�
�?J[c@so
dZd
Z
ddlZddlmZ
ddlmZ
ddlZddlmZmZ
ddlm	Z	
ddl
Z
ddlZddlZddl
Z
ddlZddlZddlZddlZd�Zed	�
Zd
ef
d��YZd�Zd
ZdZdd�
Zdd�
Zdd�
Zdd�
Zddd�Zedkrk
eejj��

ndS(s=Diagnostic functions, mainly for use when doing tech support.tMITi����N(
tStringIO(
t
HTMLParser(t
BeautifulSoupt__version__(
tbuilder_registryc
CsVd
tGHdt
jGHdddg}
xK|
D]C}x:tjD]}||jkr;Pq;q;W|
j|�

d|GHq+Wd|
kr�|
jd�

y2dd	lm	}
d
dj
tt|j
��
GHWq�tk
r�
}
dGHq�Xnd|
kr!
ydd
l}d|jGHWq!
tk
r

}
dGHq!
Xnt|d�r?
|j�}n�|jd�
s]
|jd�
ro
d|GHdGHd
SyCtjj|�
r�
d|GHt|�
�}|j�}Wd
QXnWntk
r�



n
XHx�|
D]�}d|GHt}	yt|d|�

}
t}	Wn&tk
r'
}
d|GHtj�
n
X|	rEd|GH|
j�GHnddGHq�
Wd
S(s/Diagnostic suite for isolating common problems.s'Diagnostic running on Beautiful Soup %ssPython version %sshtml.parserthtml5libtlxmls;I noticed that %s is not installed. Installing it may help.slxml-xmli����(
tetreesFound lxml version %st
.s.lxml is not installed or couldn't be imported.NsFound html5lib version %ss2html5lib is not installed or couldn't be imported.treadshttp:shttps:s<"%s" looks like a URL. Beautiful Soup is not an HTTP client.spYou need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.s7"%s" looks like a filename. Reading data from the file.s#Trying to parse your markup with %stfeaturess%s could not parse the markup.s#Here's what %s did with the markup:t
-iP(RtsystversionRtbuildersRtremovetappendRRtjointmaptstrtLXML_VERSIONtImportErrorRthasattrR
t
startswithtostpathtexiststopent
ValueErrortFalseRtTruet	Exceptiont	tracebackt	print_exctprettify(tdatat
basic_parserstnametbuilderRt
eRtfptparsertsuccesstsoup((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pytdiagnosesd	













"







	



	







	






	


	
cKs[d
dlm
}
xD|jt|�
d|
|�

D]$\}}d||j|jfGHq/WdS(s�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.
    i����(
Rthtmls%s, %4s, %sN(RRt	iterparseR
ttagttext(R$R.tkwargsRteventtelement((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pyt
lxml_traceZs
+
tAnnouncingParserc
BsheZ
dZd
�Zd�Zd�Zd�Zd�Zd�Zd�Z	d�Z
d	�Zd
�ZRS(s?Announces HTMLParser parse events, without doing anything else.c
Cs	|
GHdS(
N((tselft
s((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pyt_pgs
cCs|jd
|
�

dS(Ns%s START(
R9(R7R&tattrs((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pythandle_starttagjs
cCs|jd
|
�

dS(Ns%s END(
R9(R7R&((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pyt
handle_endtagms
cCs|jd
|
�

dS(Ns%s DATA(
R9(R7R$((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pythandle_dataps
cCs|jd
|
�

dS(Ns
%s CHARREF(
R9(R7R&((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pythandle_charrefss
cCs|jd
|
�

dS(Ns%s ENTITYREF(
R9(R7R&((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pythandle_entityrefvs
cCs|jd
|
�

dS(Ns
%s COMMENT(
R9(R7R$((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pythandle_commentys
cCs|jd
|
�

dS(Ns%s DECL(
R9(R7R$((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pythandle_decl|s
cCs|jd
|
�

dS(Ns%s UNKNOWN-DECL(
R9(R7R$((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pytunknown_decls
cCs|jd
|
�

dS(Ns%s PI(
R9(R7R$((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pyt	handle_pi�s
(
t__name__t
__module__t__doc__R9R;R<R=R>R?R@RARBRC(((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pyR6ds
									c
Cst�}
|
j
|�

d
S(s�Print out the HTMLParser events that occur during parsing.

    This lets you see how HTMLParser parses a document when no
    Beautiful Soup code is running.
    N(R6tfeed(R$R*((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pythtmlparser_trace�s	
taeioutbcdfghjklmnpqrstvwxyzic
CsSd
}
xFt|�
D]8}|ddkr2t
}nt}|
tj|�
7}
qW|
S(s#Generate a random word-like string.tii(tranget_consonantst_vowelstrandomtchoice(tlengthR8t
it
t((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pytrword�s


	

ic

Csd
jd�t
|�
D�
�
S(s'Generate a random sentence-like string.t
 c
ss'|]}
tt
jdd
��
V
qdS(ii	N(RTROtrandint(t.0RR((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pys	<genexpr>�s(RRL(
RQ((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pyt	rsentence�si�c
Cs�d
ddddddg}
g}x�t|�
D]�}t
jdd	�}|dkrut
j|
�
}|jd
|�

q.|dkr�|jtt
jdd��
�

q.|d
kr.t
j|
�
}|jd|�

q.q.Wddj|�
dS(s+Randomly generate an invalid HTML document.t
ptdivtspanRRt
btscriptttableiis<%s>i
iis</%s>s<html>s

s</html>(RLRORVRPRRXR(tnum_elementst	tag_namestelementsRRRPttag_name((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pytrdoc�s






"


i��
c

CsS
d
tGHt
|�
}
dt|
�
GHx�dddgddgD]�}t}y1tj�}t|
|�}tj�}t}Wn&tk
r�
}
d|GHtj	�
n
X|r=d|||fGHq=q=Wd	d
l
m}
tj�}|j|
�

tj�}d||GHd	dl
}	|	j�}tj�}|j|
�

tj�}d
||GHdS(s.Very basic head-to-head performance benchmark.s1Comparative parser benchmark on Beautiful Soup %ss3Generated a large invalid HTML document (%d bytes).RR.Rshtml.parsers%s could not parse the markup.s"BS4+%s parsed the markup in %.2fs.i����(
Rs$Raw lxml parsed the markup in %.2fs.Ns(Raw html5lib parsed the markup in %.2fs.(RRctlenRttimeRRR R!R"RRtHTMLRRtparse(
R_R$R*R+t
aR,R\R(RR((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pytbenchmark_parsers�s4	










	














RcCs�tj
�}|j}t|�
}td
td|d|
�}tjd|||�
tj	|�
}|j
d�

|jdd�
dS(Ntbs4R$R*sbs4.BeautifulSoup(data, parser)t
cumulatives
_html5lib|bs4i2(ttempfiletNamedTemporaryFileR&RctdictRjtcProfiletrunctxtpstatstStatst
sort_statstprint_stats(R_R*t
filehandletfilenameR$tvarststats((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pytprofile�s
	



t__main__( RFt__license__RoR
RRjRRtbs4.builderRRRqRORlReR!R
R-RR5R6RHRNRMRTRXRcRiRyRDtstdinR
(((s0/usr/lib/python2.7/site-packages/bs4/diagnose.pyt<module>
s8











	C
!