File: //opt/alt/python37/lib/python3.7/site-packages/bs4/builder/__pycache__/_htmlparser.cpython-37.pyc
B
F.�`�# �
@ s� d Z dgZddlmZ yddlmZ W n2 ek
rX Z zG dd� de�ZW ddZ[X Y nX ddlZddl Z ej
dd� \Z Z Z
e dko�e d ko�e
dkZe dko�e dkZe dko�e d
kZdd lmZmZmZmZmZ dd lmZmZ dd
lmZm Z m Z dZ G dd� de�Z G dd� de �Z e dk�r�e d k�r�e�s�ddl!Z!e!�"d�Z#e#e _#e!�"de!j$�Z%e%e _%ddlm&Z&m'Z' dd� Z(dd� Z)e(e _(e)e _)dZdS )zCUse the HTMLParser library to parse HTML files that aren't too bad.�HTMLParserTreeBuilder� )�
HTMLParser)�HTMLParseErrorc @ s e Zd ZdS )r N)�__name__�
__module__� __qualname__� r r �H/opt/alt/python37/lib/python3.7/site-packages/bs4/builder/_htmlparser.pyr s r N� � � )�CData�Comment� Declaration�Doctype�ProcessingInstruction)�EntitySubstitution�
UnicodeDammit)�HTML�HTMLTreeBuilder�STRICTz html.parserc @ sT e Zd Zdd� Zdd� Zdd� Zdd� Zd d
� Zd d � Zd
d� Z dd� Z
dd� Z dS )�BeautifulSoupHTMLParserc C sD i }x(|D ] \}}|d kr d}|||< d}q
W | j �|d d |� d S )N� z"")�soup�handle_starttag)�self�name�attrsZ attr_dict�key�value� attrvaluer r r r 7 s z'BeautifulSoupHTMLParser.handle_starttagc C s | j �|� d S )N)r �
handle_endtag)r r r r r r! C s z%BeautifulSoupHTMLParser.handle_endtagc C s | j �|� d S )N)r � handle_data)r �datar r r r" F s z#BeautifulSoupHTMLParser.handle_datac
C s� |� d�r t|�d�d�}n$|� d�r8t|�d�d�}nt|�}y t|�}W n* ttfk
rv } zd}W d d }~X Y nX | �|� d S )N�x� �Xu �)�
startswith�int�lstrip�chr�
ValueError�
OverflowErrorr" )r r Z real_namer# �er r r �handle_charrefI s
z&BeautifulSoupHTMLParser.handle_charrefc C s0 t j�|�}|d k r|}nd| }| �|� d S )Nz&%s;)r ZHTML_ENTITY_TO_CHARACTER�getr" )r r � characterr# r r r �handle_entityref[ s
z(BeautifulSoupHTMLParser.handle_entityrefc C s& | j �� | j �|� | j �t� d S )N)r �endDatar" r )r r# r r r �handle_commentc s
z&BeautifulSoupHTMLParser.handle_commentc C sN | j �� |�d�r&|td�d � }n |dkr2d}| j �|� | j �t� d S )NzDOCTYPE ZDOCTYPEr )r r2 r' �lenr" r )r r# r r r � handle_declh s
z#BeautifulSoupHTMLParser.handle_declc C sN |� � �d�r$t}|td�d � }nt}| j�� | j�|� | j�|� d S )NzCDATA[)�upperr' r
r4 r r r2 r" )r r# �clsr r r � unknown_declr s
z$BeautifulSoupHTMLParser.unknown_declc C s& | j �� | j �|� | j �t� d S )N)r r2 r" r )r r# r r r � handle_pi| s
z!BeautifulSoupHTMLParser.handle_piN) r r r r r! r" r. r1 r3 r5 r8 r9 r r r r r 6 s
r c @ s< e Zd ZdZdZeZeeegZ dd� Z
d
dd�Z dd � Z dS ) r FTc O s* t rtsd|d< tr d|d< ||f| _d S )NF�strictZconvert_charrefs)�CONSTRUCTOR_TAKES_STRICT� CONSTRUCTOR_STRICT_IS_DEPRECATED�"CONSTRUCTOR_TAKES_CONVERT_CHARREFS� parser_args)r �args�kwargsr r r �__init__� s
z HTMLParserTreeBuilder.__init__Nc c sN t |t�r |dddfV dS ||g}t||d|d�}|j|j|j|jfV dS )z�
:return: A 4-tuple (markup, original encoding, encoding
declared within markup, whether any characters had to be
replaced with REPLACEMENT CHARACTER).
NFT)Zis_html�exclude_encodings)�
isinstance�strr �markupZoriginal_encodingZdeclared_html_encodingZ contains_replacement_characters)r rE Zuser_specified_encodingZdocument_declared_encodingrB Z
try_encodingsZdammitr r r �prepare_markup� s
z$HTMLParserTreeBuilder.prepare_markupc
C sd | j \}}t||�}| j|_y|�|� W n4 tk
r^ } zt�td�� |�W d d }~X Y nX d S )Na* Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help.)r> r r �feedr �warnings�warn�RuntimeWarning)r rE r? r@ �parserr- r r r rG � s
zHTMLParserTreeBuilder.feed)NNN)
r r r Zis_xmlZ picklable�
HTMLPARSER�NAMEr r ZfeaturesrA rF rG r r r r r � s
zQ\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?a�
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s+ # whitespace before attribute name
(?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
(?:\s*=\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|\"[^\"]*\" # LIT-enclosed value
|[^'\">\s]+ # bare value
)
)?
)
)*
\s* # trailing whitespace
)�tagfind�attrfindc C s6 d | _ | �|�}|dk r |S | j}|||� | _ g }t�||d �}|sPtd��|�� }||d |� �� | _}x�||k �rN| j r�t
�||�}n t �||�}|s�P |� ddd�\} }
} |
s�d } n`| d d� d kr�| dd � k�sn | d d� d k�r| dd � k�r"n n | dd� } | �r2| �
| �} |�| �� | f� |�� }qtW |||� �� } | d k�r�| �� \}
}d
| j k�r�|
| j �d
� }
t| j �| j �d
� }n|t| j � }| j �r�| �d |||� d d � f � | �|||� � |S | �d
��r| �||� n"| �||� || jk�r2| �|� |S )Nr � z#unexpected call to parse_starttag()r r
�'����")�>z/>�
z junk characters in start tag: %r� z/>)Z__starttag_textZcheck_for_whole_start_tag�rawdatarN �match�AssertionError�end�lowerZlasttagr: rO �attrfind_tolerant�groupZunescape�append�stripZgetpos�countr4 �rfind�errorr" �endswithZhandle_startendtagr ZCDATA_CONTENT_ELEMENTS�set_cdata_mode)r �i�endposrW r rX �k�tag�mZattrname�restr rZ �lineno�offsetr r r �parse_starttag� s\
(,
rm c C s$ |� � | _t�d| j tj�| _d S )Nz </\s*%s\s*>)r[ Z
cdata_elem�re�compile�IZ interesting)r �elemr r r rd s
rd T)*�__doc__�__all__Z html.parserr r � ImportErrorr- � Exception�sysrH � version_info�major�minor�releaser; r< r= Z bs4.elementr
r r r r Z
bs4.dammitr r Z bs4.builderr r r rL r r rn ro r\ �VERBOSEZlocatestarttagendrN rO rm rd r r r r �<module> s@ " L0
7