File: //usr/lib64/python3.8/html/__pycache__/parser.cpython-38.pyc
U
e5d9E ã @ sÀ 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 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]ú>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 @ 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$„ Zd%d&„ Zd'd(„ Zd)d*„ Zd+d,„ Zd-d.„ Zd/d0„ Zd1d2„ Zd3d4„ Z d5d6„ Z d7d8„ Z d
S ):r aE Find tags and other markup and call handler functions.
Usage:
p = HTMLParser()
p.feed(data)
...
p.close()
Start tags are handled by calling self.handle_starttag() or
self.handle_startendtag(); end tags by self.handle_endtag(). The
data between tags is passed from the parser to the derived class
by calling self.handle_data() with the data as argument (the data
may be split up in arbitrary chunks). If convert_charrefs is
True the character references are converted automatically to the
corresponding Unicode character (and self.handle_data() is no
longer split in chunks), otherwise they are passed by calling
self.handle_entityref() or self.handle_charref() with the string
containing respectively the named or numeric reference as the
argument.
)ZscriptZstyleT)Úconvert_charrefsc C s || _ | ¡ dS )zÆInitialize and reset this instance.
If convert_charrefs is True (the default), all character references
are automatically converted to the corresponding Unicode characters.
N)r Úreset)Úselfr © r ú#/usr/lib64/python3.8/html/parser.pyÚ__init__W s zHTMLParser.__init__c C s( d| _ d| _t| _d| _tj | ¡ dS )z1Reset this instance. Loses all unprocessed data.Ú z???N)ÚrawdataÚlasttagÚinteresting_normalÚ interestingÚ
cdata_elemÚ _markupbaseÚ
ParserBaser ©r r r r r ` s
zHTMLParser.resetc C s | j | | _ | d¡ dS )z‘Feed data to the parser.
Call this as often as you want, with as little or as much text
as you want (may include '\n').
r N)r Úgoahead©r Údatar r r Úfeedh s zHTMLParser.feedc C s | d¡ dS )zHandle any buffered data.é N)r r r r r Úcloseq s zHTMLParser.closeNc C s | j S )z)Return full source of start tag: '<...>'.)Ú_HTMLParser__starttag_textr r r r Úget_starttag_textw s z HTMLParser.get_starttag_textc C s$ | ¡ | _t d| j tj¡| _d S )Nz </\s*%s\s*>)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_mode s zHTMLParser.clear_cdata_modec C sX | j }d}t|ƒ}||k rè| jrv| jsv| d|¡}|dk r | dt||d ƒ¡}|dkrpt d¡ ||¡spqè|}n*| j
||¡}|r’| ¡ }n| jrœqè|}||k rÞ| jrÌ| jsÌ| t
|||… ƒ¡ n| |||… ¡ | ||¡}||kröqè|j}|d|ƒrJt ||¡r"| |¡} n†|d|ƒr:| |¡} nn|d|ƒrR| |¡} nV|d|ƒrj| |¡} n>|d |ƒr‚| |¡} n&|d
|k rè| d¡ |d
} nqè| dk r<|s¼qè| d |d
¡} | dk rú| d|d
¡} | dk r|d
} n| d
7 } | jr*| js*| t
||| … ƒ¡ n| ||| … ¡ | || ¡}q|d |ƒrðt ||¡}|r²| ¡ d
d… }
| |
¡ | ¡ } |d| d
ƒs¢| d
} | || ¡}qn<d||d … krè| |||d
… ¡ | ||d
¡}qèq|d|ƒrÚt ||¡}|rP| d
¡}
| |
¡ | ¡ } |d| d
ƒsB| d
} | || ¡}qt ||¡}|rª|rè| ¡ ||d … krè| ¡ } | |kr”|} | ||d
¡}qèn.|d
|k rè| d¡ | ||d
¡}nqèqdst dƒ‚q|rF||k rF| jsF| jr(| js(| t
|||… ƒ¡ n| |||… ¡ | ||¡}||d … | _ d S )Nr ú<ú&é" z[\s;]ú</ú<!--ú<?ú<!r r z&#é éÿÿÿÿú;zinteresting.search() lied) r Úlenr r ÚfindÚrfindÚmaxr r Úsearchr ÚstartÚ handle_datar Z updateposÚ
startswithÚ starttagopenÚmatchÚparse_starttagÚ parse_endtagÚ
parse_commentÚparse_piÚparse_html_declarationÚcharrefÚgroupÚhandle_charrefÚendÚ entityrefÚhandle_entityrefÚ
incompleteÚAssertionError) r r@ r ÚiÚnÚjZampposr7 r5 ÚkÚnamer r r r † sÄ
ÿ
zHTMLParser.goaheadc C s¾ | j }|||d … dks"tdƒ‚|||d … dkr@| |¡S |||d … dkr^| |¡S |||d … ¡ d kr°| d
|d ¡}|d kr’d S | ||d |… ¡ |d S | |¡S d S )
Nr+ r* z+unexpected call to parse_html_declaration()é r( é z<![é z <!doctyper r, r )r rD r: Zparse_marked_sectionr r/ Ú handle_declÚparse_bogus_comment)r rE r Úgtposr r r r< s
z!HTMLParser.parse_html_declarationr c C s` | j }|||d … dks"tdƒ‚| d|d ¡}|dkr>dS |rX| ||d |… ¡ |d S )Nr+ )r* r' z"unexpected call to parse_comment()r r, r )r rD r/ Úhandle_comment)r rE Zreportr Úposr r r rN s z HTMLParser.parse_bogus_commentc C sd | j }|||d … dks"tdƒ‚t ||d ¡}|s:dS | ¡ }| ||d |… ¡ | ¡ }|S )Nr+ r) z unexpected call to parse_pi()r, )r rD Úpicloser2 r3 Ú handle_pir@ )r rE r r7 rG r r r r; ! s zHTMLParser.parse_pic C sì d | _ | |¡}|dk r |S | j}|||… | _ g }t ||d ¡}|sPtdƒ‚| ¡ }| d¡ ¡ | _ }||k r.t
||¡}|sŠq.| ddd¡\} }
} |
s¨d } n\| d d… d krÌ| dd … ksøn | d d… d krô| dd … krn n | dd… } | rt | ƒ} | | ¡ | f¡ | ¡ }ql|||…
¡ } | d kr¬| ¡ \}
}d
| j krˆ|
| j d
¡ }
t| j ƒ| j d
¡ }n|t| j ƒ }| |||… ¡ |S | d ¡rÆ| ||¡ n"| ||¡ || jkrè| |¡ |S ) Nr r z#unexpected call to parse_starttag()r+ rK ú'r, ú")r ú/>Ú
rV )r Úcheck_for_whole_start_tagr Útagfind_tolerantr7 rD r@ r> r r
Úattrfind_tolerantr ÚappendÚstripZgetposÚcountr. r0 r4 ÚendswithÚhandle_startendtagÚhandle_starttagÚCDATA_CONTENT_ELEMENTSr! )r rE Úendposr Úattrsr7 rH ÚtagÚmÚattrnameÚrestZ attrvaluer@ ÚlinenoÚoffsetr r r r8 - s\
&
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/rV r+ r, r z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!)r Úlocatestarttagend_tolerantr7 r@ r5 rD )r rE r re rG Únextr r r rX ` s. z$HTMLParser.check_for_whole_start_tagc C s. | j }|||d … dks"tdƒ‚t ||d ¡}|s:dS | ¡ }t ||¡}|sÜ| jd k rr| |||… ¡ |S t ||d ¡}|s¬|||d … dkr¢|d S |
|¡S | d¡ ¡ }|
d| ¡ ¡}| |¡ |d S | d¡ ¡ }| jd k r|| jkr| |||… ¡ |S | |¡ | ¡ |S ) Nr+ r' z unexpected call to parse_endtagr r, rK z</>r )r rD Ú endendtagr2 r@ Ú
endtagfindr7 r r4 rY rN r> r r/ Ú
handle_endtagr# )r rE r r7 rO Z namematchZtagnamer r r r r9 ‚ s8
zHTMLParser.parse_endtagc C s | ||¡ | |¡ d S r" )r` ro ©r rd rc r r r r_ ª s z HTMLParser.handle_startendtagc C s d S r" r rp r r r r` ¯ s zHTMLParser.handle_starttagc C s d S r" r )r rd r r r ro ³ s zHTMLParser.handle_endtagc C s d S r" r ©r rI r r r r? · s zHTMLParser.handle_charrefc C s d S r" r rq r r r rB » s zHTMLParser.handle_entityrefc C s d S r" r r r r r r4 ¿ s zHTMLParser.handle_datac C s d S r" r r r r r rP Ã s zHTMLParser.handle_commentc C s d S r" r )r Zdeclr r r rM Ç s zHTMLParser.handle_declc C s d S r" r r r r r rS Ë s zHTMLParser.handle_pic C s d S r" r r r r r Ú unknown_declÎ 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 Ò s
þzHTMLParser.unescape)r ) Ú__name__Ú
__module__Ú __qualname__Ú__doc__ra r
r r r r r r! r# r r< rN r; r8 rX r9 r_ r` ro r? rB r4 rP rM rS rr r r r r r r ? s8 z
3"()r{ r rt r Zhtmlr Ú__all__r r rC rA r= r6 rR Z commentcloserY rZ ÚVERBOSErk rm rn r r r r r r Ú<module> s,
ÿò