jzi%D 2 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$m%Z% dd lm&Z& dd
l'm(Z(m)Z)m*Z* dZ+e e e,e,f e,e,gdf Z- G d dee Z. G d de Z/y)zCUse the HTMLParser library to parse HTML files that aren't too bad. ) annotationsMITHTMLParserTreeBuilder)
HTMLParser) AnyCallablecastDictIterableListOptional
TYPE_CHECKINGTupleTypeUnion)
AttributeDictCDataComment DeclarationDoctypeProcessingInstruction)EntitySubstitution
UnicodeDammit)DetectsXMLParsedAsHTMLHTMLHTMLTreeBuilderSTRICTParserRejectedMarkup)
BeautifulSoup)NavigableString) _Encoding
_Encodings
_RawMarkupz html.parserNc e Zd ZU dZded< dZded< ed dd Zd
ed < d ed
< ded< ddZ d dZ d d dZ d d dZ
d dZ d!dZ d!dZ
d dZd"dZd dZd dZy)#BeautifulSoupHTMLParserreplacestrREPLACEignoreIGNOREon_duplicate_attributesoupr r- &Union[str, _DuplicateAttributeHandler]c || _ || _ |j j | _ t j
| g|i | g | _ | j y N)r. r- builderattribute_dict_classr __init__ already_closed_empty_element_initialize_xml_detector)selfr. r- argskwargss N/home/htdocs/ttos/venv/lib/python3.12/site-packages/bs4/builder/_htmlparser.pyr4 z BeautifulSoupHTMLParser.__init__T sS &<#$(LL$E$E!D24262 -/) %%' z List[str]r5 c t | r1 r )r7 messages r: errorz BeautifulSoupHTMLParser.erroro s #7++r; c N | j ||d | j | y)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)r7 tagattrss r: handle_startendtagz*BeautifulSoupHTMLParser.handle_startendtag s'
S%e D 3 r; c V | j }|D ]_ \ }}|d}||v rM| j }|| j k( r*|d| j fv r|||< @t t
| } |||| [|||< a | j j j r| j \ }} ndx}} | j j |dd||| }
|
<|
j r0|r.| j |d | j j | | j | j! | yy)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)r3 r- r+ r) r _DuplicateAttributeHandlerr. r2 store_line_numbersgetposrA is_empty_elementrB r5 append_root_tag_name_root_tag_encountered) r7 rC rD r@ attr_dictkeyvalueon_duperH rI tagObjs r: rA z'BeautifulSoupHTMLParser.handle_starttag sC $(#<#<#> 'JC }i 55dkk) t|| 44%*IcN "#=w GGIsE2!& #% ', 99 / /$(KKM !J %) )J** tY: +
&"9"9>R
s ?
- - 4 4S 9 & & &s + 'r; c |r*|| j v r | j j | y| j j | y)zHandle a closing tag, e.g. ''
:param tag: 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)r5 remover. rB )r7 rC rJ s r: rB z%BeautifulSoupHTMLParser.handle_endtag s< C4+L+L$L
- - 4 4S 9 II # #C (r; c : | j j | y)z4Handle some textual data that shows up between tags.N)r. handle_datar7 datas r: rZ z#BeautifulSoupHTMLParser.handle_data s d#r; c F |j d r t |j d d }n8|j d r t |j d d }n t | }t j | \ }}|rd| j
_ | j | y)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 XTN)
startswithintlstripr numeric_character_referencer. contains_replacement_charactersrZ )r7 name real_namer\ replacement_addeds r: handle_charrefz&BeautifulSoupHTMLParser.handle_charref s ??3 DKK ,b1I
__S
!DKK ,b1ID I"/"K"KI"V 8 '??CCDI D 4 rE rA rB rZ ri rn rq ru ry r| r; r: r& r& = s GS FC $ JQ (( ( !G (
(. CB"++
,
>
& &* <,
<, /<, # <,
<,|)$$ 0 &##
1r; r& c e Zd ZU dZdZded< dZded< eZded< ee e
gZ d ed
< d ed < dZ ded
< d d fd
Z
d ddZefddZ xZS )r zA Beautiful soup `bs4.builder.TreeBuilder` that uses the
:py:class:`html.parser.HTMLParser` parser, found in the Python
standard library.
Fr is_xmlT picklabler( NAMEz
Iterable[str]featuresz$Tuple[Iterable[Any], Dict[str, Any]] parser_argsTRACKS_LINE_NUMBERSc t }dD ] }||v s|j | }|||< t t | di | |xs g }|xs i }|j | d|d< ||f| _ y)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 r4 updater )r7 r
parser_kwargsr9 extra_parser_kwargsargrT __class__s r: r4 z HTMLParserTreeBuilder.__init__K s $ #f. 1Cf}
3+0#C( 1 #T3=f=!'R %+
01,1
() ' 7r; c # @ K t |t r |dddf yg }|r|j | g }|r|j | t |||d| }|j t d |j |j |j |j f yw)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_htmlexclude_encodingszPCould not convert input to Unicode, and html.parser will not accept bytestrings.)
isinstancer( rO r unicode_markupr original_encodingdeclared_html_encodingre )r7 markupuser_specified_encodingdocument_declared_encodingr r r dammits r: prepare_markupz$HTMLParserTreeBuilder.prepare_markupi s 2 fc "4u- - 57 "
% + +,C D*, %
! !"< = %=) /
( 'b
%%((--66
s B B c | j \ }}t |t sJ | j J || j g|i |} |j | |j g |_ y# t $ r}t | d}~ww xY w)z
:param markup: The markup to feed into the parser.
:param _parser_class: An HTMLParser subclass to use. This is only intended for use in unit tests.
N) r r r( r. feedcloseAssertionErrorr r5 )r7 r
_parser_classr8 r9 parseres r: r zHTMLParserTreeBuilder.feed s
'' f &#&&&
yy$$$ tyy:4:6: * KK LLN /1+ * 'q) ) *s !A0 0 B 9 BB )NN)r zOptional[Iterable[Any]]r zOptional[Dict[str, Any]]r9 r )NNN)
r r$ r Optional[_Encoding]r r r zOptional[_Encodings]r} zDIterable[Tuple[str, Optional[_Encoding], Optional[_Encoding], bool]])r r$ r z type[BeautifulSoupHTMLParser]r} r~ )r r r __doc__r r r
HTMLPARSERr r r r r r4 r r& r
__classcell__)r s @r: r r : s FDItD# #T6 2Hm255 !%$ 0426 8, 8 0 8 8B 8<:>26 FF "5F %8 F
0 F
N
FP Ul 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( rK r& r r r; r: r s I " # 9 0!+
%tCH~sC&@$&F G z1j*@ z1zT1O T1r;