Warning: session_start(): Session cannot be started after headers have already been sent in /home/tvrreohg/public_html/manga.php on line 13
3
6]3 @ s d Z dgZddlmZ yddlmZ W n2 ek
rX Z zG dd deZW Y ddZ[X nX ddlZddl Z ej
dd \Z Z Z
e dkoe d koe
dkZe dkoe dkZe dkoe d
kZdd lmZmZmZmZmZ dd lmZmZ dd
lmZm Z m Z dZ G dd deZ G dd de Z e dkre d kre rddl!Z!e!j"dZ#e#e _#e!j"de!j$Z%e%e _%ddlm&Z&m'Z' dd Z(dd Z)e(e _(e)e _)dZdS )zCUse the HTMLParser library to parse HTML files that aren't too bad.HTMLParserTreeBuilder )
HTMLParser)HTMLParseErrorc @ s e Zd ZdS )r N)__name__
__module__ __qualname__ r r !/usr/lib/python3.6/_htmlparser.pyr s r N )CDataComment DeclarationDoctypeProcessingInstruction)EntitySubstitution
UnicodeDammit)HTMLHTMLTreeBuilderSTRICTz html.parserc @ sp e Zd Zdd Zdd Zdd Zddd Zd d
d Zd d
Zdd Z dd Z
dd Z dd Z dd Z
dd ZdS ) BeautifulSoupHTMLParserc O s t j| f|| g | _d S )N)r __init__ already_closed_empty_element)selfargskwargsr r r r 9 s z BeautifulSoupHTMLParser.__init__c C s t j| dS )ai In Python 3, HTMLParser subclasses must implement error(), although this
requirement doesn't appear to be documented.
In Python 2, HTMLParser implements error() as raising an exception.
In any event, this method is called only on very strange markup and our best strategy
is to pretend it didn't happen and keep going.
N)warningswarn)r msgr r r errorE s z BeautifulSoupHTMLParser.errorc C s | j ||dd}| j| d S )NF)handle_empty_element)handle_starttag
handle_endtag)r nameattrstagr r r handle_startendtagP s z*BeautifulSoupHTMLParser.handle_startendtagTc C sl i }x(|D ] \}}|d kr d}|||< d}q
W | j j|d d |}|rh|jrh|rh| j|dd | jj| d S )N z""F)check_already_closed)soupr" Zis_empty_elementr# r append) r r$ r% r! Z attr_dictkeyvalue attrvaluer& r r r r" [ s
z'BeautifulSoupHTMLParser.handle_starttagc C s, |r || j kr | j j| n | jj| d S )N)r remover* r# )r r$ r) r r r r# w s z%BeautifulSoupHTMLParser.handle_endtagc C s | j j| d S )N)r* handle_data)r datar r r r0 s z#BeautifulSoupHTMLParser.handle_datac C s |j dr t|jdd}n$|j dr8t|jdd}nt|}d }|dk rxR| jjdfD ]B}|sdqZyt|gj|}W qZ tk
r } zW Y d d }~X qZX qZW |sy t|}W n& t t
fk
r } zW Y d d }~X nX |pd}| j | d S )Nx X z windows-1252u �)
startswithintlstripr* original_encoding bytearraydecodeUnicodeDecodeErrorchr
ValueError
OverflowErrorr0 )r r$ Z real_namer1 encodinger r r handle_charref s*
z&BeautifulSoupHTMLParser.handle_charrefc C s0 t jj|}|d k r|}nd| }| j| d S )Nz&%s)r ZHTML_ENTITY_TO_CHARACTERgetr0 )r r$ characterr1 r r r handle_entityref s
z(BeautifulSoupHTMLParser.handle_entityrefc C s& | j j | j j| | j jt d S )N)r* endDatar0 r )r r1 r r r handle_comment s
z&BeautifulSoupHTMLParser.handle_commentc C sN | j j |jdr&|tdd }n |dkr2d}| j j| | j jt d S )NzDOCTYPE ZDOCTYPEr( )r* rF r6 lenr0 r )r r1 r r r handle_decl s
z#BeautifulSoupHTMLParser.handle_declc C sN |j jdr$t}|tdd }nt}| jj | jj| | jj| d S )NzCDATA[)upperr6 r
rH r r* rF r0 )r r1 clsr r r unknown_decl s
z$BeautifulSoupHTMLParser.unknown_declc C s& | j j | j j| | j jt d S )N)r* rF r0 r )r r1 r r r handle_pi s
z!BeautifulSoupHTMLParser.handle_piN)T)T)r r r r r r' r" r# r0 rB rE rG rI rL rM r r r r r 7 s
!
r c @ s< e Zd ZdZdZeZeeegZ dd Z
d
ddZ dd Z dS ) r FTc O s, t rt rd|d< tr d|d< ||f| _d S )NFstrictZconvert_charrefs)CONSTRUCTOR_TAKES_STRICT CONSTRUCTOR_STRICT_IS_DEPRECATED"CONSTRUCTOR_TAKES_CONVERT_CHARREFS parser_args)r r r r r r r s
z HTMLParserTreeBuilder.__init__Nc c sN t |tr |dddfV dS ||g}t||d|d}|j|j|j|jfV dS )z
:return: A 4-tuple (markup, original encoding, encoding
declared within markup, whether any characters had to be
replaced with REPLACEMENT CHARACTER).
NFT)Zis_htmlexclude_encodings)
isinstancestrr markupr9 Zdeclared_html_encodingZ contains_replacement_characters)r rV Zuser_specified_encodingZdocument_declared_encodingrS Z
try_encodingsZdammitr r r prepare_markup s
z$HTMLParserTreeBuilder.prepare_markupc C sr | j \}}t||}| j|_y|j| |j W n4 tk
rf } ztjtd |W Y d d }~X nX g |_ d S )Na* Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help.)
rR r r* feedcloser r r RuntimeWarningr )r rV r r parserrA r r r rX s
zHTMLParserTreeBuilder.feed)NNN)
r r r Zis_xmlZ picklable
HTMLPARSERNAMEr r Zfeaturesr rW rX r r r r r s
zQ\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?a
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s+ # whitespace before attribute name
(?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
(?:\s*=\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|\"[^\"]*\" # LIT-enclosed value
|[^'\">\s]+ # bare value
)
)?
)
)*
\s* # trailing whitespace
)tagfindattrfindc C s, d | _ | j|}|dk r |S | j}||| | _ g }tj||d }|j }||d | j | _}x||k rD| jrt j||}n t
j||}|sP |j ddd\} }
} |
sd } nb| d d d ko| d d kn s | d d d ko| d
d kn r| dd } | r(| j | } |j
| j | f |j }qhW ||| j } | dkr| j \}
}d | j kr|
| j jd }
t| j | j jd }n|t| j }| jr| jd
||| d d f | j||| |S | jdr| j|| n"| j|| || jkr(| j| |S )Nr r r
'">/>
z junk characters in start tag: %r rg rg )rc rd )Z__starttag_textZcheck_for_whole_start_tagrawdatar^ matchendlowerZlasttagrN r_ attrfind_tolerantgroupZunescaper+ stripZgetposcountrH rfindr r0 endswithr' r" ZCDATA_CONTENT_ELEMENTSset_cdata_mode)r iendposrh r% ri kr& mZattrnamerestr. rj linenooffsetr r r parse_starttag sZ
*,
rz c C s$ |j | _tjd| j tj| _d S )Nz )rk Z
cdata_elemrecompileIZ interesting)r elemr r r rr T s
rr T)*__doc____all__Z html.parserr r ImportErrorrA Exceptionsysr version_infomajorminorreleaserO rP rQ Z bs4.elementr
r r r r Z
bs4.dammitr r Z bs4.builderr r r r\ r r r{ r| rl VERBOSEZlocatestarttagendr^ r_ rz rr r r r r sB " 2
7