U
"»ßj½M ã @ sÊ d Z ddlZddlZddlZddlmZ dgZe d¡Ze d¡Z e d¡Z
e d¡Z e d ¡Z e d
¡Z
e d ¡Ze d ¡Ze d
¡Ze d¡Ze dej¡Ze d ¡Ze d¡ZG dd„ dejƒZdS )z A parser for HTML and XHTML.é N)ÚunescapeÚ
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
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 @ sè e Zd ZdZdZddœdd„Zdd„ Zd d
„ Zd d „ Zd
Z dd„ Z
dd„ Z dd„ Z dd„ Z
dd„ Zd9dd„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 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)Úconvert_charrefsc C s || _ | ¡ dS )zÆInitialize and reset this instance.
If convert_charrefs is True (the default), all character references
are automatically converted to the corresponding Unicode characters.
N)r Úreset)Úselfr © r ú0/opt/alt/python38/lib64/python3.8/html/parser.pyÚ__init__X s zHTMLParser.__init__c C s: d| _ d| _t| _d| _g | _d| _d| _tj
| ¡ dS )z1Reset this instance. Loses all unprocessed data.Ú z???Nr é ) ÚrawdataÚlasttagÚinteresting_normalÚ interestingÚ
cdata_elemÚ_pendingÚ _pending_lenÚ_parse_thresholdÚ _markupbaseÚ
ParserBaser ©r r r r r a s zHTMLParser.resetc C s® | j t|ƒ7 _ | j | jk r,| j |¡ n~| jsB| j|7 _n,| j |¡ | jd | j¡7 _| j ¡ d| _ t| jƒ}| d¡ t| jƒ|k ržd| _n t| jƒ| _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 r r N) r Úlenr r Úappendr
ÚjoinÚclearÚgoahead)r ÚdataÚnr r r Úfeedl s
zHTMLParser.feedc C s: | j r,| jd | j ¡7 _| j ¡ d| _| d¡ dS )zHandle any buffered data.r r r N)r r
r r r r r r r r ÚcloseŠ s
zHTMLParser.closeNc C s | j S )z)Return full source of start tag: '<...>'.)Ú_HTMLParser__starttag_textr r r r Úget_starttag_text” s z HTMLParser.get_starttag_textc C s$ | ¡ | _t d| j tj¡| _d S )Nz )Úlowerr ÚreÚcompileÚIr )r Úelemr r r Úset_cdata_mode˜ s
zHTMLParser.set_cdata_modec C s t | _d | _d S ©N)r r r r r r r Úclear_cdata_modeœ s zHTMLParser.clear_cdata_modec C s2 | j }d}t|ƒ}||k rÂ| jrv| jsv| d|¡}|dk r | dt||d ƒ¡}|dkrpt d¡ ||¡spqÂ|}n*| j
||¡}|r’| ¡ }n| jrœqÂ|}||k rÞ| jrÌ| jsÌ| t
|||… ƒ¡ n| |||… ¡ | ||¡}||kröqÂ|j}|d|ƒr2t ||¡r"| |¡} nŒ|d|ƒr:| |¡} nt|d|ƒrR| |¡} n\|d|ƒrj| |¡} nD|d |ƒr‚| |¡} n,|d
|k s–|rÂ| d¡ |d
} nqÂ| dk r$|sÂqÂt ||¡rÔnL|d|ƒr"|d |krú| d¡ n&t ||¡r
n| ||d d … ¡ nþ|d|ƒrz|}d D ]*}
| |
|d
¡r6|t|
ƒ8 } qbq6| ||d
|… ¡ n¦|d|ƒrž| ||d d … ¡ n‚|||d … ¡ dkrÐ| ||d d … ¡ nP|d |ƒrô| ||d d … ¡ n,|d|ƒr| ||d d … ¡ nt dƒ‚|} | || ¡}q|d|ƒrØt ||¡}|rš| ¡ d d… } | !| ¡ | "¡ } |d| d
ƒsŠ| d
} | || ¡}qn ÚkÚsuffixÚnamer r r r £ sä
ÿ
zHTMLParser.goaheadc C s¢ | j }|||d … dkr$| |¡S |||d … dkrB| |¡S |||d … ¡ dkr”| d|d ¡}|dkrvdS | ||d |… ¡ |d
S | |¡S d S ) Nr1 r. r2 zÚ
r_ )r! Úcheck_for_whole_start_tagr
Útagfind_tolerantr@ rP rN r# r Úattrfind_tolerantr r ÚstripZgetposÚcountr r9 r= rH Úhandle_startendtagÚhandle_starttagÚCDATA_CONTENT_ELEMENTSr( )r rT Úendposr
Úattrsr@ rV ÚtagÚmÚattrnameÚrestZ attrvaluerP ÚlinenoÚoffsetr r r rA \ sZ
&
ÿ
ÿ
ÿ
zHTMLParser.parse_starttagc C s¶ | j }t ||¡}|rª| ¡ }|||d … }|dkr>|d S |dkr~| d|¡rZ|d S | d|¡rjdS ||krv|S |d S |dkrŠdS |dkr–dS ||kr¢|S |d S td ƒ‚d S )
Nr r ú/r_ r/ r6 r z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZr5 )r
Úlocatestarttagend_tolerantr@ rP r> rL )r rT r
rl rU Únextr r r ra s. z$HTMLParser.check_for_whole_start_tagc C s | j }t ||d ¡}|s dS | ¡ }t ||¡}|sÀ| jd k rV| |||… ¡ |S t ||d ¡}|s|||d … dkr†|d S | |¡S |
d¡ ¡ }| d| ¡ ¡}|
|¡ |d S |
d¡ ¡ }| jd k rø|| jkrø| |||… ¡ |S |
|¡ | ¡ |S )Nr r6 r/ r2 zr )r
Ú endendtagr; rP Ú
endtagfindr@ r r= rb rY rN r# r8 Ú
handle_endtagr* )r rT r
r@ rZ Z namematchZtagnamer' r r r rB ± s6
zHTMLParser.parse_endtagc C s | ||¡ | |¡ d S r) )rg rv ©r rk rj r r r rf Ù s z HTMLParser.handle_startendtagc C s d S r) r rw r r r rg Þ s zHTMLParser.handle_starttagc C s d S r) r )r rk r r r rv â s zHTMLParser.handle_endtagc C s d S r) r ©r rX r r r rO æ s zHTMLParser.handle_charrefc C s d S r) r rx r r r rR ê s zHTMLParser.handle_entityrefc C s d S r) r ©r r r r r r= î s zHTMLParser.handle_datac C s d S r) r ry r r r rG ò s zHTMLParser.handle_commentc C s d S r) r )r Zdeclr r r rJ ö s zHTMLParser.handle_declc C s d S r) r ry r r r rK ú s zHTMLParser.handle_pic C s d S r) r ry r r r rI ý s zHTMLParser.unknown_declc C s t jdtdd t|ƒS )NzZThe unescape method is deprecated and will be removed in 3.5, use html.unescape() instead.r/ )Ú
stacklevel)ÚwarningsÚwarnÚDeprecationWarningr )r Úsr r r r s
þzHTMLParser.unescape)r ) Ú__name__Ú
__module__Ú __qualname__Ú__doc__rh r
r r r r! r" r( r* r rE rY rD rA ra rB rf rg rv rO rR r= rG rJ rK rI r r r r r r @ s:
3"()r‚ r$ r{ r Zhtmlr Ú__all__r% r rS rQ rM r? rF r\ Z commentcloserb rc ÚVERBOSErr rt ru r r r r r r Ú s.
ÿò