View file File name : HTMLParser.pyc Content :� �bc @ s d Z d d l Z d d l 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 � Z e j d e j � Z e j d � Z e j d � Z d e f d � � YZ d e j f d � � YZ d S( s A parser for HTML and XHTML.i����Ns [&<]s &[a-zA-Z#]s% &([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]s) &#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]s <[a-zA-Z]t >s --\s*>s$ ([a-zA-Z][^ /> ]*)(?:\s|/(?!>))*s [a-zA-Z][^ /> ]*s] ((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*s <[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|/(?!>))* )* )? \s* # trailing whitespace s# </\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>t HTMLParseErrorc B s# e Z d Z d d � Z d � Z RS( s& Exception raised for all parse errors.c C s3 | s t � | | _ | d | _ | d | _ d S( Ni i ( t AssertionErrort msgt linenot offset( t selfR t position( ( s /usr/lib/python2.7/HTMLParser.pyt __init__< s c C sW | j } | j d k r, | d | j } n | j d k rS | d | j d } n | S( Ns , at line %ds , column %di ( R R t NoneR ( R t result( ( s /usr/lib/python2.7/HTMLParser.pyt __str__B s N( NN( t __name__t __module__t __doc__R R R ( ( ( s /usr/lib/python2.7/HTMLParser.pyR 9 s t HTMLParserc B s e Z d Z d Z d � Z d � Z d � Z d � Z d � Z d Z d � Z d � Z d � Z d � Z d � Z d d � Z d � Z d � Z d � Z d � Z d � Z d � Z d � Z d � Z d � Z d � Z d � Z d � Z d � Z d � Z d Z d � Z RS( s� 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). Entity references are passed by calling self.handle_entityref() with the entity reference as the argument. Numeric character references are passed to self.handle_charref() with the string containing the reference as the argument. t scriptt stylec C s | j � d S( s# Initialize and reset this instance.N( t reset( R ( ( s /usr/lib/python2.7/HTMLParser.pyR b s c C s8 d | _ d | _ t | _ d | _ t j j | � d S( s1 Reset this instance. Loses all unprocessed data.t s ???N( t rawdatat lasttagt interesting_normalt interestingR t cdata_elemt markupbaset ParserBaseR ( R ( ( s /usr/lib/python2.7/HTMLParser.pyR f s c C s! | j | | _ | j d � d S( s� 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'). i N( R t goahead( R t data( ( s /usr/lib/python2.7/HTMLParser.pyt feedn s c C s | j d � d S( s Handle any buffered data.i N( R ( R ( ( s /usr/lib/python2.7/HTMLParser.pyt closew s c C s t | | j � � � d S( N( R t getpos( R t message( ( s /usr/lib/python2.7/HTMLParser.pyt error{ s c C s | j S( s) Return full source of start tag: '<...>'.( t _HTMLParser__starttag_text( R ( ( s /usr/lib/python2.7/HTMLParser.pyt get_starttag_text� s c C s2 | j � | _ t j d | j t j � | _ d S( Ns </\s*%s\s*>( t lowerR t ret compilet IR ( R t elem( ( s /usr/lib/python2.7/HTMLParser.pyt set_cdata_mode� s c C s t | _ d | _ d S( N( R R R R ( R ( ( s /usr/lib/python2.7/HTMLParser.pyt clear_cdata_mode� s c C s| | j } d } t | � } x| | k r%| j j | | � } | rT | j � } n | j ra Pn | } | | k r� | j | | | !� n | j | | � } | | k r� Pn | j } | d | � r7t j | | � r� | j | � } n� | d | � r | j | � } n� | d | � r*| j | � } nm | d | � rK| j | � } nL | d | � rl| j | � } n+ | d | k r�| j d � | d } n P| d k r"| s�Pn | j d | d � } | d k r| j d | d � } | d k r | d } q n | d 7} | j | | | !� n | j | | � } q | d | � rt j | | � } | r�| j � d d !} | j | � | j � } | d | d � s�| d } n | j | | � } q q"d | | k r| j | | | d !� | j | | d � } n Pq | d | � rt j | | � } | r�| j d � } | j | � | j � } | d | d � sv| d } n | j | | � } q n t j | | � } | r�| r�| j � | | k r�| j d � n Pq"| d | k r | j d � | j | | d � } q"Pq d s t d � � q W| rk| | k rk| j rk| j | | | !� | j | | � } n | | | _ d S( Ni t <s </s <!--s <?s <!i R s &#i i����t ;t &s# EOF in middle of entity or char refs interesting.search() lied( R t lenR t searcht startR t handle_datat updatepost startswitht starttagopent matcht parse_starttagt parse_endtagt parse_commentt parse_pit parse_html_declarationt findt charreft groupt handle_charreft endt entityreft handle_entityreft incompleteR! R ( R R? R t it nR5 t jR3 t kt name( ( s /usr/lib/python2.7/HTMLParser.pyR � s� c C s� | j } | | | d !d k r0 | j d � n | | | d !d k rT | j | � S| | | d !d k rx | j | � S| | | d !j � d k r� | j d | d � } | d k r� d S| j | | d | !� | d S| j | � Sd S( Ni s <!s+ unexpected call to parse_html_declaration()i s <!--i s <![i s <!doctypeR i����i ( R R! R8 t parse_marked_sectionR$ R; t handle_declt parse_bogus_comment( R RC R t gtpos( ( s /usr/lib/python2.7/HTMLParser.pyR: � s i c C s | j } | | | d !d k r0 | j d � n | j d | d � } | d k rV d S| rw | j | | d | !� n | d S( Ni s <!s </s" unexpected call to parse_comment()R i����i ( s <!s </( R R! R; t handle_comment( R RC t reportR t pos( ( s /usr/lib/python2.7/HTMLParser.pyRJ s c C s� | j } | | | d !d k s, t d � � t j | | d � } | sL d S| j � } | j | | d | !� | j � } | S( Ni s <?s unexpected call to parse_pi()i����( R R t picloseR/ R0 t handle_piR? ( R RC R R5 RE ( ( s /usr/lib/python2.7/HTMLParser.pyR9 s # c C s� d | _ | j | � } | d k r( | S| j } | | | !| _ g } t j | | d � } | so t d � � | j � } | j d � j � | _ } x� | | k r�t j | | � } | s� Pn | j d d d � \ } } } | s� d } nX | d d k o| d k n s7| d d k o2| d k n rG| d d !} n | r_| j | � } n | j | j � | f � | j � } q� W| | | !j � } | d k r+| j � \ } } d | j k r | | j j d � } t | j � | j j d � } n | t | j � } | j | | | !� | S| j d � rM| j | | � n/ | j | | � | | j k r|| j | � n | S( Ni i s# unexpected call to parse_starttag()i i s 'i����t "R s />s ( R s />( R R" t check_for_whole_start_tagR t tagfindR5 R R? R= R$ R t attrfindt unescapet appendt stripR t countR. t rfindR1 t endswitht handle_startendtagt handle_starttagt CDATA_CONTENT_ELEMENTSR) ( R RC t endposR t attrsR5 RF t tagt mt attrnamet restt attrvalueR? R R ( ( s /usr/lib/python2.7/HTMLParser.pyR6 sR $$ c C s� | j } t j | | � } | r� | j � } | | | d !} | d k rR | d S| d k r� | j d | � rx | d S| j d | � r� d S| j | | d � | j d � n | d k r� d S| d k r� d S| | k r� | S| d Sn t d � � d S( Ni R t /s />i i����s malformed empty start tagR s6 abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZs we should not get here!( R t locatestarttagendR5 R? R3 R2 R! R ( R RC R Ra RE t next( ( s /usr/lib/python2.7/HTMLParser.pyRR N s, c C s� | j } | | | d !d k s, t d � � t j | | d � } | sL d S| j � } t j | | � } | s$| j d k r� | j | | | !� | St j | | d � } | s� | | | d !d k r� | d S| j | � Sn | j d � j � } | j d | j � � } | j | � | d S| j d � j � } | j d k rr| | j k rr| j | | | !� | Sn | j | � | j � | S( Ni s </s unexpected call to parse_endtagi i����i s </>R ( R R t endendtagR/ R? t endtagfindR5 R R R1 RS RJ R= R$ R; t handle_endtagR* ( R RC R R5 RK t namematcht tagnameR( ( ( s /usr/lib/python2.7/HTMLParser.pyR7 n s8 # c C s! | j | | � | j | � d S( N( R\ Rj ( R R` R_ ( ( s /usr/lib/python2.7/HTMLParser.pyR[ � s c C s d S( N( ( R R` R_ ( ( s /usr/lib/python2.7/HTMLParser.pyR\ � s c C s d S( N( ( R R` ( ( s /usr/lib/python2.7/HTMLParser.pyRj � s c C s d S( N( ( R RG ( ( s /usr/lib/python2.7/HTMLParser.pyR> � s c C s d S( N( ( R RG ( ( s /usr/lib/python2.7/HTMLParser.pyRA � s c C s d S( N( ( R R ( ( s /usr/lib/python2.7/HTMLParser.pyR1 � s c C s d S( N( ( R R ( ( s /usr/lib/python2.7/HTMLParser.pyRL � s c C s d S( N( ( R t decl( ( s /usr/lib/python2.7/HTMLParser.pyRI � s c C s d S( N( ( R R ( ( s /usr/lib/python2.7/HTMLParser.pyRP � s c C s d S( N( ( R R ( ( s /usr/lib/python2.7/HTMLParser.pyt unknown_decl� s c s2 d | k r | S� f d � } t j d | | � S( NR- c s | j � d } yZ | d d k ri | d } | d d k rS t | d d � } n t | � } t | � SWn t k r� d | d SXt j d k r� d d l } i d d 6} x- | j j � D] \ } } t | � | | <q� W| t _ n y � j | SWn t k rd | d SXd S( Ni t #i t xt Xi s &#R, i����u 't aposR- ( Rp Rq ( t groupst intt unichrt ValueErrorR t entitydefsR t htmlentitydefst name2codepointt iteritemst KeyError( t st cRx Rw RF t v( R ( s /usr/lib/python2.7/HTMLParser.pyt replaceEntities� s( s# &(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));( R% t sub( R R| R ( ( R s /usr/lib/python2.7/HTMLParser.pyRU � s ( R R N(! R R R R] R R R R R! R R" R# R) R* R R: RJ R9 R6 RR R7 R[ R\ Rj R> RA R1 RL RI RP Rn Rw RU ( ( ( s /usr/lib/python2.7/HTMLParser.pyR K s< ^ 4 ( ( R R R% R& R RB R@ R< R4 RO t commentcloseRS t tagfind_tolerantRT t VERBOSERf Rh Ri t ExceptionR R R ( ( ( s /usr/lib/python2.7/HTMLParser.pyt <module> s&