ó
5Þ Pc @ s d Z d d l Z d d l Z e j d ƒ Z e j d ƒ Z e j d ƒ Z e j d ƒ Z e j d ƒ Z e j d ƒ Z e j d ƒ Z
e j d
ƒ Z e j d ƒ Z e j d ƒ Z
e j d
e j ƒ Z e j d ƒ Z e j d ƒ Z d e f d „ ƒ YZ d e j 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:_]*sJ \s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?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 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__4 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__: s N( NN( t __name__t
__module__t __doc__R R R ( ( ( s /usr/lib/python2.7/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 | j ƒ d S( s# Initialize and reset this instance.N( t reset( R ( ( s /usr/lib/python2.7/HTMLParser.pyR Z s c C s8 d | _ d | _ t | _ d | _ t j j | ƒ d S( s1 Reset this instance. Loses all unprocessed data.t s ???N( t rawdatat lasttagt interesting_normalt interestingR t cdata_tagt
markupbaset
ParserBaseR ( R ( ( s /usr/lib/python2.7/HTMLParser.pyR ^ s
c C s! | j | | _ | j 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 '\n').
i N( R t goahead( R t data( ( s /usr/lib/python2.7/HTMLParser.pyt feedf s c C s | j d ƒ d S( s Handle any buffered data.i N( R ( R ( ( s /usr/lib/python2.7/HTMLParser.pyt closeo s c C s t | | j ƒ ƒ ‚ d S( N( R t getpos( R t message( ( s /usr/lib/python2.7/HTMLParser.pyt errors 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_textx s c C s t | _ | j ƒ | _ d S( N( t interesting_cdataR t lowerR ( R t tag( ( 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 sõ | j } d } t | ƒ } x‹| | k r¨| j j | | ƒ } | rT | j ƒ } n | } | | k r} | j | | | !ƒ n | j | | ƒ } | | k rŸ Pn | j } | d | ƒ rÅt j | | ƒ rÛ | j
| ƒ } n¯ | d | ƒ rü | j | ƒ } nŽ | d | ƒ r | j | ƒ } nm | d | ƒ r>| j
| ƒ } nL | d | ƒ r_| j | ƒ } n+ | d | k r‰| j d ƒ | d } n P| d k r°| r¬| j d ƒ n Pn | j | | ƒ } q | d | ƒ rt j | | ƒ } | rP| j ƒ d
d !} | j | ƒ | j ƒ } | d | d ƒ s8| d } n | j | | ƒ } q q¥d | | k r‰| j | d d
!ƒ | j | d
ƒ } n Pq | d
| ƒ r–t j | | ƒ } | r| j d ƒ } | j | ƒ | j ƒ } | d | d ƒ sü| d } n | j | | ƒ } q n t j | | ƒ } | r\| rX| j ƒ | | k rX| j d ƒ n Pq¥| d | k r’| j d
ƒ | j | | d ƒ } q¥Pq d s t d ‚ q W| rä| | k rä| j | | | !ƒ | j | | ƒ } n | | | _ d S( Ni t