+ h!csRt^RIt^RIt^RIHt^RIHt^RIH t ^RI H t H t H t ]t^RIHt^RIHt!RR ]4t^R IHt!R R ]4t]!4tR tRRltRRltRRltRRlt RRlt!Rt"]!4t#R# ]d]]3tLgi;i ]d ^RIHtLsi;i ]d ^RIHtLi;i ]dLhi;i)z? An interface to html5lib that mimics the lxml.html interface. N) HTMLParser) TreeBuilder)etree)ElementXHTML_NAMESPACE_contains_block_level_tag)urlopen)urlparsecs.a]tRt^toRtRRltRtVtR#)rz*An html5lib HTML parser with lxml as tree.c D\P!V3RVR\/VBR#stricttreeN) _HTMLParser__init__rZselfr Zkwargs&&,D  99#6 77rcs\V\4'g \R4hVf\p/pVf\V\4'dRpVeWR&VP !V3/VBP 4#)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_parserbytesparseZgetroot)html guess_charsetparseroptionss&&& rdocument_fromstringr(7sp dH % %)** ~GD%!8!8  -  << ( ( 0 0 22rcs\V\4'g \R4hVf\p/pVf\V\4'dRpVeW$R&VP !VR3/VBpV'dj\V^,\4'dMV'dEV^,P 4'd%\P!RV^,,4hV^V#)aHParses several HTML elements, returning a list of elements. The first item in the list may be a string. If no_leading_text is true, then it will be an error if there is leading text, and it will always be a list of only elements. If `guess_charset` is true, the `chardet` library will perform charset guessing on the string. rFrdivzThere is leading text: %r) rrr r!r"Z parseFragmentstripr ParserError)r$no_leading_textr%r&r'Zchildrens&&&& rfragments_fromstringr-Os dH % %)** ~GD%!8!8  - ##D%;7;HJx{H55 {  ""''(C(0 )455 Orcs\V\4'g \R4h\V4p\ WVV'*R7pV'dm\V\4'gRp\ V4pV'd@\V^,\4'dV^,VnV^VPV4V#V'g\P!R4h\V4^8d\P!R4hV^,pVP'dHVPP4'd(\P!RVP,4hRVn V#)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. r)r%r&r,r)zNo elements foundzMultiple elements foundzElement followed by text: %rN) rrr Zboolr-rtextZextendrr+lentailr*)r$Z create_parentr%r&Zaccept_leading_textZelementsZnew_rootZresults&&&& rfragment_fromstringr1qs dH % %)**}-# &//1H-22!M=) (1+x00 (  QK OOH %  344 8}q 9:: a[F {{{v{{((** > LMMFK Mrcs\V\4'g \R4h\WVR7pVR,p\V\4'dVP RR4pVP 4P4pVPR4'gVPR4'dV#\VR4p\V4'dV#\VR 4p\V4^8Xd|VP'd!VPP4'gJVR ,P'd(VR ,PP4'g V^,#\V4'd R VnV#R VnV#) aParse the html, returning a single element/document. This tries to minimally parse the chunk of text, without knowing if it is a fragment or a document. 'base_url' will set the document's base_url attribute (and the tree's docinfo.URL) If `guess_charset` is true, or if the input is not Unicode but a byte string, the `chardet` library will perform charset guessing on the string. r)r&r%:Ni2NZasciiZreplacezr9s .8IIH'&! NN !4SlS =L830D)X3l!'H l ks|H'&'&%&  sEBBB(B; BB B%$B%( B87B8;CC