MhE L d Z ddlmZ dZdgZddlmZ ddlmZm Z m
Z
m Z m Z m
Z
mZmZmZmZmZ ddlmZmZmZmZmZmZ ddlmZm Z dd l m Z m Z m Z m!Z! dd
l"m#Z# erdd l$m%Z% dd lm&Z& dd
l'm(Z(m)Z)m*Z* dZ+e e e,e,f e,e,gdf Z- G d dee Z. G d de Z/dS )zCUse the HTMLParser library to parse HTML files that aren't too bad. ) annotationsMITHTMLParserTreeBuilder)
HTMLParser) AnyCallablecastDictIterableListOptional
TYPE_CHECKINGTupleTypeUnion)
AttributeDictCDataComment DeclarationDoctypeProcessingInstruction)EntitySubstitution
UnicodeDammit)DetectsXMLParsedAsHTMLHTMLHTMLTreeBuilderSTRICTParserRejectedMarkup)
BeautifulSoup)NavigableString) _Encoding
_Encodings
_RawMarkupz html.parserNc e Zd ZU dZded< dZded< edd(dZd ed < ded< ded< d)dZd*dZ d+d,d Z d+d-d Z
d.d Z d/d!Z d/d"Z
d.d#Zd.d$Zd.d%Zd.d&Zd'S )0BeautifulSoupHTMLParserreplacestrREPLACEignoreIGNOREon_duplicate_attributesoupr argsr r- &Union[str, _DuplicateAttributeHandler]kwargsc || _ || _ |j j | _ t j | g|R i | g | _ | d S N)r. r- builderattribute_dict_classr __init__ already_closed_empty_element_initialize_xml_detector)selfr. r- r/ r1 s W/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/bs4/builder/_htmlparser.pyr6 z BeautifulSoupHTMLParser.__init__T sc &<#$(L$E!D242226222 -/) %%''''' z List[str]r7 messagereturnNonec t | r3 r )r9 r< s r: errorz BeautifulSoupHTMLParser.erroro s #7+++r; nameattrs List[Tuple[str, Optional[str]]]c ` | ||d | | dS )zHandle an incoming empty-element tag.
html.parser only calls this method when the markup looks like
.
F)handle_empty_elementN)handle_starttag
handle_endtag)r9 rA rB s r: handle_startendtagz*BeautifulSoupHTMLParser.handle_startendtag s9
T5u EEE 4 r; TrE boolc 4 | }|D ]Y\ }}|d}||v rG| j }|| j k r |d| j fv r|||< 1t t
| } |||| T|||< Z| j j j r| \ }} ndx}} | j
|dd||| }
|
r:|
j r3|r1| |d | j
| | j | | dS dS )zHandle an opening tag, e.g. ''
:param handle_empty_element: True if this tag is known to be
an empty-element tag (i.e. there is not expected to be any
closing tag).
N )
sourceline sourceposF)check_already_closed)r5 r- r+ r) r _DuplicateAttributeHandlerr. r4 store_line_numbersgetposrF is_empty_elementrG r7 append_root_tag_name_root_tag_encountered) r9 rA rB rE attr_dictkeyvalueon_duperL rM tags r: rF z'BeautifulSoupHTMLParser.handle_starttag s| $(#<#<#>#> ' 'JC }i 5dk)) t| 444%*IcNN "#=w G GGGIsE2222!& # 9 / *$(KKMM !J %) )Ji'' $iJ) (
;3' ;,@ ;
t% @ @ @
- 4 4T : : : & & &t , , , , , ' &r; rN c |r%|| j v r | j | dS | j | dS )zHandle a closing tag, e.g. ''
:param name: A tag name.
:param check_already_closed: True if this tag is expected to
be the closing portion of an empty-element tag,
e.g. ''.
N)r7 remover. rG )r9 rA rN s r: rG z%BeautifulSoupHTMLParser.handle_endtag sT *DD,M$M$M
- 4 4T : : : : : I # #D ) ) ) ) )r; datac : | j | dS )z4Handle some textual data that shows up between tags.N)r. handle_datar9 r] s r: r_ z#BeautifulSoupHTMLParser.handle_data s d#####r; c . | d r$t | d d }nH| d r$t | d d }nt | }d}|dk rH| j j dfD ]9}|s t |g | }*# t $ r Y 6w xY w|s( t | }n# t t f$ r Y nw xY w|pd}| | dS )zHandle a numeric character reference by converting it to the
corresponding Unicode character and treating it as textual
data.
:param name: Character number, possibly in hexadecimal.
x XN z windows-1252u �)
startswithintlstripr. original_encoding bytearraydecodeUnicodeDecodeErrorchr
ValueError
OverflowErrorr_ )r9 rA real_namer] encodings r: handle_charrefz&BeautifulSoupHTMLParser.handle_charref sM ??3 "DKK , ,b11II
__S
!
! "DKK , ,b11IID I s?? "Y 8. I
$i[1188BBDD) D
9~~
.
22 s$ #C
CCC% %C98C9c t j | }||}nd|z }| | dS )zHandle a named entity reference by converting it to the
corresponding Unicode character(s) and treating it as textual
data.
:param name: Name of the entity reference.
Nz&%s)r HTML_ENTITY_TO_CHARACTERgetr_ )r9 rA characterr] s r: handle_entityrefz(BeautifulSoupHTMLParser.handle_entityref
sL '?CCDII DD 4 )rA r( rB rC r= r> )T)rA r( rB rC rE rI r= r> )rA r( rN rI r= r> )r] r( r= r> )rA r( r= r> )__name__
__module__ __qualname__r) __annotations__r+ r6 r@ rH rF rG r_ rr rw rz r} r r r; r: r& r& = sz G F $ JQ ( ( ( ( ( (. CBBB++++, , , ,
!
!
!
!& &* <- <- <- <- <-|* * * * *$$ $ $ $& & & & P &# # # ## # # #
1 1 1 1 1 1r; r& c e Zd ZU dZdZded< dZded< eZded< ee e
gZ d ed
< d ed < dZ ded
< d!d" fd
Z
d#d$d Zd%d Z xZS )&r zA Beautiful soup `bs4.builder.TreeBuilder` that uses the
:py:class:`html.parser.HTMLParser` parser, found in the Python
standard library.
FrI is_xmlT picklabler( NAMEz
Iterable[str]featuresz$Tuple[Iterable[Any], Dict[str, Any]] parser_argsTRACKS_LINE_NUMBERSNOptional[Iterable[Any]]
parser_kwargsOptional[Dict[str, Any]]r1 r c t }dD ] }||v r| | }|||< ! t t | j di | |pg }|pi }| | d|d< ||f| _ dS )a Constructor.
:param parser_args: Positional arguments to pass into
the BeautifulSoupHTMLParser constructor, once it's
invoked.
:param parser_kwargs: Keyword arguments to pass into
the BeautifulSoupHTMLParser constructor, once it's
invoked.
:param kwargs: Keyword arguments for the superclass constructor.
r, Fconvert_charrefsNr )dictpopsuperr r6 updater )r9 r r r1 extra_parser_kwargsargrX __class__s r: r6 z HTMLParserTreeBuilder.__init__[ s $ #ff. 1 1Cf}}
3+0#C(3#T**3==f===!'R %+
0111,1
() ' 7r; markupr$ user_specified_encodingOptional[_Encoding]document_declared_encodingexclude_encodingsOptional[_Encodings]r= DIterable[Tuple[str, Optional[_Encoding], Optional[_Encoding], bool]]c # 8 K t |t r
|dddfV dS g }|r| | g }|r| | t |||d| }|j t d |j |j |j |j fV dS )a2 Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
:param markup: Some markup -- probably a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples: (markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for parsing the document.
This TreeBuilder uses Unicode, Dammit to convert the markup
into Unicode, so the ``markup`` element of the tuple will
always be a string.
NFT)known_definite_encodingsuser_encodingsis_htmlr zPCould not convert input to Unicode, and html.parser will not accept bytestrings.)
isinstancer( rS r unicode_markupr ri declared_html_encoding contains_replacement_characters)r9 r r r r r r dammits r: prepare_markupz$HTMLParserTreeBuilder.prepare_markupy s 2 fc " " 4u- - - - F 57 " E
% + +,C D D D*, % >
! !"< = = = %=) /
( 'b
%(-6
r; r> c * | j \ }}t |t sJ | j J t | j g|R i |} | | | n!# t $ r}t | d }~ww xY wg |_ d S r3 )
r r r( r. r& feedcloseAssertionErrorr r7 )r9 r r/ r1 parseres r: r zHTMLParserTreeBuilder.feed s ' f &#&&&&&
y$$$(DTDDDVDD * KK LLNNNN * * * 'q)) ) *
/1+++s )A+ +
B 5BB )NN)r r r r r1 r )NNN)
r r$ r r r r r r r= r )r r$ r= r> )r r r __doc__r r r
HTMLPARSERr r r r r r6 r r
__classcell__)r s @r: r r J s FID #T6 2H22225555 !%$$$$ 0426 8 8 8 8 8 8 8B 8<:>26 F F F F FP1 1 1 1 1 1 1 1r; )0r
__future__r __license____all__ html.parserr typingr r r r
r r r
r r r r bs4.elementr r r r r r
bs4.dammitr r bs4.builderr r r r bs4.exceptionsr bs4r r! bs4._typingr" r# r$ r r( rO r& r r r; r: r sx I I " " " " " " # " " " " " 9 8 8 8 8 8 8 8 0 / / / / / !!!!!!++++++
%tCH~sC&@$&F G J1 J1 J1 J1 J1j*@ J1 J1 J1ZP1 P1 P1 P1 P1O P1 P1 P1 P1 P1r;