U
,a9E @ s d Z ddlZddlZddlZddlmZ dgZedZedZ edZ
edZ ed Z ed
Z
ed Zed Zed
ZedejZed
ZedZG dd dejZdS )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#c @ s e Zd ZdZdZddddZdd Zd d
Zd d Zd
Z dd Z
dd Z dd Z dd Z
dd Zd9ddZdd 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 )zInitialize 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/python38/lib64/python3.8/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)rawdatalasttaginteresting_normal interesting
cdata_elem _markupbase
ParserBaser r r r r r ` s
zHTMLParser.resetc C s | j | | _ | d dS )zFeed 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 goaheadr 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_textr r r r get_starttag_textw s z HTMLParser.get_starttag_textc C s$ | | _td| j tj| _d S )Nz )lowerr recompileIr )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 sJ | j }d}t|}||k r| jrv| jsv|d|}|dk r|dt||d }|dkrptd ||spq|}n*| j
||}|r| }n| jrq|}||k r| jr| js| t
||| n| ||| | ||}||krq|j}|d|rJt||r"| |} n|d|r:| |} nn|d|rR| |} nV|d|rj| |} n>|d |r| |} n&|d
|k r| d |d
} nq| dk r<|sq|d |d
} | dk r|d|d
} | dk r|d
} n| d
7 } | jr*| js*| t
||| n| ||| | || }q|d |rt||}|r| d
d }
| |
| } |d| d
s| d
} | || }qn
rR )r check_for_whole_start_tagr tagfind_tolerantr4 r= r; r r
attrfind_tolerantr appendstripZgetposcountr+ r- r1 endswithhandle_startendtaghandle_starttagCDATA_CONTENT_ELEMENTSr! )r rA endposr attrsr4 rD tagmattrnamerestZ attrvaluer= linenooffsetr r r r5 - sZ
&
zHTMLParser.parse_starttagc C s | j }t||}|r| }|||d }|dkr>|d S |dkr~|d|rZ|d S |d|rjdS ||krv|S |d S |dkrdS |dkrdS ||kr|S |d S td d S )
Nr r /rR r( r) r z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!)r locatestarttagend_tolerantr4 r= r2 AssertionError)r rA r ra rC nextr r r rT ` s. z$HTMLParser.check_for_whole_start_tagc C s | j }t||d }|s dS | }t||}|s| jd k rV| ||| |S t||d }|s|||d dkr|d S | |S |
d }| d| }|
| |d S |
d }| jd k r|| jkr| ||| |S |
| | |S )Nr r) r( rG zr )r endendtagr/ r=
endtagfindr4 r r1 rU rJ r; r r,
handle_endtagr# )r rA r r4 rK Z namematchZtagnamer r r r r6 s6
zHTMLParser.parse_endtagc C s | || | | d S r" )r\ rl r r` r_ r r r r[ s z HTMLParser.handle_startendtagc C s d S r" r rm r r r r\ s zHTMLParser.handle_starttagc C s d S r" r )r r` r r r rl s zHTMLParser.handle_endtagc C s d S r" r r rE r r r r< s zHTMLParser.handle_charrefc C s d S r" r rn r r r r? s zHTMLParser.handle_entityrefc C s d S r" r r r r r r1 s zHTMLParser.handle_datac C s d S r" r r r r r rL s zHTMLParser.handle_commentc C s d S r" r )r Zdeclr r r rI s zHTMLParser.handle_declc C s d S r" r r r r r rO s zHTMLParser.handle_pic C s d S r" 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)warningswarnDeprecationWarningr )r sr r r r s
zHTMLParser.unescape)r ) __name__
__module__ __qualname____doc__r] r
r r r r r r! r# r r9 rJ r8 r5 rT r6 r[ r\ rl r< r? r1 rL rI rO ro r r r r r r ? s8 z
3"()rx r rq r Zhtmlr __all__r r r@ r> r: r3 rN Z commentcloserU rV VERBOSErg rj rk r r r r r r s,