관리-도구
편집 파일: parser.cpython-35.opt-1.pyc
��Yf?E � @ s d Z d d l Z d d l Z d d l Z d d l m Z d g Z e j d � Z e j d � Z e j d � Z e j d � Z e j d � Z e j d � Z e j d � Z e j d � Z e j d � Z e j d e j � Z e j d � Z e j d � Z Gd d � d e j � Z d S)z A 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$([a-zA-Z][^ /> ]*)(?:\s|/(?!>))*z]((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*aF <[a-zA-Z][^\t\n\r\f />\x00]* # tag name (?:[\s/]* # optional whitespace before attribute name (?:(?<=['"\s/])[^\s/>][^\s/=>]* # attribute name (?:\s*=+\s* # value indicator (?:'[^']*' # LITA-enclosed value |"[^"]*" # LIT-enclosed value |(?!['"])[^>\s]* # bare value ) (?:\s*,)* # possibly followed by a comma )?(?:\s|/(?!>))* )* )? \s* # trailing whitespace z#</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>c @ sW e Z d Z d Z d: Z d d d d � Z d d � Z d d � Z d d � Z d Z d d � Z d d � Z d d � Z d d � Z d d � Z d d d � Z d d � Z d d � Z d d! � Z d" d# � Z d$ d% � Z d& d' � Z d( d) � Z d* d+ � Z d, d- � Z d. d/ � Z d0 d1 � Z d2 d3 � Z d4 d5 � Z d6 d7 � Z d8 d9 � Z d S);r aE Find 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. �script�style�convert_charrefsTc C s | | _ | j � d S)z�Initialize and reset this instance. If convert_charrefs is True (the default), all character references are automatically converted to the corresponding Unicode characters. N)r �reset)�selfr � r �0/opt/alt/python35/lib64/python3.5/html/parser.py�__init__W s zHTMLParser.__init__c C s8 d | _ d | _ t | _ d | _ t j j | � d S)z1Reset this instance. Loses all unprocessed data.� z???N)�rawdata�lasttag�interesting_normal� interesting� cdata_elem� _markupbase� ParserBaser )r r r r r ` s zHTMLParser.resetc C s! | j | | _ | j d � d S)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'). r N)r �goahead)r �datar r r �feedh s zHTMLParser.feedc C s | j d � d S)zHandle any buffered data.� N)r )r r r r �closeq s zHTMLParser.closeNc C s | j S)z)Return full source of start tag: '<...>'.)�_HTMLParser__starttag_text)r r r r �get_starttag_textw s z HTMLParser.get_starttag_textc C s2 | j � | _ t j d | j t j � | _ d S)Nz </\s*%s\s*>)�lowerr �re�compile�Ir )r �elemr r r �set_cdata_mode{ s zHTMLParser.set_cdata_modec C s t | _ d | _ d S)N)r r r )r r r r �clear_cdata_mode s zHTMLParser.clear_cdata_modec C s� | j } d } t | � } x�| | k r| j r� | j r� | j d | � } | d k r� | j d t | | d � � } | d k r� t j d � j | | � r� P| } n: | j j | | � } | r� | j � } n | j r� P| } | | k r<| j r%| j r%| j t | | | � � � n | j | | | � � | j | | � } | | k r[P| j } | d | � rt j | | � r�| j | � } n� | d | � r�| j | � } n� | d | � r�| j | � } nm | d | � r�| j | � } nL | d | � r| j | � } n+ | d | k rE| j d � | d } n P| d k r�| sYP| j d | d � } | d k r�| j d | d � } | d k r�| d } n | d 7} | j r�| j r�| j t | | | � � � n | j | | | � � | j | | � } q | d | � r�t j | | � } | r�| j � d d � } | j | � | j � } | d | d � s�| d } | j | | � } q qd | | d � k r�| j | | | d � � | j | | d � } Pq | d | � r t j | | � } | rj| j d � } | j | � | j � } | d | d � sU| d } | j | | � } q t j | | � } | r�| r�| j � | | d � k r�| j � } | | k r�| } | j | | d � } Pq| d | k r| j d � | j | | d � } qPq q W| r�| | k r�| j r�| j ri| j ri| j t | | | � � � n | j | | | � � | j | | � } | | d � | _ d S)Nr �<�&�" z[\s;]z</z<!--z<?z<!r r z&#� �;���) r �lenr r �find�rfind�maxr r �searchr �start� handle_datar Z updatepos� startswith� starttagopen�match�parse_starttag� parse_endtag� parse_comment�parse_pi�parse_html_declaration�charref�group�handle_charref�end� entityref�handle_entityref� incomplete) r r; r �i�n�jZampposr2 r0 �k�namer r r r � s� " zHTMLParser.goaheadc C s� | j } | | | d � d k r0 | j | � S| | | d � d k rW | j | � S| | | d � j � d k r� | j d | d � } | d k r� d S| j | | d | � � | d S| j | � Sd S) N� z<!--� z<![� z <!doctyper r r& r( r( )r r5 Zparse_marked_sectionr r* � handle_decl�parse_bogus_comment)r r? r �gtposr r r r7 s z!HTMLParser.parse_html_declarationr c C sX | j } | j d | d � } | d k r/ d S| rP | j | | d | � � | d S)Nr r& r r( r( )r r* �handle_comment)r r? Zreportr �posr r r rH s z HTMLParser.parse_bogus_commentc C s` | j } t j | | d � } | s) d S| j � } | j | | d | � � | j � } | S)Nr& r r( )r �picloser- r. � handle_pir; )r r? r r2 rA r r r r6 ! s zHTMLParser.parse_pic C s� d | _ | j | � } | d k r( | S| j } | | | � | _ g } t j | | d � } | j � } | j d � j � | _ } x� | | k r�t j | | � } | s� P| j d d d � \ } } } | s� d } np | d d � d k o| d d � k n s=| d d � d k o8| d d � k n rM| d d � } | r_t | � } | j | j � | f � | j � } q� W| | | � j � } | d k r1| j � \ } } d | j k r| | j j d � } t | j � | j j d � } n | t | j � } | j | | | � � | S| j d � rS| j | | � n, | j | | � | | j k r| j | � | S)Nr r r& rE �'�"r �/>� r( r( r( )r rP )r �check_for_whole_start_tagr �tagfind_tolerantr2 r; r9 r r �attrfind_tolerantr �append�stripZgetpos�countr) r+ r/ �endswith�handle_startendtag�handle_starttag�CDATA_CONTENT_ELEMENTSr! )r r? �endposr �attrsr2 rB �tag�mZattrname�restZ attrvaluer; �lineno�offsetr r r r3 - sP 00 zHTMLParser.parse_starttagc C s� | j } t j | | � } | r� | j � } | | | d � } | d k rU | d S| d k r� | j d | � r{ | d S| j d | � r� d S| | k r� | S| d S| d k r� d S| d k r� d S| | k r� | S| d St d � � d S) Nr r �/z/>r& r z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!r( r( r( )r �locatestarttagend_tolerantr2 r; r0 �AssertionError)r r? r r_ rA �nextr r r rR ` s. z$HTMLParser.check_for_whole_start_tagc C ss | j } t j | | d � } | s) d S| j � } t j | | � } | s| j d k rw | j | | | � � | St j | | d � } | s� | | | d � d k r� | d S| j | � S| j d � j � } | j d | j � � } | j | � | d S| j d � j � } | j d k rR| | j k rR| j | | | � � | S| j | j � � | j � | S)Nr r& rE z</>r r( )r � endendtagr- r; � endtagfindr2 r r/ rS rH r9 r r* � handle_endtagr" )r r? r r2 rI Z namematchZtagnamer r r r r4 � s6 zHTMLParser.parse_endtagc C s! | j | | � | j | � d S)N)rZ ri )r r^ r] r r r rY � s z HTMLParser.handle_startendtagc C s d S)Nr )r r^ r] r r r rZ � s zHTMLParser.handle_starttagc C s d S)Nr )r r^ r r r ri � s zHTMLParser.handle_endtagc C s d S)Nr )r rC r r r r: � s zHTMLParser.handle_charrefc C s d S)Nr )r rC r r r r= � s zHTMLParser.handle_entityrefc C s d S)Nr )r r r r r r/ � s zHTMLParser.handle_datac C s d S)Nr )r r r r r rJ � s zHTMLParser.handle_commentc C s d S)Nr )r Zdeclr r r rG � s zHTMLParser.handle_declc C s d S)Nr )r r r r r rM � s zHTMLParser.handle_pic C s d S)Nr )r r r r r � unknown_decl� s zHTMLParser.unknown_declc C s t j d t d d �t | � S)NzZThe unescape method is deprecated and will be removed in 3.5, use html.unescape() instead.� stacklevelr& )�warnings�warn�DeprecationWarningr )r �sr r r r � s zHTMLParser.unescape)r r ) �__name__� __module__� __qualname__�__doc__r[ r r r r r r r! r" r r7 rH r6 r3 rR r4 rY rZ ri r: r= r/ rJ rG rM rj r r r r r r ? s8 z 3 " ( )rs r rl r Zhtmlr �__all__r r r> r< r8 r1 rL Z commentcloserS rT �VERBOSErd rg rh r r r r r r �<module> s(