U
    pc                     @   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reej   dS ))z=Diagnostic functions, mainly for use when doing tech support.MIT    N)BytesIO)
HTMLParser)BeautifulSoup__version__)builder_registryc                 C   sL  t dt  t dtj  dddg}|D ]4}tjD ]}||jkr2 q(q2|| t d|  q(d|kr|d z*dd	l	m
} t d
dtt|j  W n* tk
r } zt d W 5 d}~X Y nX d|krzddl}t d|j  W n, tk
r } zt d W 5 d}~X Y nX t| dr.|  } n| dsF| dr^t d|   t d dS z:tj| rt d|   t| }| } W 5 Q R X W n tk
r   Y nX t d |D ]}t d|  d}	zt| |d}
d}	W n8 tk
r } zt d|  t  W 5 d}~X Y nX |	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.zlxml-xmlr   etreezFound lxml version %s.z.lxml is not installed or couldn't be imported.Nz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   Zbuildersr   removeappendr
   r   joinmapstrZLXML_VERSIONImportErrorr	   hasattrr   
startswithospathexistsopen
ValueErrorr   	Exception	traceback	print_excZprettify)dataZbasic_parsersnameZbuilderr   er	   fpparsersuccesssoup r,   0/tmp/pip-unpacked-wheel-a4a_sgaz/bs4/diagnose.pydiagnose   sr    







r.   Tc                 K   sp   ddl m} |dd}t| tr,| d} t| }|j|f||d|D ]\}}td||j	|j
f  qLd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)htmlr/   z%s, %4s, %sN)r
   r   pop
isinstancer   encoder   	iterparser   tagtext)r%   r1   kwargsr   r/   readereventelementr,   r,   r-   
lxml_trace]   s    

 r<   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sr,   r,   r-   _p{   s    zAnnouncingParser._pc                 C   s   |  d|  d S )Nz%s STARTr@   )r>   r&   attrsr,   r,   r-   handle_starttag~   s    z AnnouncingParser.handle_starttagc                 C   s   |  d|  d S )Nz%s ENDrA   r>   r&   r,   r,   r-   handle_endtag   s    zAnnouncingParser.handle_endtagc                 C   s   |  d|  d S )Nz%s DATArA   r>   r%   r,   r,   r-   handle_data   s    zAnnouncingParser.handle_datac                 C   s   |  d|  d S )Nz
%s CHARREFrA   rD   r,   r,   r-   handle_charref   s    zAnnouncingParser.handle_charrefc                 C   s   |  d|  d S )Nz%s ENTITYREFrA   rD   r,   r,   r-   handle_entityref   s    z!AnnouncingParser.handle_entityrefc                 C   s   |  d|  d S )Nz
%s COMMENTrA   rF   r,   r,   r-   handle_comment   s    zAnnouncingParser.handle_commentc                 C   s   |  d|  d S )Nz%s DECLrA   rF   r,   r,   r-   handle_decl   s    zAnnouncingParser.handle_declc                 C   s   |  d|  d S )Nz%s UNKNOWN-DECLrA   rF   r,   r,   r-   unknown_decl   s    zAnnouncingParser.unknown_declc                 C   s   |  d|  d S )Nz%s PIrA   rF   r,   r,   r-   	handle_pi   s    zAnnouncingParser.handle_piN)__name__
__module____qualname____doc__r@   rC   rE   rG   rH   rI   rJ   rK   rL   rM   r,   r,   r,   r-   r=   s   s   r=   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)r=   feed)r%   r)   r,   r,   r-   htmlparser_trace   s    rS   ZaeiouZ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)lengthr?   itr,   r,   r-   rword   s    r^      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 )r_   	   N)r^   rY   randint).0r\   r,   r,   r-   	<genexpr>   s     zrsentence.<locals>.<genexpr>)r   rV   )r[   r,   r,   r-   	rsentence   s    re     c                 C   s   dddddddg}g }t | D ]r}tdd	}|dkrPt|}|d
|  q|dkrp|ttdd q|dkrt|}|d|  qdd| d S )z+Randomly generate an invalid HTML document.pdivspanr\   bscripttabler      z<%s>   r_   rU   z</%s>z<html>
z</html>)rV   rY   rb   rZ   r   re   r   )num_elementsZ	tag_nameselementsr\   rZ   Ztag_namer,   r,   r-   rdoc   s    

rr   順 c           
      C   s$  t dt  t| }t dt|  dddgddfD ]z}d}z"t }t||}t }d}W n6 tk
r } zt d	|  t  W 5 d
}~X Y nX |r4t d||| f  q4ddl	m
} t }|| t }t d||   dd
l}	|	 }t }|| t }t d||   d
S )z.Very basic head-to-head performance benchmark.z1Comparative parser benchmark on Beautiful Soup %sz3Generated a large invalid HTML document (%d bytes).r
   r1   r	   r   FTr   Nz"BS4+%s parsed the markup in %.2fs.r   r   z$Raw lxml parsed the markup in %.2fs.z(Raw html5lib parsed the markup in %.2fs.)r   r   rr   lentimer   r"   r#   r$   r
   r   ZHTMLr	   r   parse)
rp   r%   r)   r*   ar+   rj   r'   r   r	   r,   r,   r-   benchmark_parsers   s4    


rx   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)Z
cumulativez_html5lib|bs42   N)tempfileNamedTemporaryFiler&   rr   dictry   cProfileZrunctxpstatsZStatsZ
sort_statsZprint_stats)rp   r)   Z
filehandlefilenamer%   varsstatsr,   r,   r-   profile   s    

r   __main__)T)rT   )r_   )rf   )rs   )rs   r
   )!rQ   __license__r~   ior   html.parserr   ry   r   r   Zbs4.builderr   r   r   rY   r{   ru   r#   r   r.   r<   r=   rS   rX   rW   r^   re   rr   rx   r   rN   stdinr   r,   r,   r,   r-   <module>   s8   G
&



 

