B ܠg!@sdZddlZddlZddlZddlmZdgZedZedZ edZ edZ ed Z ed Z ed Zed Zed ZedejZed ZedZGdddejZdS)zA parser for HTML and XHTML.N)unescape 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]>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 comma )?(?:\s|/(?!>))* )* )? \s* # trailing whitespace z#c@seZdZdZdZddddZddZd d Zd d Zd Z ddZ ddZ ddZ ddZ ddZd9ddZddZddZdd Zd!d"Zd#d$Zd%d&Zd'd(Zd)d*Zd+d,Zd-d.Zd/d0Zd1d2Zd3d4Zd5d6Zd7d8Zd S):raEFind tags and other markup and call handler functions. Usage: p = HTMLParser() p.feed(data) ... p.close() Start tags are handled by calling self.handle_starttag() or self.handle_startendtag(); end tags by self.handle_endtag(). The data between tags is passed from the parser to the derived class by calling self.handle_data() with the data as argument (the data may be split up in arbitrary chunks). If convert_charrefs is True the character references are converted automatically to the corresponding Unicode character (and self.handle_data() is no longer split in chunks), otherwise they are passed by calling self.handle_entityref() or self.handle_charref() with the string containing respectively the named or numeric reference as the argument. )ZscriptZstyleT)convert_charrefscCs||_|dS)zInitialize and reset this instance. If convert_charrefs is True (the default), all character references are automatically converted to the corresponding Unicode characters. N)rreset)selfrr0/opt/alt/python37/lib64/python3.7/html/parser.py__init__WszHTMLParser.__init__cCs(d|_d|_t|_d|_tj|dS)z1Reset this instance. Loses all unprocessed data.z???N)rawdatalasttaginteresting_normal interesting cdata_elem _markupbase ParserBaser)rrrr r`s zHTMLParser.resetcCs|j||_|ddS)zFeed data to the parser. Call this as often as you want, with as little or as much text as you want (may include '\n'). rN)r goahead)rdatarrr feedhs zHTMLParser.feedcCs|ddS)zHandle any buffered data.N)r)rrrr closeqszHTMLParser.closeNcCs|jS)z)Return full source of start tag: '<...>'.)_HTMLParser__starttag_text)rrrr get_starttag_textwszHTMLParser.get_starttag_textcCs$||_td|jtj|_dS)Nz )lowerrrecompileIr)relemrrr set_cdata_mode{s zHTMLParser.set_cdata_modecCst|_d|_dS)N)rrr)rrrr clear_cdata_modeszHTMLParser.clear_cdata_modec CsN|j}d}t|}x||kr|jrx|jsx|d|}|dkr|dt||d}|dkrrtd ||srP|}n(|j ||}|r| }n |jrP|}||kr|jr|js| t |||n| ||||||}||krP|j}|d|rDt||r ||} n|d|r8||} nl|d|rP||} nT|d|rh||} n<|d |r||} n$|d |kr| d|d } nP| dkr6|sP|d |d } | dkr|d|d } | dkr|d } n| d 7} |jr$|js$| t ||| n| ||| ||| }q|d |rt||}|r|d d} || |} |d| d s| d } ||| }qn:d||dkr| |||d |||d }Pq|d|rt||}|rH|d } || |} |d| d s:| d } ||| }qt||}|r|r|||dkr|} | |kr|} |||d }Pn,|d |kr| d|||d }nPqdstdqW|r<||kr<|js<|jr|js| t |||n| ||||||}||d|_dS)Nr<&"z[\s;]zr gtposrrr r5s  z!HTMLParser.parse_html_declarationrcCs`|j}|||ddks"td|d|d}|dkr>dS|rX|||d||dS)Nr$)zZreportr posrrr rGszHTMLParser.parse_bogus_commentcCsd|j}|||ddks"tdt||d}|s:dS|}|||d||}|S)Nr$zr r0r@rrr r4!szHTMLParser.parse_picCsd|_||}|dkr|S|j}||||_g}t||d}|sPtd|}|d|_ }x||kr.t ||}|sP|ddd\} } } | sd} n\| dddkr| ddksn| dddkr| ddkrnn | dd} | rt | } | | | f|}qnW||| } | d kr|\} }d |jkr| |jd } t|j|jd }n|t|j}|||||S| d r|||n"|||||jkr|||S) Nrrz#unexpected call to parse_starttag()r$rD'r%")rz/> z/>)rcheck_for_whole_start_tagr tagfind_tolerantr0r=r9r7rr attrfind_tolerantrappendstripZgetposcountr'r)r-endswithhandle_startendtaghandle_starttagCDATA_CONTENT_ELEMENTSr)rr>endposr attrsr0rAtagmZattrnamerestZ attrvaluer9linenooffsetrrr r1-sR    &*         zHTMLParser.parse_starttagcCs|j}t||}|r|}|||d}|dkr>|dS|dkr~|d|rZ|dS|d|rjdS||krv|S|dS|dkrdS|dkrdS||kr|S|dStd dS) Nrr/z/>r$r%r z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!)r locatestarttagend_tolerantr0r9r.r=)rr>r r]r@nextrrr rP`s.   z$HTMLParser.check_for_whole_start_tagcCs.|j}|||ddks"tdt||d}|s:dS|}t||}|s|jdk rr|||||St ||d}|s|||ddkr|dS| |S| d }| d|}|||dS| d }|jdk r||jkr|||||S||||S) Nr$zr)r r= endendtagr+r9 endtagfindr0rr-rQrGr7rr( handle_endtagr )rr>r r0rHZ namematchZtagnamerrrr r2s8       zHTMLParser.parse_endtagcCs|||||dS)N)rXrf)rr\r[rrr rWs zHTMLParser.handle_startendtagcCsdS)Nr)rr\r[rrr rXszHTMLParser.handle_starttagcCsdS)Nr)rr\rrr rfszHTMLParser.handle_endtagcCsdS)Nr)rrBrrr r8szHTMLParser.handle_charrefcCsdS)Nr)rrBrrr r;szHTMLParser.handle_entityrefcCsdS)Nr)rrrrr r-szHTMLParser.handle_datacCsdS)Nr)rrrrr rIszHTMLParser.handle_commentcCsdS)Nr)rZdeclrrr rFszHTMLParser.handle_declcCsdS)Nr)rrrrr rLszHTMLParser.handle_picCsdS)Nr)rrrrr unknown_declszHTMLParser.unknown_declcCstjdtddt|S)NzZThe unescape method is deprecated and will be removed in 3.5, use html.unescape() instead.r$) stacklevel)warningswarnDeprecationWarningr)rsrrr rs zHTMLParser.unescape)r)__name__ __module__ __qualname____doc__rYr rrrrrrr rr5rGr4r1rPr2rWrXrfr8r;r-rIrFrLrgrrrrr r?s8  z  3"()rprrirZhtmlr__all__rrr<r:r6r/rKZ commentcloserQrRVERBOSErbrdrerrrrrr s(