OwgK: d Z dZdgZddlmZ ddlZddlZddlmZm Z m
Z
m Z m Z ddl
mZmZ ddlmZmZmZmZmZ d Z G d
d ee Z G d de Zy)
zCUse the HTMLParser library to parse HTML files that aren't too bad.MITHTMLParserTreeBuilder )
HTMLParserN)CDataComment DeclarationDoctypeProcessingInstruction)EntitySubstitution
UnicodeDammit)DetectsXMLParsedAsHTMLParserRejectedMarkupHTMLHTMLTreeBuilderSTRICTz html.parserc d e Zd ZdZdZdZd Zd Zd ZddZ ddZ
d Z d
Z d Z
d Zd
Zd Zd Zy)BeautifulSoupHTMLParserzA subclass of the Python standard library's HTMLParser class, which
listens for HTMLParser events and translates them into calls
to Beautiful Soup's tree construction API.
ignorereplacec |j d| j | _ t j | g|i | g | _ | j
y)a Constructor.
:param on_duplicate_attribute: A strategy for what to do if a
tag includes the same attribute more than once. Accepted
values are: REPLACE (replace earlier values with later
ones, the default), IGNORE (keep the earliest value
encountered), or a callable. A callable must take three
arguments: the dictionary of attributes already processed,
the name of the duplicate attribute, and the most recent value
encountered.
on_duplicate_attributeN)popREPLACEr r __init__ already_closed_empty_element_initialize_xml_detector)selfargskwargss N/var/www/horilla/myenv/lib/python3.12/site-packages/bs4/builder/_htmlparser.pyr z BeautifulSoupHTMLParser.__init__. sN '-jj $dll'
# D24262 -/) %%' c t | )N)r )r messages r errorz BeautifulSoupHTMLParser.errorJ s #7++r! c N | j ||d }| j | y)zHandle an incoming empty-element tag.
This is only called when the markup looks like .
:param name: Name of the tag.
:param attrs: Dictionary of the tag's attributes.
F)handle_empty_elementN)handle_starttag
handle_endtag)r nameattrstags r handle_startendtagz*BeautifulSoupHTMLParser.handle_startendtagZ s) ""4U"K 4 r! c i }|D ]Q \ }}|d}||v r=| j }|| j k( rn&|d| j fv r|||< n |||| n|||< d}S | j \ } }
| j j |dd|| |
} | r<| j r0|r.| j |d | j j | | j | j | yy)a3 Handle an opening tag, e.g. ''
:param name: Name of the tag.
:param attrs: Dictionary of the tag's attributes.
: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 z"")
sourceline sourceposF)check_already_closed) r IGNOREr getpossoupr' is_empty_elementr( r append _root_tag_root_tag_encountered) r r) r* r& attr_dictkeyvalueon_dupe attrvaluer/ r0 r+ s r r' z'BeautifulSoupHTMLParser.handle_starttagi s JC }i 55dkk) t|| 44%*IcNIsE2!& # I% ( !%
Iii'' $iJ (
3'',@
t% @
- - 4 4T : >> ! & &t , "r! c |r*|| j v r | j j | y| j j | y)zHandle a closing tag, e.g. ''
:param name: A tag name.
:param check_already_closed: True if this tag is expected to
be the closing portion of an empty-element tag,
e.g. ''.
N)r remover4 r( )r r) r1 s r r( z%BeautifulSoupHTMLParser.handle_endtag s< DD,M,M$M
- - 4 4T : II # #D )r! c : | j j | y)z4Handle some textual data that shows up between tags.N)r4 handle_datar datas r rA z#BeautifulSoupHTMLParser.handle_data s d#r! c |j d r t |j d d }n8|j d r t |j d d }n t | }d}|dk r<| j j dfD ]! }|s t |g j
| }# |s t | }|xs d}| j | y# t $ r
}Y d}~Xd}~ww xY w# t t f$ r
}Y d}~Bd}~ww xY w)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 �)
startswithintlstripr4 original_encoding bytearraydecodeUnicodeDecodeErrorchr
ValueError
OverflowErrorrA )r r) real_namerC encodinges r handle_charrefz&BeautifulSoupHTMLParser.handle_charref s ??3 DKK ,b1I
__S
!DKK ,b1ID I s? "YY 8 8. I
$i[188BD
9~ 22 *
.
s$ C, C% C" C"%C>9C>c x t j j | }||}nd|z }| j | y)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_CHARACTERgetrA )r r) characterrC s r handle_entityrefz(BeautifulSoupHTMLParser.handle_entityref s> '??CCDI D 4BJN/7b1r! )rl __license____all__ html.parserr syswarnings bs4.elementr r r r r
bs4.dammitr r bs4.builderr
r r r r r r r rm r! r r sf I #
9
v1j*@ v1rf1O f1r!