o
    _"<f                     @   s  d Z dZddlZddlmZ ddlmZ ddlZddlmZm	Z	 ddl
mZ ddlZddlZddlZddlZddlZddlZddlZddlZdd	 Zd#ddZG dd deZdd ZdZdZd$ddZd%ddZd&ddZd'ddZd(d d!Zed"kreej   dS dS ))z=Diagnostic functions, mainly for use when doing tech support.MIT    N)BytesIO)
HTMLParser)BeautifulSoup__version__)builder_registryc                 C   sR  t dt  t dtj  g d}|D ]}tjD ]	}||jv r! nq|| t d|  qd|v rc|d zddl	m
} t d	d
tt|j  W n tyb } z
t d W Y d}~nd}~ww d|v rzddl}t d|j  W n ty } z
t d W Y d}~nd}~ww t| dr|  } nJ| ds| drt d|   t d dS z&tj| rt d|   t| }| } W d   n1 sw   Y  W n	 ty   Y nw t d |D ]E}t d|  d}	z
t| |d}
d}	W n ty } zt d|  t  W Y d}~nd}~ww |	r"t d|  t |
  t d qdS )zDiagnostic suite for isolating common problems.

    :param data: A string containing markup that needs to be explained.
    :return: None; diagnostics are printed to standard output.
    z'Diagnostic running on Beautiful Soup %szPython version %s)html.parserhtml5liblxmlz;I noticed that %s is not installed. Installing it may help.r
   zlxml-xmlr   etreezFound lxml version %s.z.lxml is not installed or couldn't be imported.Nr	   zFound html5lib version %sz2html5lib is not installed or couldn't be imported.readzhttp:zhttps:z<"%s" looks like a URL. Beautiful Soup is not an HTTP client.zpYou need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.z7"%s" looks like a filename. Reading data from the file. z#Trying to parse your markup with %sF)featuresT%s could not parse the markup.z#Here's what %s did with the markup:zP--------------------------------------------------------------------------------)printr   sysversionr   buildersr   removeappendr
   r   joinmapstrLXML_VERSIONImportErrorr	   hasattrr   
startswithospathexistsopen
ValueErrorr   	Exception	traceback	print_excprettify)databasic_parsersnamebuilderr   er	   fpparsersuccesssoup r1   C/var/www/html/kck/venv/lib/python3.10/site-packages/bs4/diagnose.pydiagnose   s   








r3   Tc                 K   sp   ddl m} |dd}t| tr| d} t| }|j|f||d|D ]\}}td||j	|j
f  q&dS )	a  Print out the lxml events that occur during parsing.

    This lets you see how lxml parses a document when no Beautiful
    Soup code is running. You can use this to determine whether
    an lxml-specific problem is in Beautiful Soup's lxml tree builders
    or in lxml itself.

    :param data: Some markup.
    :param html: If True, markup will be parsed with lxml's HTML parser.
       if False, lxml's XML parser will be used.
    r   r   recoverTutf8)htmlr4   z%s, %4s, %sN)r
   r   pop
isinstancer   encoder   	iterparser   tagtext)r(   r6   kwargsr   r4   readereventelementr1   r1   r2   
lxml_trace]   s   

rA   c                   @   s`   e Zd ZdZdd Zdd Zdd Zdd	 Zd
d Zdd Z	dd Z
dd Zdd Zdd ZdS )AnnouncingParserzSubclass of HTMLParser that announces parse events, without doing
    anything else.

    You can use this to get a picture of how html.parser sees a given
    document. The easiest way to do this is to call `htmlparser_trace`.
    c                 C   s   t | d S )N)r   )selfsr1   r1   r2   _p{   s   zAnnouncingParser._pc                 C      |  d|  d S )Nz%s STARTrE   )rC   r*   attrsr1   r1   r2   handle_starttag~      z AnnouncingParser.handle_starttagc                 C   rF   )Nz%s ENDrG   rC   r*   r1   r1   r2   handle_endtag   rJ   zAnnouncingParser.handle_endtagc                 C   rF   )Nz%s DATArG   rC   r(   r1   r1   r2   handle_data   rJ   zAnnouncingParser.handle_datac                 C   rF   )Nz
%s CHARREFrG   rK   r1   r1   r2   handle_charref   rJ   zAnnouncingParser.handle_charrefc                 C   rF   )Nz%s ENTITYREFrG   rK   r1   r1   r2   handle_entityref   rJ   z!AnnouncingParser.handle_entityrefc                 C   rF   )Nz
%s COMMENTrG   rM   r1   r1   r2   handle_comment   rJ   zAnnouncingParser.handle_commentc                 C   rF   )Nz%s DECLrG   rM   r1   r1   r2   handle_decl   rJ   zAnnouncingParser.handle_declc                 C   rF   )Nz%s UNKNOWN-DECLrG   rM   r1   r1   r2   unknown_decl   rJ   zAnnouncingParser.unknown_declc                 C   rF   )Nz%s PIrG   rM   r1   r1   r2   	handle_pi   rJ   zAnnouncingParser.handle_piN)__name__
__module____qualname____doc__rE   rI   rL   rN   rO   rP   rQ   rR   rS   rT   r1   r1   r1   r2   rB   s   s    rB   c                 C   s   t  }||  dS )zPrint out the HTMLParser events that occur during parsing.

    This lets you see how HTMLParser parses a document when no
    Beautiful Soup code is running.

    :param data: Some markup.
    N)rB   feed)r(   r.   r1   r1   r2   htmlparser_trace   s   rZ   aeioubcdfghjklmnpqrstvwxyz   c                 C   s:   d}t | D ]}|d dkrt}nt}|t|7 }q|S )z#Generate a random word-like string.r      r   )range_consonants_vowelsrandomchoice)lengthrD   itr1   r1   r2   rword   s   rg      c                 C   s   d dd t| D S )z'Generate a random sentence-like string. c                 s   s     | ]}t td dV  qdS )rh   	   N)rg   rb   randint).0re   r1   r1   r2   	<genexpr>   s    zrsentence.<locals>.<genexpr>)r   r_   )rd   r1   r1   r2   	rsentence   s   rn     c                 C   s   g d}g }t | D ]9}tdd}|dkr#t|}|d|  q
|dkr3|ttdd q
|dkrCt|}|d|  q
d	d
| d S )z+Randomly generate an invalid HTML document.)pdivspanre   bscripttabler      z<%s>   rh   r^   z</%s>z<html>
z</html>)r_   rb   rk   rc   r   rn   r   )num_elements	tag_nameselementsre   rc   tag_namer1   r1   r2   rdoc   s   

r}   順 c           
      C   s&  t dt  t| }t dt|  dddgddfD ]>}d}zt }t||}t }d}W n tyK } zt d	|  t  W Y d
}~nd
}~ww |rXt d||| f  qddl	m
} t }|| t }t d||   dd
l}	|	 }t }|| t }t d||   d
S )z.Very basic head-to-head performance benchmark.z1Comparative parser benchmark on Beautiful Soup %sz3Generated a large invalid HTML document (%d bytes).r
   r6   r	   r   FTr   Nz"BS4+%s parsed the markup in %.2fs.r   r   z$Raw lxml parsed the markup in %.2fs.z(Raw html5lib parsed the markup in %.2fs.)r   r   r}   lentimer   r$   r%   r&   r
   r   HTMLr	   r   parse)
ry   r(   r.   r/   ar0   rs   r,   r   r	   r1   r1   r2   benchmark_parsers   s:   


r   r
   c                 C   sX   t  }|j}t| }tt||d}td||| t	|}|
d |dd dS )z7Use Python's profiler on a randomly generated document.)bs4r(   r.   zbs4.BeautifulSoup(data, parser)
cumulativez_html5lib|bs42   N)tempfileNamedTemporaryFiler*   r}   dictr   cProfilerunctxpstatsStats
sort_statsprint_stats)ry   r.   
filehandlefilenamer(   varsstatsr1   r1   r2   profile   s   

r   __main__)T)r]   )rh   )ro   )r~   )r~   r
   )!rX   __license__r   ior   html.parserr   r   r   r   bs4.builderr   r   r   rb   r   r   r%   r   r3   rA   rB   rZ   ra   r`   rg   rn   r}   r   r   rU   stdinr   r1   r1   r1   r2   <module>   s<    
G&




 