MhyUddlmZdZddlmZddlZddlmZddlm Z m Z m Z m Z m Z mZmZmZmZmZmZddlZddlZddlmZmZmZmZmZmZmZmZmZm Z ddl!m"Z"dd l#m$Z$m%Z%dd l&m'Z'erdd l(m)Z)dd lm*Z*m+Z+dd l#m,Z,m-Z-m.Z.m/Z/m0Z0gdZ1dZ2dZ3dZ4dZ5dZ6dZ7gdZ1Gdde8Z9e9Z:de;d<Gdde8Z<Gdde<Z=Gdde<Z>Gdd e8Z?d*d%Z@d&d'lAmBZBe@eB d&d(lAmCZCe@eCn #eD$rYnwxYw d&d)lAmEZEe@eEdS#eD$rYdSwxYw)+) annotationsMIT) defaultdictN) ModuleType) AnycastDictIterableListOptionalPatternSetTupleType TYPE_CHECKING) AttributeDictAttributeValueListCharsetMetaAttributeValueContentMetaAttributeValueRubyParenthesisStringRubyTextString StylesheetScriptTemplateStringnonwhitespace_re)ParserRejectedMarkup)_AttributeValues_RawAttributeValue)XMLParsedAsHTMLWarning) BeautifulSoup)NavigableStringTag)_AttributeValue _Encoding _Encodings_RawOrProcessedAttributeValues _RawMarkup)HTMLTreeBuilderSAXTreeBuilder TreeBuilderTreeBuilderRegistryfast permissivestrictxmlhtmlhtml5)r+r*r(DetectsXMLParsedAsHTMLrc@eZdZUdZded<ded<ddZdd ZddZdS)r+zYA way of looking up TreeBuilder subclasses by their name or by desired features. z"Dict[str, List[Type[TreeBuilder]]]builders_for_featurezList[Type[TreeBuilder]]buildersreturnNonecFtt|_g|_dSN)rlistr4r5selfs T/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/bs4/builder/__init__.py__init__zTreeBuilderRegistry.__init__^s$/$5$5! treebuilder_classtype[TreeBuilder]c|jD]#}|j|d|$|jd|dS)zRegister a treebuilder based on its advertised features. :param treebuilder_class: A subclass of `TreeBuilder`. its `TreeBuilder.features` attribute should list its features. rN)featuresr4insertr5)r<r@features r=registerzTreeBuilderRegistry.registerbsY )1 L LG  %g . 5 5a9J K K K K Q 122222r?rCstrOptional[Type[TreeBuilder]]c*t|jdkrdSt|dkr |jdSt|}|d}d}t|dkr|}|j|g}t|dkr6||}t|}n"|t|}t|dk||dS|D] }||vr|cS dS)ajLook up a TreeBuilder subclass with the desired features. :param features: A list of features to look for. If none are provided, the most recently registered TreeBuilder subclass will be used. :return: A TreeBuilder subclass, or None if there's no registered subclass with all the requested features. rN) lenr5r:reversepopr4getset intersection)r<rC feature_list candidates candidate_setrEwe_have_the_feature candidates r=lookupzTreeBuilderRegistry.lookuplsE t}   " "4 x==A  =# #H~~   ,!##"&&((G"&";"?"?"L"L &''!++%!4J$' OOMM%2$>$>sCV?W?W$X$XM,!##  J$64# ! !IM))    *tr?Nr6r7)r@rAr6r7)rCrGr6rH)__name__ __module__ __qualname____doc____annotations__r>rFrUr?r=r+r+Vsv=<<<%%%%3333++++++r?r+builder_registryceZdZUdZeZded<eeeeeeefdAdZ dZ ded<gZ ded<gZ ded<dZ d ed<dZd ed<ded<dZded <ded<ded<d ed <d ed <eeZded!<eZded"<iZd#ed$<dZded%<dZd ed&<dBd*ZdCd+ZdDd-ZdEd0Z dFdGd7ZdHd9ZdId<ZdJd@ZdS)Kr*aTurn a textual document into a Beautiful Soup object tree. This is an abstract superclass which smooths out the behavior of different parser libraries into a single, unified interface. :param multi_valued_attributes: If this is set to None, the TreeBuilder will not turn any values for attributes like 'class' into lists. Setting this to a dictionary will customize this behavior; look at :py:attr:`bs4.builder.HTMLTreeBuilder.DEFAULT_CDATA_LIST_ATTRIBUTES` for an example. Internally, these are called "CDATA list attributes", but that probably doesn't make sense to an end-user, so the argument name is ``multi_valued_attributes``. :param preserve_whitespace_tags: A set of tags to treat the way 
 tags are treated in HTML. Tags in this set
     are immune from pretty-printing; their contents will always be
     output as-is.

    :param string_containers: A dictionary mapping tag names to
     the classes that should be instantiated to contain the textual
     contents of those tags. The default is to use NavigableString
     for every tag, no matter what the name. You can override the
     default by changing :py:attr:`DEFAULT_STRING_CONTAINERS`.

    :param store_line_numbers: If the parser keeps track of the line
     numbers and positions of the original markup, that information
     will, by default, be stored in each corresponding
     :py:class:`bs4.element.Tag` object. You can turn this off by
     passing store_line_numbers=False; then Tag.sourcepos and
     Tag.sourceline will always be None. If the parser you're using
     doesn't keep track of this information, then store_line_numbers
     is irrelevant.

    :param attribute_dict_class: The value of a multi-valued attribute
      (such as HTML's 'class') willl be stored in an instance of this
      class.  The default is Beautiful Soup's built-in
      `AttributeValueList`, which is a normal Python list, and you
      will probably never need to change it.
    rUSE_DEFAULTmulti_valued_attributesDict[str, Set[str]]preserve_whitespace_tagsSet[str]store_line_numbersboolstring_containers Dict[str, Type[NavigableString]]empty_element_tagsattribute_dict_classType[AttributeDict]attribute_value_list_classType[AttributeValueList]c*d|_||jur|j}||_||jur|j}||_||jur
|j|_n||_||jkr|j}||_	||jkr|j
}||_||_||_
dSr9)soupr_DEFAULT_CDATA_LIST_ATTRIBUTEScdata_list_attributes DEFAULT_PRESERVE_WHITESPACE_TAGSrbDEFAULT_EMPTY_ELEMENT_TAGSrhTRACKS_LINE_NUMBERSrdDEFAULT_STRING_CONTAINERSrfrirk)r<r`rbrdrfrhrirks        r=r>zTreeBuilder.__init__s	"d&666&*&H#%<"#t'777'+'L$(@%!111&*&ED##&8D#!111!%!9"4 000 $ >!2$8!*D'''r?z[Unknown tree builder]rGNAMEz
Iterable[str]ALTERNATE_NAMESrCFis_xml	picklablezOptional[BeautifulSoup]rnNzOptional[Set[str]]rptracks_line_numbersrorq,Dict[str, Type[bs4.element.NavigableString]]rtrrrsr r6r7c||_dS)zThe BeautifulSoup object has been initialized and is now
        being associated with the TreeBuilder.

        :param soup: A BeautifulSoup object.
        N)rn)r<rns  r=initialize_soupzTreeBuilder.initialize_soups			r?cdS)zDo any work necessary to reset the underlying parser
        for a new document.

        By default, this does nothing.
        Nr\r;s r=resetzTreeBuilder.resets		
r?tag_namec&|jdS||jvS)aMight a tag with this name be an empty-element tag?

        The final markup may or may not actually present this tag as
        self-closing.

        For instance: an HTMLBuilder does not consider a 
 tag to be
        an empty-element tag (it's not in
        HTMLBuilder.empty_element_tags). This means an empty 
 tag
        will be presented as "
", not "
" or "
".

        The default implementation has no opinion about which tags are
        empty-element tags, so a tag will be presented as an
        empty-element tag if and only if it has no children.
        "" will become "", and "bar" will
        be left alone.

        :param tag_name: The name of a markup tag.
        NT)rh)r<rs  r=can_be_empty_elementz TreeBuilder.can_be_empty_element"s &"*44222r?markupr'ct)z1Run incoming markup through some parsing process.NotImplementedErrorr<rs  r=feedzTreeBuilder.feed9s!###r?user_specified_encodingOptional[_Encoding]document_declared_encodingexclude_encodingsOptional[_Encodings]KIterable[Tuple[_RawMarkup, Optional[_Encoding], Optional[_Encoding], bool]]c#K|dddfVdS)aRun any preliminary steps necessary to make incoming markup
        acceptable to the parser.

        :param markup: The markup that's about to be parsed.
        :param user_specified_encoding: The user asked to try this encoding
           to convert the markup into a Unicode string.
        :param document_declared_encoding: The markup itself claims to be
            in this encoding. NOTE: This argument is not used by the
            calling code and can probably be removed.
        :param exclude_encodings: The user asked *not* to try any of
            these encodings.

        :yield: A series of 4-tuples: (markup, encoding, declared encoding,
            has undergone character replacement)

            Each 4-tuple represents a strategy that the parser can try
            to convert the document to Unicode and parse it. Each
            strategy will be tried in turn.

         By default, the only strategy is to parse the markup
         as-is. See `LXMLTreeBuilderForXML` and
         `HTMLParserTreeBuilder` for implementations that take into
         account the quirks of particular parsers.

        :meta private:

        NFr\)r<rrrrs     r=prepare_markupzTreeBuilder.prepare_markup=s$DdD%''''''r?fragmentc|S)aWrap an HTML fragment to make it look like a document.

        Different parsers do this differently. For instance, lxml
        introduces an empty  tag, and html5lib
        doesn't. Abstracting this away lets us write simple tests
        which run HTML fragments through the parser and compare the
        results against other HTML fragments.

        This method should not be used outside of unit tests.

        :param fragment: A fragment of HTML.
        :return: A full HTML document.
        :meta private:
        r\)r<rs  r=test_fragment_to_documentz%TreeBuilder.test_fragment_to_documentas	r?tagr"cdS)a,Set up any substitutions that will need to be performed on
        a `Tag` when it's output as a string.

        By default, this does nothing. See `HTMLTreeBuilder` for a
        case where this is used.

        :return: Whether or not a substitution was performed.
        :meta private:
        Fr\)r<rs  r=set_up_substitutionsz TreeBuilder.set_up_substitutionsrs	ur?attrsr&rctt|}|r|js|S|jdt	}|j|d}t
|D]X}||vs|rP||vrL||}t|tr(|
tj|}n|}|||<Y|S)a)When an attribute value is associated with a tag that can
        have multiple values for that attribute, convert the string
        value to a list of strings.

        Basically, replaces class="foo bar" with class=["foo", "bar"]

        NOTE: This method modifies its input in place.

        :param tag_name: The name of a tag.
        :param attrs: A dictionary containing the tag's attributes.
           Any appropriate attribute values will be modified in place.
        :return: The modified dictionary that was originally passed in.
        *N)
rrrprMrNlowerr:keys
isinstancerrkrfindall)	r<rrmodified_attrs	universaltag_specificattroriginal_valuemodified_values	         r=$_replace_cdata_list_attribute_valuesz0TreeBuilder._replace_cdata_list_attribute_values~s(.66	"T%?	"!!#8<rurvrCrwrxrhrrNrorqrtrrrsr|r~rrrrrrr\r?r=r*r*s@((TvxxK8C-8#.>I'24A?QEEEEEB)D((((%'O'''' H    FI!!!!.21111....&&&&7777:ES9I9I!IIII25$6666OQPPPP6:9999!&%%%%



3333.$$$$8<:>26"("("("("(H"



666666r?r*c|eZdZdZdfdZd d
Zd!dZd"dZd#dZd$dZ	d%dZ
d&dZd'dZd(dZ
d!dZd!dZxZS))r)a/A Beautiful Soup treebuilder that listens for SAX events.

    This is not currently used for anything, and it will be removed
    soon. It was a good idea, but it wasn't properly integrated into the
    rest of Beautiful Soup, so there have been long stretches where it
    hasn't worked properly.
    argsrkwargsr6r7ctjdtdtt|j|i|dS)NzThe SAXTreeBuilder class was deprecated in 4.13.0 and will be removed soon thereafter. It is completely untested and probably doesn't work; do not use it.
stacklevel)warningswarnDeprecationWarningsuperr)r>)r<rr	__class__s   r=r>zSAXTreeBuilder.__init__sR

i	
	
	
	

	-nd##,d=f=====r?rr'ctr9rrs  r=rzSAXTreeBuilder.feeds!###r?cdSr9r\r;s r=closezSAXTreeBuilder.closer?namerGrDict[str, str]ctdt|D}|jJ|j|dd|dS)Nc30K|]\}}|d|fVdS)Nr\).0keyvalues   r=	z.SAXTreeBuilder.startElement..s.TT*#us1vuoTTTTTTr?)rr:itemsrnhandle_starttag)r<rrs   r=startElementzSAXTreeBuilder.startElements^TTU[[]]@S@STTTTTy$$$	!!$dE:::::r?cL|jJ|j|dSr9)rn
handle_endtagr<rs  r=
endElementzSAXTreeBuilder.endElements,y$$$	%%%%%r?nsTupleTuple[str, str]nodeNamec2|||dSr9)r)r<rrrs    r=startElementNSzSAXTreeBuilder.startElementNSs 	
(E*****r?c0||dSr9)r)r<rrs   r=endElementNSzSAXTreeBuilder.endElementNSs!!!!!r?prefix	nodeValuecdSr9r\)r<rrs   r=startPrefixMappingz!SAXTreeBuilder.startPrefixMappingsr?cdSr9r\)r<rs  r=endPrefixMappingzSAXTreeBuilder.endPrefixMappings		
r?contentcL|jJ|j|dSr9)rnhandle_data)r<rs  r=
characterszSAXTreeBuilder.characterss,y$$$	g&&&&&r?cdSr9r\r;s r=
startDocumentzSAXTreeBuilder.startDocumentrr?cdSr9r\r;s r=endDocumentzSAXTreeBuilder.endDocumentrr?)rrrrr6r7rrV)rrGrrr6r7rrGr6r7)rrrrGrrr6r7)rrrrGr6r7)rrGrrGr6r7)rrGr6r7)rrGr6r7)rWrXrYrZr>rrrrrrrrrrr
__classcell__)rs@r=r)r)s#>>>>>>$$$$



;;;;&&&&
++++""""








''''











r?r)ceZdZUdZegdZded<egdZded<ee	e
eedZ
ded	<hd
ddhddhd
hd
hdhdhdhdhdhdhdZded<eddgZded<d dZdS)!r(zpThis TreeBuilder knows facts about HTML, such as which tags are treated
    specially by the HTML standard.
    )areabasebrcolembedhrimginputkeygenlinkmenuitemmetaparamsourcetrackwbrbasefontbgsoundcommandframeimageisindexnextidspacerrcrr)#addressarticleaside
blockquotecanvasdddivdldtfieldset
figcaptionfigurefooterformh1h2h3h4h5h6headerrlimainnavnoscriptoloutputppresectiontabletfootulvideoDEFAULT_BLOCK_ELEMENTS)rtrpstylescripttemplaterzrt>classdropzone	accesskeyrelrevheaderszaccept-charsetarchivesizessandboxfor)rartdthrrriconiframerrarortextareazset[str]rqrr"r6rec|jdkrdSttt|d}ttt|d}|d}d}|t
||d<d}n/|-td|Drt||d<d}|S)	aReplace the declared encoding in a  tag with a placeholder,
        to be substituted when the tag is output to a string.

        An HTML document may come in to Beautiful Soup as one
        encoding, but exit in a different encoding, and the  tag
        needs to be changed to reflect this.

        :return: Whether or not a substitution was performed.

        :meta private:
        rFrcharsetz
http-equivNTc3FK|]}|dkVdS)zcontent-typeN)r)rxs  r=rz7HTMLTreeBuilder.set_up_substitutions..s@)
)
,-AGGII')
)
)
)
)
)
r?)	rrrrGrMget_attribute_listranyr)r<rrr0
http_equivsubstituteds      r=rz$HTMLTreeBuilder.set_up_substitutions|s8v5"&hsmSWWY5G5G!H!H!%hsmSWWY5G5G!H!H
!$ 6 6| D D
7w??C	NKK

 S)
)
1;)
)
)
&
&

 
7w??C	NKr?Nr)rWrXrYrZrNrrr[rrrrrrrtrorqrr\r?r=r(r(s^,/3	
	
	
,,F(+s$	
$	
$	
&(&(&&&&r#"OO 0
/
/U^kk!"+	+'
:
:!



"25eZ5H1I1I$IIII444444r?r(ceZdZUdZejdejZded<ejdejZ	ded<dZ
d	ed
<dZded
<ded<ded<e	d"d#dZ
ed$d%dZd&dZd'dZd(d Zd!S))r2aA mixin class for any class (a TreeBuilder, or some class used by a
    TreeBuilder) that's in a position to detect whether an XML
    document is being incorrectly parsed as HTML, and issue an
    appropriate warning.

    This requires being able to observe an incoming processing
    instruction that might be an XML declaration, and also able to
    observe tags as they're opened. If you can't do that for a given
    `TreeBuilder`, there's a less reliable implementation based on
    examining the raw markup.
    z
<[^ +]htmlzPattern[str]LOOKS_LIKE_HTMLs
<[^ +]htmlzPattern[bytes]LOOKS_LIKE_HTML_Bz5fe$$		9$H%00 ;+226:::
N#H%009)00888
	IIaI0004ur?r7cRtjtjt|dS)z/Issue a warning about XML being parsed as HTML.rN)rrrMESSAGE)rFrs  r=rEzDetectsXMLParsedAsHTML._warns3	
"*"!	
	
	
	
	
	
r?c"d|_d|_dS)z+Call this method before parsing a document.Nr=r>r;s r=_initialize_xml_detectorz/DetectsXMLParsedAsHTML._initialize_xml_detectors-1*"r?processing_instructionc4|j|jdS||_dS)a.Call this method when encountering an XML declaration, or a
        "processing instruction" that might be an XML declaration.

        This helps Beautiful Soup detect potential issues later, if
        the XML document turns out to be a non-XHTML document that's
        being parsed as XML.
        NrO)r<rQs  r=_document_might_be_xmlz-DetectsXMLParsedAsHTML._document_might_be_xmls+
.:".
F-C***r?rc|jdS||_|dkrK|jF|jdr|ddSdSdSdS)zCall this when you encounter the document's root tag.

        This is where we actually check whether an XML document is
        being incorrectly parsed as HTML, and issue the warning.
        Nr0zxml 
r)r>r=rrCrErs  r=_root_tag_encounteredz,DetectsXMLParsedAsHTML._root_tag_encountereds*
F"
FNN2>288::EEfMM?
JJ"J%%%%%
N>>>>r?N)r?)rr@rrAr6re)rK)rrAr6r7rV)rQrGr6r7r)rWrXrYrZrecompileIr8r[r9r:r<classmethodrJrErPrSrVr\r?r=r2r2s3

%/BJ|RT$B$BOBBBB)3
="$(G(GGGGGJ#L""""1000!!!!=>    [ D



[
####
DDDD*&&&&&&r?r2modulerr6r7ctjt}|jD]l}t	||}t|trEt||||j||j	
|mdS)z9Copy TreeBuilders from the given module into this module.N)sysmodulesrW__all__getattr
issubclassr*setattrappendr]rF)r[this_modulerobjs    r=register_treebuilders_fromrf/s+h'K77fd##c;''	7Ks+++&&t,,,(11#66677r?r)_htmlparser)	_html5lib)_lxml)r[rr6r7)F
__future__r__license__collectionsrrWtypesrtypingrrr	r
rrr
rrrrrr]bs4.elementrrrrrrrrrrbs4.exceptionsrbs4._typingrr
bs4._warningsrbs4r r!r"r#r$r%r&r'r_FAST
PERMISSIVESTRICTXMLHTMLHTML_5rr+r]r[r*r)r(r2rfrgrhImportErrorrir\r?r=r|s^"""""""######				



0/////
100000!!!!!!

	
	AAAAA&AAAL)<(;(=(=====UUUUU&UUUp>
>
>
>
>
[>
>
>
Bxxxxxkxxxvy&y&y&y&y&Vy&y&y&x
7
7
7
7";'''	y))))			D		u%%%%%			DD	s$DDD#D66D?>D?