+
B*jT R t ^ RIt^ RIt^ RIHt ^ RIHt R.t]P ! R4 t
]P ! R4 t ]P ! R4 t ]P ! R4 t
]P ! R 4 t]P ! R
4 t]P ! R 4 t]P ! R 4 t]P ! R
4 t]P ! R4 t]P ! R4 t]P ! R4 t]P ! R]P, 4 t]P ! R]P, 4 t]P ! R]P, 4 t]P ! R
4 t]P ! R4 tR t R t ! R R]P< 4 t R# )z A parser for HTML and XHTML.N)unescape)html5
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&#(?:[0-9]|[xX][0-9a-fA-F])z6&(#[0-9]+|#[xX][0-9a-fA-F]+|[a-zA-Z][a-zA-Z0-9]*)[;=]?z <[a-zA-Z]z
z--!?>z-?>z0([a-zA-Z][^\t\n\r\f />]*)(?:[\t\n\r\f ]|/(?!>))*a{
(
(?<=['"\t\n\r\f /])[^\t\n\r\f />][^\t\n\r\f /=>]* # attribute name
)
([\t\n\r\f ]*=[\t\n\r\f ]* # value indicator
('[^']*' # LITA-enclosed value
|"[^"]*" # LIT-enclosed value
|(?!['"])[^>\t\n\r\f ]* # bare value
)
)?
(?:[\t\n\r\f ]|/(?!>))* # possibly followed by a space
a
[a-zA-Z][^\t\n\r\f />]* # tag name
[\t\n\r\f /]* # optional whitespace before attribute name
(?:(?<=['"\t\n\r\f /])[^\t\n\r\f />][^\t\n\r\f /=>]* # attribute name
(?:[\t\n\r\f ]*=[\t\n\r\f ]* # value indicator
(?:'[^']*' # LITA-enclosed value
|"[^"]*" # LIT-enclosed value
|(?!['"])[^>\t\n\r\f ]* # bare value
)
)?
[\t\n\r\f /]* # possibly followed by a space
)*
>?
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 V P ^ 4 pVP R4 ' d \ V4 # VP R4 ' g VR, \ 9 d \ V4 # V# ) &#=: NN)group
startswithr endswithhtml5_entities)matchrefs & (/usr/local/lib/python3.14/html/parser.py_replace_attr_charrefr ] sS
++a.C
~~d} << RN!:} J c 6 \ P \ V 4 # N) attr_charrefsubr )ss &r _unescape_attrvaluer i s 11 55r c a a ] tR t^mt oRtR#tR$tRRRR/V 3R lltV 3R ltR t R t
R
t R t R R/R
lt
R tR%R ltR tR tR%R ltR&R ltR tR tR tR tR tR tR tR tR t R t R t R t R t R! t!R"t"Vt#V ;t$# )'r a 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.
convert_charrefsT scriptingFc \ < \ SV ` 4 Wn W n V P 4 R# )aJ Initialize and reset this instance.
If convert_charrefs is true (the default), all character references
are automatically converted to the corresponding Unicode characters.
If *scripting* is false (the default), the content of the
``noscript`` element is parsed normally; if it's true,
it's returned as is without being parsed.
N)super__init__r r reset)selfr r __class__s &$$r r HTMLParser.__init__ s$ 0 "
r c < RV n RV n \ V n RV n RV n RV n \ SV `! 4 R# )z1Reset this instance. Loses all unprocessed data. z???NT) rawdatalasttaginteresting_normal interesting
cdata_elem_support_cdata
_escapabler r )r! r" s &r r HTMLParser.reset s8 - "
r c X V P V, V n V P ^ 4 R# )zyFeed data to the parser.
Call this as often as you want, with as little or as much text
as you want (may include '\n').
N)r& goaheadr! datas &&r feedHTMLParser.feed s ||d* Qr c ( V P ^4 R# )zHandle any buffered data.N)r/ r! s &r closeHTMLParser.close s
Qr Nc V P # )z)Return full source of start tag: '<...>'.)_HTMLParser__starttag_textr5 s &r get_starttag_text HTMLParser.get_starttag_text s ###r escapablec VP 4 V n W n V P R 8X d \ P ! R4 V n R# V' de V P ' gS \ P ! RV P , \ P \ P , 4 V n R# \ P ! RV P , \ P \ P , 4 V n R# ) plaintextz\zz&|])z])N) lowerr* r, recompiler) r
IGNORECASEASCII)r! elemr< s &&$r set_cdata_modeHTMLParser.set_cdata_mode s **,# ??k ) !zz% 0D
t 4 4 4 !zz*Dt*V*,--*@ BD "zz*BT__*T*,--*@ BD r c 8 \ V n R V n RV n R # )NT)r( r) r* r, r5 s &r clear_cdata_modeHTMLParser.clear_cdata_mode s - r c Wn R# )a Enable or disable support of the CDATA sections.
If enabled, "<[CDATA[" starts a CDATA section which ends with "]]>".
If disabled, "<[CDATA[" starts a bogus comments which ends with ">".
This method is not called by default. Its purpose is to be called
in custom handle_starttag() and handle_endtag() methods, with
value that depends on the adjusted current node.
See https://html.spec.whatwg.org/multipage/parsing.html#markup-declaration-open-state
for details.
N)r+ )r! flags &&r _set_support_cdata HTMLParser._set_support_cdata s
#r c J V P p^ p\ V4 pW48 Ed V P ' d V P ' gs VP RV4 pV^ 8 dY VP R\
W4^",
4 4 pV^ 8 d. \ P ! R4 P W&4 ' g EMTpMJV P P W#4 pV' d VP 4 pMV P ' d EMTpW58 dU V P ' d0 V P ' d V P \ W#V 4 4 MV P W#V 4 V P W54 pW48X d EM3VP pV! RV4 ' Ed \" P% W#4 ' d V P' V4 p MV! RV4 ' d V P) V4 p MV! RV4 ' d V P+ V4 p MuV! RV4 ' d V P- V4 p MTV! RV4 ' d V P/ V4 p M3V^, V8 g V' d V P R4 V^, p MEM3V ^ 8 Ed V' g EM!\" P% W#4 ' d EMV! RV4 ' d[ V^, V8X d V P R4 EMt\0 P% W#4 ' d EMWV P3 W#^, R 4 EM;V! RV4 ' dY TpR F5 p
VP5 W^, 4 ' g K# V\ V
4 , p M V P3 W#^, V 4 MV! R V4 ' d. V P6 ' d V P9 W#^, R 4 MW#V^ , P; 4 R
8X d V P= W#^, R 4 M_V! RV4 ' d V P3 W#^, R 4 M5V! RV4 ' d V P? W#^, R 4 M \A R 4 hTp V P W94 pEKC V! R V4 ' Ed \B P% W#4 pV' dh VPE 4 ^R p V PG V 4 VPI 4 p V! R
V ^,
4 ' g
V ^,
p V P W94 pEK \J P% W#4 pV' d8 V' d. V PG W#^, R 4 V P W44 pEMdEMbV^, V8 d- V P R 4 V P W3^, 4 pEKe EM&V! RV4 ' Ed \L P% W#4 pV' df VPE ^4 p V PO V 4 VPI 4 p V! R
V ^,
4 ' g
V ^,
p V P W94 pEK \P P% W#4 pV' d6 V' d- V PO W#^, R 4 V P W44 pMCMBV^, V8 d- V P R4 V P W3^, 4 pEK MQ R4 hV' dl W48 df V P ' d0 V P ' d V P \ W#V 4 4 MV P W#V 4 V P W44 pW#R V n R# )r <&z [\t\n\r\f ;] >w O O A ((//;
A Au(((T___$$Xgl%;<$$Wq\2q$Avu ++J#q!! %%g11 ++A.A a(( ))!,A ** **1-A a((
a(A a(( 33A6A!eq[C$$S)AAq5 #))'55 #D!,, q5A: , ,T 2 ' - -g 9 9 ! / /!
>#FA.. &8F & / /! < < !S[ 0 % '9 ++GaCN;#K338K8K8K ))'A#$-8 1Q3 --/;> ((1 7#D!,, ++GaCDM:#D!,, wst}5 ,-F GGANN1(D!$$
g1 ;;=2.D''- A%c1Q3// E q,A *00< ++GaCDM: NN1 0 UQY $$T* qa%0AC##!3 ;;q>D))$/ A%c1Q3// E q,A "((4 --gcdm< NN1 0 UQY $$S) qa%0A555q 15$$$ 'A,!78 1 .q$A r{ r c @ V P pW!V^, R8X g Q R4 hW!V^, R8X d V P V4 # W!V^ , R8X dX V P ' dF VP RV^ , 4 pV^ 8 d R# V P W!^, V 4 V^, # W!V^ , P 4 R8X dF VP RV^ , 4 pVR8X d R# V P
W!^, V 4 V^, # V P V4 # ) rT z+unexpected call to parse_html_declaration()rR rU z]]>rV r rY )r& re r+ r[ rj r? rk parse_bogus_comment)r! ru r& rw gtposs && r rg !HTMLParser.parse_html_declarationj s ,,1~% D )C D% QqS>V #%%a( (
qs^{
*t/B/B/B UAaC(A1u gc1o .q5L
qs^
!
!
#{
2LLac*E{ WqS / 07N++A. .r c p V P pVP R V4 ' g Q R4 h\ P W1^, 4 pV' g' \ P W1^, 4 pV' g R# V' d+ VP
4 pV P W1^, V 4 VP 4 # )rR z"unexpected call to parse_comment()rY ) r& r commentcloser^ commentabruptcloser r_ ri rp )r! ru reportr& r rw s &&& r re HTMLParser.parse_comment s ,,!!&!,,R.RR, ##GqS1&,,Wc:E
A !Q 0yy{r c V P pW1V^, R9 g Q R4 hVP RV^, 4 pVR8X d R# V' d V P W1^, V 4 V^, # )r~ z(unexpected call to parse_bogus_comment()r )rT rQ rY )r& r[ ri )r! ru r r& poss &&& r r HTMLParser.parse_bogus_comment ss ,,1~ - I 1H I-ll3!$ "9I !C 0 1Qwr c V P pW!V^, R8X g Q R4 h\ P W!^, 4 pV' g R# VP 4 pV P W!^, V 4 VP 4 pV# )r~ rS z unexpected call to parse_pi()rY )r& picloser^ r_ rl rp r! ru r& r rw s && r rf HTMLParser.parse_pi sp ,,1~%F'FF%w!,I KKM wsA' IIKr c h R V n V P V4 pV^ 8 d V# V P pW1V V n . p\ P W1^, 4 pV' g Q R4 hVP 4 pVP
^4 P 4 ;V n pWb8 d \ P W64 pV' g MVP
^^^4 w rp V
' g R p Mnoscriptr> F)r< TrY )r r )r9 check_for_whole_start_tagr& tagfind_tolerantr rp r r? r' attrfind_tolerantr appendstripr` r
handle_startendtaghandle_starttagCDATA_CONTENT_ELEMENTSr rE RCDATA_CONTENT_ELEMENTS)
r! ru endposr& attrsr ry tagmattrnamerest attrvaluerp s
&& r rc HTMLParser.parse_starttag s $ //2 A:M,, & 0 &&w!4;;;u IIK "[[^ 1 1 33 sj!''3A()1a(8 %HI 2 $8)BC.82 #723 7 %aO / : LL(..*I6 7A %%' k ! Wv . /M << # #C /
,222 C:$5{"##C5#9
444##C4#8
r c V P p\ P W!^, 4 pV' g Q hVP 4 pW$^,
, R8w d R# V# )r
r rY )r& locatetagendr rp r s && r r $HTMLParser.check_for_whole_start_tag sI ,, ""7aC0 u IIK Q3<3 Ir c V P pW!V^, R8X g Q R4 hVP RV^, 4 ^ 8 d R# \ P W!4 ' g2 W!^, V^, R8X d
V^, # V P V4 # \
P W!^, 4 pV' g Q hVP
4 pW$^,
, R8w d R# \ P W!^, 4 pV' g Q hVP ^4 P 4 pV P V4 V P 4 V# )r~ rQ z unexpected call to parse_endtagr rY ) r& r[ rh r r r rp r r r?
handle_endtagrH )r! ru r& r rw r s && r rd HTMLParser.parse_endtag s ,,1~%H'HH% <<QqS !A %I ++s1Q3 3&s
//22 ""7aC0 u IIK Q3<3 I !&&w!4 ukk!n""$ 3 r c J V P W4 V P V4 R # r )r r r! r r s &&&r r HTMLParser.handle_startendtag s S( 3 r c R # r r s &&&r r HTMLParser.handle_starttag r c R # r r )r! r s &&r r HTMLParser.handle_endtag
r r c R # r r r! r{ s &&r ro HTMLParser.handle_charref r r c R # r r r s &&r rs HTMLParser.handle_entityref r r c R # r r r0 s &&r r` HTMLParser.handle_data r r c R # r r r0 s &&r ri HTMLParser.handle_comment r r c R # r r )r! decls &&r rk HTMLParser.handle_decl! r r c R # r r r0 s &&r rl HTMLParser.handle_pi% r r c R # r r r0 s &&r rj HTMLParser.unknown_decl( r r ) __starttag_textr, r+ r* r r) r' r& r )scriptstylexmpiframenoembednoframes)textareatitle)T)r
)%__name__
__module__ __qualname____firstlineno____doc__r r r r r2 r6 r9 r: rE rH rL r/ rg re r rf rc r rd r r r ro rs r` ri rk rl rj __static_attributes____classdictcell__
__classcell__)r"
__classdict__s @@r r r m s 0 Y 3
4
5
O$
B
B
# O#h/2 .d<
r ) r r@ _markupbasehtmlr
html.entitiesr r __all__rA r( rt rr rn rq r rb rh r r r r VERBOSEr r locatestarttagend_tolerant endendtag
endtagfindr r
ParserBaser r r r r si "
1 . ZZ'
ZZ
%
JJ> ?
**@
AZZ => zzST zz+&
ZZ
%
**S/zz(# ZZ' :: QR JJ ZZ zz
ZZ
ZZ ) ZZ
JJsO
ZZ>
?
6|
'' |
r