h!SrSSKrSSKrSSKJr SSKJr SSKJ r SSK J r J r J r \rSSKJr SSKJr "S S \5rSS KJr "S S \5r\"5rSrSSjrSSjrSSjrSSjr SSjr!Sr"\"5r#g!\a \\4rNif=f!\a SSKJr Ntf=f!\a SSKJr Nf=f!\a Ngf=f)z? An interface to html5lib that mimics the lxml.html interface. N) HTMLParser) TreeBuilder)etree)ElementXHTML_NAMESPACE_contains_block_level_tag)urlopen)urlparsec"\rSrSrSrSSjrSrg)rz*An html5lib HTML parser with lxml as tree.c @[R"U4U[S.UD6 gN)stricttree) _HTMLParser__init__rselfrkwargss G/var/www/html/env/lib/python3.13/site-packages/lxml/html/html5parser.pyrHTMLParser.__init__sTM&{MfMNF__name__ __module__ __qualname____firstlineno____doc__r__static_attributes__rrrrrs 4Nrr) XHTMLParserc"\rSrSrSrSSjrSrg)r"'z+An html5lib XHTML Parser with lxml as tree.c @[R"U4U[S.UD6 gr) _XHTMLParserrrrs rrXHTMLParser.__init__*s  ! !$ RvK R6 RrrNrrrrrr"r"'s 9 Srr"chURU5nUbU$URS[<SU<35$)N{})findr)rtagelems r _find_tagr.0s. 99S>D  99#6 77rc[U[5(d [S5eUc[n0nUc[U[5(aSnUbXS'UR "U40UD6R 5$)z Parse a whole document into a string. If `guess_charset` is true, or if the input is not Unicode but a byte string, the `chardet` library will perform charset guessing on the string. string requiredT useChardet) isinstance_strings TypeError html_parserbytesparsegetroot)html guess_charsetparseroptionss rdocument_fromstringr=7sp dH % %)** ~GD%!8!8  -  << ( ( 0 0 22rc[U[5(d [S5eUc[n0nUc[U[5(aSnUbX$S'UR "US40UD6nU(aV[US[5(a>U(a7USR 5(a[R"SUS-5eUS U$)aHParses several HTML elements, returning a list of elements. The first item in the list may be a string. If no_leading_text is true, then it will be an error if there is leading text, and it will always be a list of only elements. If `guess_charset` is true, the `chardet` library will perform charset guessing on the string. r0Fr1divrzThere is leading text: %r) r2r3r4r5r6 parseFragmentstripr ParserError)r9no_leading_textr:r;r<childrens rfragments_fromstringrEOs dH % %)** ~GD%!8!8  - ##D%;7;HJx{H55 {  ""''(C(0 )455 Orc[U[5(d [S5e[U5n[ XUU(+S9nU(aa[U[5(dSn[ U5nU(a6[US[5(a USUlUS URU5 U$U(d[R"S5e[U5S:a[R"S5eUSnUR(aBURR5(a#[R"SUR-5eS Ul U$) aParses a single HTML element; it is an error if there is more than one element, or if anything but whitespace precedes or follows the element. If 'create_parent' is true (or is a tag name) then a parent node will be created to encapsulate the HTML in a single element. In this case, leading or trailing text is allowed. If `guess_charset` is true, the `chardet` library will perform charset guessing on the string. r0)r:r;rCr?rzNo elements foundzMultiple elements foundzElement followed by text: %rN) r2r3r4boolrErtextextendrrBlentailrA)r9 create_parentr:r;accept_leading_textelementsnew_rootresults rfragment_fromstringrRqs dH % %)**}-# &//1H-22!M=) (1+x00 (  QK OOH %  344 8}q 9:: a[F {{v{{((** > LMMFK Mrc[U[5(d [S5e[XUS9nUSSn[U[5(aUR SS5nUR 5R5nURS5(dURS5(aU$[US 5n[U5(aU$[US 5n[U5S :XakUR(aURR5(d;US R(a"US RR5(dUS $[U5(a SUlU$SUlU$)aParse the html, returning a single element/document. This tries to minimally parse the chunk of text, without knowing if it is a fragment or a document. 'base_url' will set the document's base_url attribute (and the tree's docinfo.URL) If `guess_charset` is true, or if the input is not Unicode but a byte string, the `chardet` library will perform charset guessing on the string. r0)r;r:N2asciireplacezr{s .8IIH'&! NN !4SlS =L8300548D-237)X3l!'H l ks|H'&'&%&  sEBBB)B; BB B&%B&) B87B8;CC