U Å:âe9Eã@sÀdZddlZddlZddlZddlmZdgZe 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¡ZGdd„dejƒZdS)zA parser for HTML and XHTML.éN)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#c@sèeZdZdZdZddœdd„Zdd„Zd d „Zd d „Zd Z dd„Z dd„Z dd„Z dd„Z dd„Zd9dd„Zdd„Zdd„Zdd „Zd!d"„Zd#d$„Zd%d&„Zd'd(„Zd)d*„Zd+d,„Zd-d.„Zd/d0„Zd1d2„Zd3d4„Zd5d6„Zd7d8„Zd S):raEFind tags and other markup and call handler functions. Usage: p = HTMLParser() p.feed(data) ... p.close() Start tags are handled by calling self.handle_starttag() or self.handle_startendtag(); end tags by self.handle_endtag(). The data between tags is passed from the parser to the derived class by calling self.handle_data() with the data as argument (the data may be split up in arbitrary chunks). If convert_charrefs is True the character references are converted automatically to the corresponding Unicode character (and self.handle_data() is no longer split in chunks), otherwise they are passed by calling self.handle_entityref() or self.handle_charref() with the string containing respectively the named or numeric reference as the argument. )ZscriptÚstyleT)Úconvert_charrefscCs||_| ¡dS)zÆInitialize and reset this instance. If convert_charrefs is True (the default), all character references are automatically converted to the corresponding Unicode characters. N)rÚreset)Úselfr©r ú0/usr/local/python38/lib/python3.8/html/parser.pyÚ__init__WszHTMLParser.__init__cCs(d|_d|_t|_d|_tj |¡dS)z1Reset this instance. Loses all unprocessed data.Úz???N)ÚrawdataÚlasttagÚinteresting_normalÚ interestingÚ cdata_elemÚ _markupbaseÚ ParserBaser©rr r r r`s zHTMLParser.resetcCs|j||_| d¡dS)z‘Feed data to the parser. Call this as often as you want, with as little or as much text as you want (may include '\n'). rN)r Úgoahead©rÚdatar r r Úfeedhs zHTMLParser.feedcCs| d¡dS)zHandle any buffered data.éN)rrr r r ÚcloseqszHTMLParser.closeNcCs|jS)z)Return full source of start tag: '<...>'.)Ú_HTMLParser__starttag_textrr r r Úget_starttag_textwszHTMLParser.get_starttag_textcCs$| ¡|_t d|jtj¡|_dS)Nz )ÚlowerrÚreÚcompileÚIr)rÚelemr r r Úset_cdata_mode{s zHTMLParser.set_cdata_modecCst|_d|_dS©N)rrrrr r r Úclear_cdata_modeszHTMLParser.clear_cdata_modec CsJ|j}d}t|ƒ}||krÚ|jrv|jsv| d|¡}|dkr | dt||dƒ¡}|dkrpt d¡  ||¡spqÚ|}n*|j   ||¡}|r’|  ¡}n|jrœqÚ|}||krÞ|jrÌ|jsÌ|  t |||…ƒ¡n|  |||…¡| ||¡}||kröqÚ|j}|d|ƒrJt ||¡r"| |¡} n†|d|ƒr:| |¡} nn|d|ƒrR| |¡} nV|d|ƒrj| |¡} n>|d |ƒr‚| |¡} n&|d |krÚ|  d¡|d } nqÚ| dkr<|s¼qÚ| d |d ¡} | dkrú| d|d ¡} | dkr|d } n| d 7} |jr*|js*|  t ||| …ƒ¡n|  ||| …¡| || ¡}q|d |ƒrðt ||¡}|r²| ¡d d…} | | ¡| ¡} |d| d ƒs¢| d } | || ¡}qnr ÚiÚnÚjZampposr5r3ÚkÚnamer r r r†sÄ   ÿ                                zHTMLParser.goaheadcCs¢|j}|||d…dkr$| |¡S|||d…dkrB| |¡S|||d… ¡dkr”| d|d¡}|dkrvdS| ||d |…¡|d S| |¡SdS) Nér(éz)rrBr r5rDr r r r9!szHTMLParser.parse_picCsÞd|_| |¡}|dkr|S|j}|||…|_g}t ||d¡}| ¡}| d¡ ¡|_}||kr t  ||¡}|s~q | ddd¡\} } } | sœd} nZ| dd…dkrÀ| dd…ksên| dd…dkræ| dd…krönn | dd…} | rt | ƒ} |  |  ¡| f¡| ¡}q`|||…  ¡} | dkrž|  ¡\} }d |jkrz| |j d ¡} t|jƒ|j d ¡}n|t|jƒ}| |||…¡|S|  d ¡r¸| ||¡n"| ||¡||jkrÚ| |¡|S) Nrrr)rHú'r*ú")rú/>Ú rS)rÚcheck_for_whole_start_tagr Útagfind_tolerantr5r>r<rrÚattrfind_tolerantrÚappendÚstripZgetposÚcountr,r.r2ÚendswithÚhandle_startendtagÚhandle_starttagÚCDATA_CONTENT_ELEMENTSr")rrBÚendposr Úattrsr5rEÚtagÚmÚattrnameÚrestZ attrvaluer>ÚlinenoÚoffsetr r r r6-sZ   & ÿ ÿ       ÿ    zHTMLParser.parse_starttagcCs¶|j}t ||¡}|rª| ¡}|||d…}|dkr>|dS|dkr~| d|¡rZ|dS| d|¡rjdS||krv|S|dS|dkrŠdS|dkr–dS||kr¢|S|dStd ƒ‚dS) Nrrú/rSr)r*r z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!)r Úlocatestarttagend_tolerantr5r>r3ÚAssertionError)rrBr rbrDÚnextr r r rU`s.   z$HTMLParser.check_for_whole_start_tagcCs|j}t ||d¡}|sdS| ¡}t ||¡}|sÀ|jdk rV| |||…¡|St ||d¡}|s|||d…dkr†|dS|  |¡S|  d¡  ¡}|  d| ¡¡}|  |¡|dS|  d¡  ¡}|jdk rø||jkrø| |||…¡|S|  |¡| ¡|S)Nrr*r)rHzr)r Ú endendtagr0r>Ú endtagfindr5rr2rVrKr<rr-Ú handle_endtagr$)rrBr r5rLZ namematchZtagnamer!r r r r7‚s6       zHTMLParser.parse_endtagcCs| ||¡| |¡dSr#)r]rm©rrar`r r r r\ªs zHTMLParser.handle_startendtagcCsdSr#r rnr r r r]¯szHTMLParser.handle_starttagcCsdSr#r )rrar r r rm³szHTMLParser.handle_endtagcCsdSr#r ©rrFr r r r=·szHTMLParser.handle_charrefcCsdSr#r ror r r r@»szHTMLParser.handle_entityrefcCsdSr#r rr r r r2¿szHTMLParser.handle_datacCsdSr#r rr r r rMÃszHTMLParser.handle_commentcCsdSr#r )rZdeclr r r rJÇszHTMLParser.handle_declcCsdSr#r rr r r rPËszHTMLParser.handle_picCsdSr#r rr r r Ú unknown_declÎszHTMLParser.unknown_declcCstjdtddt|ƒS)NzZThe unescape method is deprecated and will be removed in 3.5, use html.unescape() instead.r))Ú stacklevel)ÚwarningsÚwarnÚDeprecationWarningr)rÚsr r r rÒs þzHTMLParser.unescape)r)Ú__name__Ú __module__Ú __qualname__Ú__doc__r^r rrrrrr"r$rr:rKr9r6rUr7r\r]rmr=r@r2rMrJrPrprr r r r r?s8  z  3"()ryrrrrZhtmlrÚ__all__rrrAr?r;r4rOZ commentcloserVrWÚVERBOSErhrkrlrrr r r r Ús,          ÿò