B
    5d                 @   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   s  t dt  t dtj  dddg}x>|D ]6}x0tjD ]}||jkr6P q6W || t d|  q*W d|kr|d y*dd	l	m
} t d
dtt|j  W n* tk
r } zt d W dd}~X Y nX d|kryddl}t d|j  W n, tk
r } zt d W dd}~X Y nX t| dr2|  } x|D ]}t d|  d}yt| |d}	d}W n8 tk
r } zt d|  t  W dd}~X Y nX |rt d|  t |	  t d q8W d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 %sz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#Trying to parse your markup with %sF)featuresTz%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   r   	Exception	traceback	print_excZprettify)
dataZbasic_parsersnamebuilderr
   er   parsersuccesssoup r"   0/tmp/pip-unpacked-wheel-2xr6_e3g/bs4/diagnose.pydiagnose   sR    






r$   Tc             K   st   ddl m} |dd}t| tr,| d} t| }x:|j|f||d|D ]\}}td||j	|j
f  qNW 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)htmlr%   z%s, %4s, %sN)r	   r
   pop
isinstancer   encoder   	iterparser   tagtext)r   r'   kwargsr
   r%   readereventelementr"   r"   r#   
lxml_traceN   s    

r2   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#   _pl   s    zAnnouncingParser._pc             C   s   |  d|  d S )Nz%s START)r6   )r4   r   attrsr"   r"   r#   handle_starttago   s    z AnnouncingParser.handle_starttagc             C   s   |  d|  d S )Nz%s END)r6   )r4   r   r"   r"   r#   handle_endtagr   s    zAnnouncingParser.handle_endtagc             C   s   |  d|  d S )Nz%s DATA)r6   )r4   r   r"   r"   r#   handle_datau   s    zAnnouncingParser.handle_datac             C   s   |  d|  d S )Nz
%s CHARREF)r6   )r4   r   r"   r"   r#   handle_charrefx   s    zAnnouncingParser.handle_charrefc             C   s   |  d|  d S )Nz%s ENTITYREF)r6   )r4   r   r"   r"   r#   handle_entityref{   s    z!AnnouncingParser.handle_entityrefc             C   s   |  d|  d S )Nz
%s COMMENT)r6   )r4   r   r"   r"   r#   handle_comment~   s    zAnnouncingParser.handle_commentc             C   s   |  d|  d S )Nz%s DECL)r6   )r4   r   r"   r"   r#   handle_decl   s    zAnnouncingParser.handle_declc             C   s   |  d|  d S )Nz%s UNKNOWN-DECL)r6   )r4   r   r"   r"   r#   unknown_decl   s    zAnnouncingParser.unknown_declc             C   s   |  d|  d S )Nz%s PI)r6   )r4   r   r"   r"   r#   	handle_pi   s    zAnnouncingParser.handle_piN)__name__
__module____qualname____doc__r6   r8   r9   r:   r;   r<   r=   r>   r?   r@   r"   r"   r"   r#   r3   d   s   r3   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)r3   feed)r   r   r"   r"   r#   htmlparser_trace   s    rF   ZaeiouZbcdfghjklmnpqrstvwxyz   c             C   s>   d}x4t | D ](}|d dkr$t}nt}|t|7 }qW |S )z#Generate a random word-like string.    r   )range_consonants_vowelsrandomchoice)lengthr5   itr"   r"   r#   rword   s    rR      c             C   s   d dd t| D S )z'Generate a random sentence-like string. c             s   s   | ]}t td dV  qdS )rS   	   N)rR   rM   randint).0rP   r"   r"   r#   	<genexpr>   s    zrsentence.<locals>.<genexpr>)r   rJ   )rO   r"   r"   r#   	rsentence   s    rY     c             C   s   dddddddg}g }x~t | D ]r}tdd	}|dkrRt|}|d
|  q |dkrr|ttdd q |dkr t|}|d|  q W dd| d S )z+Randomly generate an invalid HTML document.pdivspanrP   bscripttabler      z<%s>   rS   rI   z</%s>z<html>
z</html>)rJ   rM   rV   rN   r   rY   r   )num_elementsZ	tag_nameselementsrP   rN   Ztag_namer"   r"   r#   rdoc   s    

rf   順 c       
      C   s(  t dt  t| }t dt|  xdddgddgD ]z}d}y"t }t||}t }d}W n6 tk
r } zt d	|  t  W d
d
}~X Y nX |r6t d||| f  q6W ddl	m
} t }|| t }t d||   dd
l}	|	 }t }|| t }t d||   d
S )z.Very basic head-to-head performance benchmark.z1Comparative parser benchmark on Beautiful Soup %sz3Generated a large invalid HTML document (%d bytes).r	   r'   r   zhtml.parserFTz%s could not parse the markup.Nz"BS4+%s parsed the markup in %.2fs.r   )r
   z$Raw lxml parsed the markup in %.2fs.z(Raw html5lib parsed the markup in %.2fs.)r   r   rf   lentimer   r   r   r   r	   r
   ZHTMLr   r   parse)
rd   r   r   r    ar!   r^   r   r
   r   r"   r"   r#   benchmark_parsers   s4    


rl   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   rf   dictrm   cProfileZrunctxpstatsZStatsZ
sort_statsZprint_stats)rd   r   Z
filehandlefilenamer   varsstatsr"   r"   r#   profile   s    

rw   __main__)T)rG   )rS   )rZ   )rg   )rg   r	   )!rD   __license__rr   ior   html.parserr   rm   r   r   Zbs4.builderr   osrs   rM   ro   ri   r   r   r$   r2   r3   rF   rL   rK   rR   rY   rf   rl   rw   rA   stdinr   r"   r"   r"   r#   <module>   s8   8
&



 

