Lc @ s d Z d d k Z d d k Z e i d Z e i d Z e i d Z e i d Z e i d Z e i d Z e i d Z
e i d
Z e i d Z e i d Z
e i d
e i Z e i d Z e i d Z d e f d YZ d e i f d YZ d S( s A parser for HTML and XHTML.iNs [&<]s <(/|\Z)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][-.a-zA-Z0-9:_]*s_ \s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~@]*))?s
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s+ # whitespace before attribute name
(?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
(?:\s*=\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|\"[^\"]*\" # LIT-enclosed value
|[^'\">\s]+ # bare value
)
)?
)
)*
\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 s5 | p t | | _ | d | _ | d | _ d S( Ni i ( t AssertionErrort msgt linenot offset( t selfR t position( ( s /usr/lib/python2.6/HTMLParser.pyt __init__4 s
c C s[ | i } | i d j o | d | i } n | i d j o | d | i d } n | S( Ns , at line %ds , column %di ( R R t NoneR ( R t result( ( s /usr/lib/python2.6/HTMLParser.pyt __str__: s N( NN( t __name__t
__module__t __doc__R R R ( ( ( s /usr/lib/python2.6/HTMLParser.pyR 1 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
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 | i d S( s# Initialize and reset this instance.N( t reset( R ( ( s /usr/lib/python2.6/HTMLParser.pyR Z s c C s/ d | _ d | _ t | _ t i i | d S( s1 Reset this instance. Loses all unprocessed data.t s ???N( t rawdatat lasttagt interesting_normalt interestingt
markupbaset
ParserBaseR ( R ( ( s /usr/lib/python2.6/HTMLParser.pyR ^ s c C s! | i | | _ | i 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 '
').
i N( R t goahead( R t data( ( s /usr/lib/python2.6/HTMLParser.pyt feede s c C s | i d d S( s Handle any buffered data.i N( R ( R ( ( s /usr/lib/python2.6/HTMLParser.pyt closen s c C s t | | i d S( N( R t getpos( R t message( ( s /usr/lib/python2.6/HTMLParser.pyt errorr s c C s | i S( s) Return full source of start tag: '<...>'.( t _HTMLParser__starttag_text( R ( ( s /usr/lib/python2.6/HTMLParser.pyt get_starttag_textw s c C s
t | _ d S( N( t interesting_cdataR ( R ( ( s /usr/lib/python2.6/HTMLParser.pyt set_cdata_mode{ s c C s
t | _ d S( N( R R ( R ( ( s /usr/lib/python2.6/HTMLParser.pyt clear_cdata_mode~ s c
C s) | i } d } t | } x| | j o| i i | | } | o | i } n | } | | j o | i | | | ! n | i | | } | | j o Pn | i } | d | o t i | | o | i
| } n | d | o | i | } n | d | o | i | } nt | d | o | i
| } nQ | d | o | i | } n. | d | j o | i d | d } n P| d j o | o | i d n Pn | i | | } q | d | o t i | | } | og | i d
d !} | i | | i } | d | d p | d } n | i | | } q qd | | j o* | i | d d
! | i | d
} n Pq | d
| ot i | | } | oc | i d } | i | | i } | d | d p | d } n | i | | } q n t i | | } | o4 | o( | i | | j o | i d n Pq| d | j o' | i d
| i | | d } qPq d p
t d q W| o7 | | j o* | i | | | ! | i | | } n | | | _ d S( Ni t <s </s <!--s <?s <!i s EOF in middle of constructs &#i it ;t &s# EOF in middle of entity or char refs interesting.search() lied( R t lenR t searcht startt handle_datat updatepost
startswitht starttagopent matcht parse_starttagt parse_endtagt
parse_commentt parse_pit parse_declarationR t charreft groupt handle_charreft endt entityreft handle_entityreft
incompleteR (
R R9 R t it nR0 t jR. t kt name( ( s /usr/lib/python2.6/HTMLParser.pyR s
c C s | i } | | | d !d j p
t d t i | | d } | p d S| i } | i | | d | ! | i } | S( Ni s <?s unexpected call to parse_pi()i( R R t picloseR* R+ t handle_piR9 ( R R= R R0 R? ( ( s /usr/lib/python2.6/HTMLParser.pyR4 s " c
C s d | _ | i | } | d j o | S| i } | | | !| _ g } t i | | d } | p
t d | i } | | d | !i | _ } x | | j o t
i | | } | p Pn | i d d d \ } }
} |
p
d } nm | d d j o | d j n p& | d d j o | d j n o | d d !} | i | } n | i
| i | f | i } q W| | | !i } | d j o | i \ }
} d | i j o9 |
| i i d }
t | i | i i d } n | t | i } | i d | | | !d
f n | i d
o | i | | n/ | i | | | | i j o | i n | S( Ni i s# unexpected call to parse_starttag()i i s 'it "R s />s
s junk characters in start tag: %ri ( R s />( R R! t check_for_whole_start_tagR t tagfindR0 R R9 t lowerR t attrfindR7 t unescapet appendt stripR t countR) t rfindR t endswitht handle_startendtagt handle_starttagt CDATA_CONTENT_ELEMENTSR$ ( R R= t endposR t attrsR0 R@ t tagt mt attrnamet restt attrvalueR9 R R ( ( s /usr/lib/python2.6/HTMLParser.pyR1 sR
&&
c C s | i } t i | | } | o | i } | | | d !} | d j o | d S| d j oY | i d | o | d S| i d | o d S| i | | d | i d n | d j o d S| d j o d S| i | | | i d
n t d d S( Ni R t /s />i is malformed empty start tagR s6 abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZs malformed start tags we should not get here!( R t locatestarttagendR0 R9 R. R- R R ( R R= R RU R? t next( ( s /usr/lib/python2.6/HTMLParser.pyRE s*
c C s | i } | | | d !d j p
t d t i | | d } | p d S| i } t i | | } | p | i d | | | !f n | i d } | i | i
| i | S( Ni s </s unexpected call to parse_endtagi is bad end tag: %r( R R t endendtagR* R9 t
endtagfindR0 R R7 t
handle_endtagRG R% ( R R= R R0 R? RT ( ( s /usr/lib/python2.6/HTMLParser.pyR2 4 s "
c C s! | i | | | i | d S( N( RP R^ ( R RT RS ( ( s /usr/lib/python2.6/HTMLParser.pyRO D s c C s d S( N( ( R RT RS ( ( s /usr/lib/python2.6/HTMLParser.pyRP I s c C s d S( N( ( R RT ( ( s /usr/lib/python2.6/HTMLParser.pyR^ M s c C s d S( N( ( R RA ( ( s /usr/lib/python2.6/HTMLParser.pyR8 Q s c C s d S( N( ( R RA ( ( s /usr/lib/python2.6/HTMLParser.pyR; U s c C s d S( N( ( R R ( ( s /usr/lib/python2.6/HTMLParser.pyR, Y s c C s d S( N( ( R R ( ( s /usr/lib/python2.6/HTMLParser.pyt handle_comment] s c C s d S( N( ( R t decl( ( s /usr/lib/python2.6/HTMLParser.pyt handle_decla s c C s d S( N( ( R R ( ( s /usr/lib/python2.6/HTMLParser.pyRC e s c C s | i d | f d S( Ns unknown declaration: %r( R ( R R ( ( s /usr/lib/python2.6/HTMLParser.pyt unknown_declh s c s4 d | j o | S f d } t i d | | S( NR( c s | i d } | d d j oI | d } | d d j o t | d d } n
t | } t | Sd d k } t i d j oH h d d 6} t _ x1 | i i D] \ } } t | | | <q Wn y i | SWn t j
o d
| d SXd S(
Ni t #i t xt Xi iu 't aposR( R' ( Rd Re (
t groupst intt unichrt htmlentitydefsR t
entitydefsR t name2codepointt iteritemst KeyError( t st cRj Rk R@ t v( R ( s /usr/lib/python2.6/HTMLParser.pyt replaceEntitiesp s"
s# &(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));( t ret sub( R Ro Rr ( ( R s /usr/lib/python2.6/HTMLParser.pyRI m s
( R R N( R R
R RQ R R R R R R R! R" R$ R% R R4 R1 RE R2 RO RP R^ R8 R; R, R_ Ra RC Rb Rk RI ( ( ( s /usr/lib/python2.6/HTMLParser.pyR C s8 S 3 ( R R Rs t compileR R# R< R: R6 R/ RB t commentcloseRF RH t VERBOSERZ R\ R] t ExceptionR R R ( ( ( s /usr/lib/python2.6/HTMLParser.pyt <module> s&
y~or5J ={Eeu磝Qk ᯘG{?+]ן?wM3X^歌>{7پK>on\jy R g/=fOroNVv~Y+ NGuÝHWyw[eQʨSb> >}Gmx[o[<{Ϯ_qF vM IENDB`
