP � 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 r )r ) �__name__�
__module__� __qualname__�__doc__r^ r r r r r r r! r" r r7 rI r6 r3 rU r4 r\ r] rk r: r= r/ rM rH rP rl r r
r
r
r r ? s8 z
3"()ru r rn r Zhtmlr �__all__r r r> r< r8 r1 rO Z commentcloserV rW �VERBOSErg ri rj r r r
r
r
r �<module> s(