MfFdZdZddlZddlmZddlmZddlZddlmZm Z ddl m Z ddl Z ddl Z ddlZddlZddlZddlZddlZddlZdZdd ZGd d eZd ZdZdZddZddZddZddZd dZedkr$eej dSdS)!z=Diagnostic functions, mainly for use when doing tech support.MITN)BytesIO) HTMLParser) BeautifulSoup __version__)builder_registryc :tdtztdtjzgd}|D]C}tjD] }||jvrn(||td|zDd|vr|d ddl m }td d tt|jzn&#t$r}td Yd }~nd }~wwxYwd |vrC dd l}td|jzn&#t$r}tdYd }~nd }~wwxYwt#|dr|}|D]}td|zd} t'||} d}n<#t($r/}td|zt+jYd }~nd }~wwxYw|r3td|zt| tdd 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 %szPython version %s) html.parserhtml5liblxmlz;I noticed that %s is not installed. Installing it may help.r zlxml-xmlretreezFound lxml version %s.z.lxml is not installed or couldn't be imported.Nr zFound html5lib version %sz2html5lib is not installed or couldn't be imported.readz#Trying to parse your markup with %sF)featuresT%s could not parse the markup.z#Here's what %s did with the markup:zP--------------------------------------------------------------------------------)printrsysversionrbuildersrremoveappendr rjoinmapstr LXML_VERSION ImportErrorr hasattrrr Exception traceback print_excprettify) data basic_parsersnamebuilderrer parsersuccesssoups K/var/www/surfInsights/venv3-11/lib/python3.11/site-packages/bs4/diagnose.pydiagnoser,s  4{ BDDD  ,...777M'0  Gw'''(   & & & M   Z((( B " " " " " " *SXXc#e>P6Q6Q-R-RR T T T T B B B @ B B B B B B B B B ]"" F OOO .1EE G G G G F F F D F F F F F F F F FtVyy{{   4v=??? " 777DGG " " " 3f< > > >   ! ! ! ! ! ! ! ! "  % 86A C C C 4==?? $ $ $ x  sIAC C?&C::C?D## E-EEF G$%GGTc "ddlm}|dd}t|tr|d}t |}|j|f||d|D]'\}}t|d|j dd|j (d S) aPrint out the lxml events that occur during parsing. This lets you see how lxml parses a document when no Beautiful Soup code is running. You can use this to determine whether an lxml-specific problem is in Beautiful Soup's lxml tree builders or in lxml itself. :param data: Some markup. :param html: If True, markup will be parsed with lxml's HTML parser. if False, lxml's XML parser will be used. rr recoverTutf8)htmlr.z, z>4N) r rpop isinstancerencoder iterparsertagtext)r#r0kwargsrr.readereventelements r+ lxml_tracer;NsjjD))G$#{{6"" T]]F)%/7.4DDw w{{{{GLLACCCCDDcNeZdZdZdZdZdZdZdZdZ dZ d Z d Z 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$t|dS)N)r)selfss r+_pzAnnouncingParser._pls ar<c6|d|zdS)Nz%s STARTrB)r@r%attrss r+handle_starttagz AnnouncingParser.handle_starttagos  T!"""""r<c6|d|zdS)Nz%s ENDrDr@r%s r+ handle_endtagzAnnouncingParser.handle_endtagrs 4     r<c6|d|zdS)Nz%s DATArDr@r#s r+ handle_datazAnnouncingParser.handle_datau  D !!!!!r<c6|d|zdS)Nz %s CHARREFrDrHs r+handle_charrefzAnnouncingParser.handle_charrefx  t#$$$$$r<c6|d|zdS)Nz %s ENTITYREFrDrHs r+handle_entityrefz!AnnouncingParser.handle_entityref{s %&&&&&r<c6|d|zdS)Nz %s COMMENTrDrKs r+handle_commentzAnnouncingParser.handle_comment~rPr<c6|d|zdS)Nz%s DECLrDrKs r+ handle_declzAnnouncingParser.handle_declrMr<c6|d|zdS)Nz%s UNKNOWN-DECLrDrKs r+ unknown_declzAnnouncingParser.unknown_decls  !D()))))r<c6|d|zdS)Nz%s PIrDrKs r+ handle_pizAnnouncingParser.handle_pis $r<N)__name__ __module__ __qualname____doc__rBrFrIrLrOrRrTrVrXrZr<r+r>r>ds###!!!"""%%%'''%%%"""***     r<r>cLt}||dS)zPrint out the HTMLParser events that occur during parsing. This lets you see how HTMLParser parses a document when no Beautiful Soup code is running. :param data: Some markup. N)r>feed)r#r(s r+htmlparser_tracerbs'  F KKr<aeioubcdfghjklmnpqrstvwxyzcd}t|D]1}|dzdkrt}nt}|tj|z }2|S)z#Generate a random word-like string.r)range _consonants_vowelsrandomchoice)lengthrAits r+rwordrqsP A 6]] q5A::AAA V]1   Hr<cZddt|DS)z'Generate a random sentence-like string. c3ZK|]&}ttjddV'dS)rr N)rqrlrandint).0ros r+ zrsentence..s6FF1E&.1--..FFFFFFr<)rri)rns r+ rsentencerzs) 88FFf FFF F FFr<c gd}g}t|D]}tjdd}|dkr-tj|}|d|zJ|dkr6|t tjdd|dkr,tj|}|d|zd d |zd zS) z+Randomly generate an invalid HTML document.)pdivspanrobscripttablerz<%s>rrrhzz z)rirlrwrmrrzr) num_elements tag_nameselementsrormtag_names r+rdocrsAAAIH < 0 0!$$ Q;;}Y//H OOFX- . . . . q[[ OOIfnQq&9&9:: ; ; ; ; q[[}Y//H OOGh. / / / dii)) )I 55r<順cDtdtzt|}tdt|zdddgddfD]}d} t j}t ||}t j}d}n<#t $r/}td |ztjYd }~nd }~wwxYw|rtd |||z fzd d l m }t j}| |t j}td||z zd d l } | }t j}||t j}td||z zd S)z.Very basic head-to-head performance benchmark.z1Comparative parser benchmark on Beautiful Soup %sz3Generated a large invalid HTML document (%d bytes).r r0r r FTrNz"BS4+%s parsed the markup in %.2fs.rr z$Raw lxml parsed the markup in %.2fs.z(Raw html5lib parsed the markup in %.2fs.)rrrlentimerrr r!r rHTMLr rparse) rr#r(r)ar*rr'rr s r+benchmark_parsersrs > LNNN   D @3t99 LNNNFF+ZG J J " A v..D AGG " " " 3f< > > >   ! ! ! ! ! ! ! ! "  J 761Q3-G I I I A JJt A 1QqS 9;;;OOO  " "F A LL A 51 =?????s8B  C%CCr c2tj}|j}t|}t t ||}t jd|||tj |}| d| dddS)z7Use Python's profiler on a randomly generated document.)bs4r#r(zbs4.BeautifulSoup(data, parser) cumulativez _html5lib|bs42N) tempfileNamedTemporaryFiler%rdictrcProfilerunctxpstatsStats sort_stats print_stats)rr( filehandlefilenamer#varsstatss r+profilers,..JH   D Cd6 2 2 2D O5dHMMM L " "E \""" or*****r<__main__)T)re)rr)r{)r)rr )!r^ __license__rior html.parserrrrr bs4.builderrosrrlrrr rr,r;r>rbrkrjrqrzrrrr[stdinrr_r<r+rsCC """""" ********((((((   666pDDDD,$ $ $ $ $ z$ $ $ L    %      GGGG6666$@@@@@ + + + + z HSY^^  r<