Ñò
§ÚêLc @ s d Z d d k Z d d k Z e i d ƒ Z e i d ƒ Z e i d ƒ Z e i d ƒ Z e i d ƒ Z e i d ƒ Z e i d ƒ Z
e i d
ƒ Z e i d ƒ Z e i d ƒ Z
e i d
e i ƒ Z e i d ƒ Z e i d ƒ Z d e f d „ ƒ YZ d e i f d „ ƒ YZ d S( s A parser for HTML and XHTML.iÿÿÿÿNs [&<]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./,:;+*%?!&$\(\)_#=~@]*))?sê
<[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# 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/lib64/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/lib64/python2.6/HTMLParser.pyt __str__: s N( NN( t __name__t
__module__t __doc__R R R ( ( ( s" /usr/lib64/python2.6/HTMLParser.pyR 1 s t
HTMLParserc B sø 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( sÇ 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 ƒ d S( s# Initialize and reset this instance.N( t reset( R ( ( s" /usr/lib64/python2.6/HTMLParser.pyR Z s c C s/ d | _ d | _ t | _ t i i | ƒ d S( s1 Reset this instance. Loses all unprocessed data.t s ???N( t rawdatat lasttagt interesting_normalt interestingt
markupbaset
ParserBaseR ( R ( ( s" /usr/lib64/python2.6/HTMLParser.pyR ^ s c C s! | i | | _ | i d ƒ 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/lib64/python2.6/HTMLParser.pyt feede s c C s | i d ƒ d S( s Handle any buffered data.i N( R ( R ( ( s" /usr/lib64/python2.6/HTMLParser.pyt closen s c C s t | | i ƒ ƒ ‚ d S( N( R t getpos( R t message( ( s" /usr/lib64/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/lib64/python2.6/HTMLParser.pyt get_starttag_textw s c C s
t | _ d S( N( t interesting_cdataR ( R ( ( s" /usr/lib64/python2.6/HTMLParser.pyt set_cdata_mode{ s c C s
t | _ d S( N( R R ( R ( ( s" /usr/lib64/python2.6/HTMLParser.pyt clear_cdata_mode~ s c
C s) | i } d } t | ƒ } x¼| | j o®| i i | | ƒ } | o | i ƒ } n | } | | j o | i | | | !ƒ n | i | | ƒ } | | j o Pn | i } | d | ƒ o t i | | ƒ o | i
| ƒ } nº | d | ƒ o | i | ƒ } n— | d | ƒ o | i | ƒ } nt | d | ƒ o | i
| ƒ } nQ | d | ƒ o | i | ƒ } n. | d | j o | i d ƒ | d } n P| d j o | o | i d ƒ n Pn | i | | ƒ } q | d | ƒ oÀ t i | | ƒ } | og | i ƒ d
d !} | i | ƒ | i ƒ } | d | d ƒ p | d } n | i | | ƒ } q qÕd | | j o* | i | d d
!ƒ | i | d
ƒ } n Pq | d
| ƒ ot i | | ƒ } | oc | i d ƒ } | i | ƒ | i ƒ } | d | d ƒ p | d } n | i | | ƒ } q n t i | | ƒ } | o4 | o( | i ƒ | | j o | i d ƒ n PqÕ| d | j o' | i d
ƒ | i | | d ƒ } qÕPq d p
t d ‚ q W| o7 | | j o* | i | | | !ƒ | i | | ƒ } n | | | _ d S( Ni t