| Current File : //usr/lib/python3.6/site-packages/bs4/builder/__pycache__/_htmlparser.cpython-36.pyc |
3
6]�3 � @ s� d Z dgZddlmZ yddlmZ W n2 ek
rX Z zG dd� de�ZW Y ddZ[X 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 �r�ddl!Z!e!j"d�Z#e#e _#e!j"de!j$�Z%e%e _%ddlm&Z&m'Z' dd� Z(dd� Z)e(e _(e)e _)dZdS )zCUse the HTMLParser library to parse HTML files that aren't too bad.�HTMLParserTreeBuilder� )�
HTMLParser)�HTMLParseErrorc @ s e Zd ZdS )r N)�__name__�
__module__� __qualname__� r r �!/usr/lib/python3.6/_htmlparser.pyr s r N� � � )�CData�Comment� Declaration�Doctype�ProcessingInstruction)�EntitySubstitution�
UnicodeDammit)�HTML�HTMLTreeBuilder�STRICTz html.parserc @ sp e Zd Zdd� Zdd� Zdd� Zddd �Zd d
d �Zd d
� Zdd� Z dd� Z
dd� Z dd� Z dd� Z
dd� ZdS ) �BeautifulSoupHTMLParserc O s t j| f|�|� g | _d S )N)r �__init__� already_closed_empty_element)�self�args�kwargsr r r r 9 s z BeautifulSoupHTMLParser.__init__c C s t j|� dS )ai In Python 3, HTMLParser subclasses must implement error(), although this
requirement doesn't appear to be documented.
In Python 2, HTMLParser implements error() as raising an exception.
In any event, this method is called only on very strange markup and our best strategy
is to pretend it didn't happen and keep going.
N)�warnings�warn)r �msgr r r �errorE s z BeautifulSoupHTMLParser.errorc C s | j ||dd�}| j|� d S )NF)�handle_empty_element)�handle_starttag�
handle_endtag)r �name�attrs�tagr r r �handle_startendtagP s z*BeautifulSoupHTMLParser.handle_startendtagTc C sl i }x(|D ] \}}|d kr d}|||< d}q
W | j j|d d |�}|rh|jrh|rh| j|dd� | jj|� d S )N� z""F)�check_already_closed)�soupr" Zis_empty_elementr# r �append) r r$ r% r! Z attr_dict�key�value� attrvaluer& r r r r" [ s
z'BeautifulSoupHTMLParser.handle_starttagc C s, |r || j kr | j j|� n | jj|� d S )N)r �remover* r# )r r$ r) r r r r# w s z%BeautifulSoupHTMLParser.handle_endtagc C s | j j|� d S )N)r* � handle_data)r �datar r r r0 � s z#BeautifulSoupHTMLParser.handle_datac C s� |j d�r t|jd�d�}n$|j d�r8t|jd�d�}nt|�}d }|dk r�xR| jjdfD ]B}|sdqZyt|g�j|�}W qZ tk
r� } zW Y d d }~X qZX qZW |s�y t|�}W n& t t
fk
r� } zW Y d d }~X nX |p�d}| j |� d S )N�x� �X� z windows-1252u �) �
startswith�int�lstripr* �original_encoding� bytearray�decode�UnicodeDecodeError�chr�
ValueError�
OverflowErrorr0 )r r$ Z real_namer1 �encoding�er r r �handle_charref� s*
z&BeautifulSoupHTMLParser.handle_charrefc C s0 t jj|�}|d k r|}nd| }| j|� d S )Nz&%s)r ZHTML_ENTITY_TO_CHARACTER�getr0 )r r$ � characterr1 r r r �handle_entityref� s
z(BeautifulSoupHTMLParser.handle_entityrefc C s& | j j� | j j|� | j jt� d S )N)r* �endDatar0 r )r r1 r r r �handle_comment� s
z&BeautifulSoupHTMLParser.handle_commentc C sN | j j� |jd�r&|td�d � }n |dkr2d}| j j|� | j jt� d S )NzDOCTYPE ZDOCTYPEr( )r* rF r6 �lenr0 r )r r1 r r r � handle_decl� s
z#BeautifulSoupHTMLParser.handle_declc C sN |j � jd�r$t}|td�d � }nt}| jj� | jj|� | jj|� d S )NzCDATA[)�upperr6 r
rH r r* rF r0 )r r1 �clsr r r � unknown_decl� s
z$BeautifulSoupHTMLParser.unknown_declc C s& | j j� | j j|� | j jt� d S )N)r* rF r0 r )r r1 r r r � handle_pi� s
z!BeautifulSoupHTMLParser.handle_piN)T)T)r r r r r r' r" r# r0 rB rE rG rI rL rM r r r r r 7 s
!
r c @ s< e Zd ZdZdZeZeeegZ dd� Z
d
dd�Z dd � Z dS ) r FTc O s, t rt rd|d< tr d|d< ||f| _d S )NF�strictZconvert_charrefs)�CONSTRUCTOR_TAKES_STRICT� CONSTRUCTOR_STRICT_IS_DEPRECATED�"CONSTRUCTOR_TAKES_CONVERT_CHARREFS� parser_args)r r r r r r r � 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 �markupr9 Zdeclared_html_encodingZ contains_replacement_characters)r rV Zuser_specified_encodingZdocument_declared_encodingrS Z
try_encodingsZdammitr r r �prepare_markup� s
z$HTMLParserTreeBuilder.prepare_markupc C sr | j \}}t||�}| j|_y|j|� |j� W n4 tk
rf } ztjtd�� |�W Y d d }~X nX g |_ d S )Na* Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help.)
rR r r* �feed�closer r r �RuntimeWarningr )r rV r r �parserrA r r r rX � s
zHTMLParserTreeBuilder.feed)NNN)
r r r Zis_xmlZ picklable�
HTMLPARSER�NAMEr r Zfeaturesr rW rX r r r r r � s
zQ\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?a�
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s+ # whitespace before attribute name
(?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
(?:\s*=\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|\"[^\"]*\" # LIT-enclosed value
|[^'\">\s]+ # bare value
)
)?
)
)*
\s* # trailing whitespace
)�tagfind�attrfindc C s8 d | _ | j|�}|dk r |S | j}|||� | _ g }tj||d �}|sPtd��|j� }||d |� j� | _}x�||k �rP| j r�t
j||�}n t j||�}|s�P |j ddd�\} }
} |
s�d } nb| d d� d ko�| d
d � kn �s| d d� d k�o| dd � kn �r$| dd� } | �r4| j
| �} |j| j� | f� |j� }qtW |||� j� } | dk�r�| j� \}
}d
| j k�r�|
| j jd
� }
t| j �| j jd
� }n|t| j � }| j �r�| jd |||� d d � f � | j|||� � |S | jd ��r| j||� n"| j||� || jk�r4| j|� |S )Nr � z#unexpected call to parse_starttag()r r
�'�"�>�/>�
z junk characters in start tag: %r� ���rg rg )rc rd )Z__starttag_textZcheck_for_whole_start_tag�rawdatar^ �match�AssertionError�end�lowerZlasttagrN r_ �attrfind_tolerant�groupZunescaper+ �stripZgetpos�countrH �rfindr r0 �endswithr' r" ZCDATA_CONTENT_ELEMENTS�set_cdata_mode)r �i�endposrh r% ri �kr& �mZattrname�restr. rk �lineno�offsetr r r �parse_starttag s\
*,
r{ c C s$ |j � | _tjd| j tj�| _d S )Nz </\s*%s\s*>)rl Z
cdata_elem�re�compile�IZ interesting)r �elemr r r rs T s
rs T)*�__doc__�__all__Z html.parserr r � ImportErrorrA � Exception�sysr � version_info�major�minor�releaserO rP rQ Z bs4.elementr
r r r r Z
bs4.dammitr r Z bs4.builderr r r r\ r r r| r} rm �VERBOSEZlocatestarttagendr^ r_ r{ rs r r r r �<module> sB " 2
7