Server : Apache/2.4.52 (Ubuntu) System : Linux webserver 6.8.0-49-generic #49~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Nov 6 17:42:15 UTC 2 x86_64 User : www-data ( 33) PHP Version : 8.1.2-1ubuntu2.21 Disable Function : NONE Directory : /lib/python3.10/html/__pycache__/ |
o
�*�g�C � @ 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�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 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$� Zd%d&� Zd'd(� Zd)d*� Zd+d,� Zd-d.� Zd/d0� Zd1d2� Zd3d4� Z d5d6� Z d
S )8r aE Find tags and other markup and call handler functions.
Usage:
p = HTMLParser()
p.feed(data)
...
p.close()
Start tags are handled by calling self.handle_starttag() or
self.handle_startendtag(); end tags by self.handle_endtag(). The
data between tags is passed from the parser to the derived class
by calling self.handle_data() with the data as argument (the data
may be split up in arbitrary chunks). If convert_charrefs is
True the character references are converted automatically to the
corresponding Unicode character (and self.handle_data() is no
longer split in chunks), otherwise they are passed by calling
self.handle_entityref() or self.handle_charref() with the string
containing respectively the named or numeric reference as the
argument.
)�script�styleT)�convert_charrefsc C s || _ | �� dS )z�Initialize and reset this instance.
If convert_charrefs is True (the default), all character references
are automatically converted to the corresponding Unicode characters.
N)r �reset)�selfr � r
�"/usr/lib/python3.10/html/parser.py�__init__V s zHTMLParser.__init__c C s( d| _ d| _t| _d| _tj�| � dS )z1Reset this instance. Loses all unprocessed data.� z???N)�rawdata�lasttag�interesting_normal� interesting�
cdata_elem� _markupbase�
ParserBaser �r r
r
r r _ s
zHTMLParser.resetc C s | j | | _ | �d� dS )z�Feed data to the parser.
Call this as often as you want, with as little or as much text
as you want (may include '\n').
r N)r �goahead�r �datar
r
r �feedg s zHTMLParser.feedc C s | � d� dS )zHandle any buffered data.� N)r r r
r
r �closep s zHTMLParser.closeNc C s | j S )z)Return full source of start tag: '<...>'.)�_HTMLParser__starttag_textr r
r
r �get_starttag_textv s z HTMLParser.get_starttag_textc C s$ |� � | _t�d| j tj�| _d S )Nz </\s*%s\s*>)�lowerr �re�compile�Ir )r �elemr
r
r �set_cdata_modez 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 �r�| jr;| js;|�d|�}|dk r:|�dt||d ��}|dkr8t�d�� ||�s8�n�|}n| j
� ||�}|rI|� � }n| jrN�n�|}||k ro| jrf| jsf| � t
|||� �� n | � |||� � | �||�}||kr{�nj|j}|d|��r t�||�r�| �|�} n>|d|�r�| �|�} n3|d|�r�| �|�} n(|d|�r�| �|�} n |d |�r�| �|�} n|d
|k r�| � d� |d
} n�n| dk �r|sאn|�d |d
�} | dk r�|�d|d
�} | dk r�|d
} n| d
7 } | j�r | j�s | � t
||| � �� n | � ||| � � | �|| �}n�|d |��rlt�||�}|�rO|�� d
d� }
| �|
� |�� } |d| d
��sH| d
} | �|| �}q d||d � v �rk| � |||d
� � | �||d
�}ny|d|��r�t�||�}|�r�|�d
�}
| � |
� |�� } |d| d
��s�| d
} | �|| �}q t �||�}|�r�|�r�|�� ||d � k�r�|�� } | |k�r�|} | �||d
�}n |d
|k �r�| � d� | �||d
�}nnJ d��||k s|�r||k �r| j�s| j�r| j�s| � t
|||� �� n | � |||� � | �||�}||d � | _ d S )Nr �<�&�" z[\s;]�</�<!--�<?�<!r r 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�charref�group�handle_charref�end� entityref�handle_entityref�
incomplete) r rC r �i�n�j�ampposr: r8 �k�namer
r
r r � s�
��
�
�k 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* � z<![� z <!doctyper r. r )r r= �parse_marked_sectionr r1 � handle_decl�parse_bogus_comment)r rG r �gtposr
r
r r? � 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 r. r )r r1 �handle_comment)r rG �reportr �posr
r
r rR 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()r. )r �picloser4 r5 � handle_pirC )r rG r r: rI r
r
r r> 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- rN �'r. �")r �/>�
r[ )r �check_for_whole_start_tagr �tagfind_tolerantr: rC rA r r �attrfind_tolerantr �append�strip�getpos�countr0 r2 r6 �endswith�handle_startendtag�handle_starttag�CDATA_CONTENT_ELEMENTSr# )r rG �endposr �attrsr: rK �tag�m�attrname�rest� attrvaluerC �lineno�offsetr
r
r r; , 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 �/r[ r- r. r
z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!)r �locatestarttagend_tolerantr: rC r8 �AssertionError)r rG r rk rI �nextr
r
r r] _ s. z$HTMLParser.check_for_whole_start_tagc C s* | j }|||d � dksJ d��t�||d �}|s dS |�� }t�||�}|sn| jd ur9| �|||� � |S t�||d �}|sV|||d � dkrQ|d S | � |�S |�
d�� � }|� d|�� �}| �
|� |d S |�
d�� � }| jd ur�|| jkr�| �|||� � |S | �
|� | �� |S ) Nr- r) z unexpected call to parse_endtagr r. rN z</>r )r � endendtagr4 rC �
endtagfindr: r r6 r^ rR rA r r1 �
handle_endtagr% )r rG r r: rS � namematch�tagnamer" r
r
r r< � s8
zHTMLParser.parse_endtagc C s | � ||� | �|� d S r$ )rf rw �r rj ri r
r
r re � s z HTMLParser.handle_startendtagc C � d S r$ r
rz r
r
r rf � � zHTMLParser.handle_starttagc C r{ r$ r
)r rj r
r
r rw � r| zHTMLParser.handle_endtagc C r{ r$ r
�r rL r
r
r rB � r| zHTMLParser.handle_charrefc C r{ r$ r
r} r
r
r rE � r| zHTMLParser.handle_entityrefc C r{ r$ r
r r
r
r r6 � r| zHTMLParser.handle_datac C r{ r$ r
r r
r
r rT � r| zHTMLParser.handle_commentc C r{ r$ r
)r �declr
r
r rQ � r| zHTMLParser.handle_declc C r{ r$ r
r r
r
r rX � r| zHTMLParser.handle_pic C r{ r$ r
r r
r
r � unknown_decl� r| zHTMLParser.unknown_decl)r ) �__name__�
__module__� __qualname__�__doc__rg r r r r r r r# r% r r? rR r> r; r] r< re rf rw rB rE r6 rT rQ rX r r
r
r
r r > s8 z
3"( )r� r r �htmlr �__all__r r rF rD r@ r9 rW � commentcloser^ r_ �VERBOSErr ru rv r r r
r
r
r �<module> s,
��