#j`#dZddlZddlZddlmZmZddlmZddlm Z m Z m Z ddl m Z mZmZmZmZddlmZddlmZmZdd lmZmZdd lmZdd lmZmZdd lm Z dd l!m"Z"m#Z#m$Z$ d+de de"de%de%dedzde&dee&dzde%de'de&de%de%dzd e(d!e(d"e(d#e d$df"d%Z) d,d'e#de%dee&dzde&d(e(de%dedzd$e%fd)Z* d-d'e#de%dee&dzde&d(e(dedzd$eefd*Z+dS).zIFunctions that can be used for the most common use-cases for pdfminer.sixN) ContainerIterator)StringIO)AnyBinaryIOcast) HOCRConverter HTMLConverterPDFPageAggregator TextConverter XMLConverter) ImageWriter)LAParamsLTPage) PDFDevice TagExtractor) PDFValueError)PDFPageInterpreterPDFResourceManager)PDFPage)AnyIO FileOrName open_filenametextutf-8?normalFinfoutfp output_typecodeclaparamsmaxpages page_numberspasswordscalerotation layoutmode output_dir strip_controldebugdisable_cachingkwargsreturnc :| r0tjtjd}| rt | }t | }d}|dkr!|t jkrt jj}|dkrt|||||}n|dkrt|||||| }nx|dkrt||||| ||}n[|d krt||||| }n@|d kr&t|tt|| }nd |}t!||Jt#||}t%j||||| D])}|j| zdz|_||*|dS)akParses text from inf-file and writes to outfp file-like object. Takes loads of optional arguments but the defaults are somewhat sane. Beware laparams: Including an empty LAParams is not the same as passing None! :param inf: a file-like object to read PDF structure from, such as a file handler (using the builtin `open()` function) or a `BytesIO`. :param outfp: a file-like object to write the text to. :param output_type: May be 'text', 'xml', 'html', 'hocr', 'tag'. Only 'text' works properly. :param codec: Text decoding codec :param laparams: An LAParams object from pdfminer.layout. Default is None but may not layout correctly. :param maxpages: How many pages to stop parsing after :param page_numbers: zero-indexed page numbers to operate on. :param password: For encrypted PDFs, the password to decrypt. :param scale: Scale factor :param rotation: Rotation factor :param layoutmode: Default is 'normal', see pdfminer.converter.HTMLConverter :param output_dir: If given, creates an ImageWriter for extracted images. :param strip_control: Does what it says on the tin :param debug: Output more logging data :param disable_caching: Does what it says on the tin :param other: :return: nothing, acting as it does on two streams. Use StringIO to get strings. Ncachingr)r"r# imagewriterxml)r"r#r3 stripcontrolhtml)r"r'r)r#r3hocr)r"r#r5tag)r"z1Output type can be text, html, xml or tag but is r$r&r2ih)logging getLoggersetLevelDEBUGrrsysstdoutbufferr r r r rrrrrr get_pagesrotate process_pageclose)rr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r3rsrcmgrdevicemsg interpreterpages [/home/rurouni/.hermes/hermes-agent/venv/lib/python3.11/site-packages/pdfminer/high_level.pyextract_text_to_fprKs$^ 4$$W]333K.!*--  _)<===G#Ff#*!4!4 !f  #         #&         !#        &       gtHe'<'>>"#3hGGG()96BB %       D  $ $T * * *&&((FLLLL  sBCCC) rrNrNrrrrNFFF)rNrTrN)rNrTN),__doc__r:r>collections.abcrriortypingrrrpdfminer.converterr r r r r pdfminer.imagerpdfminer.layoutrrpdfminer.pdfdevicerrpdfminer.pdfexceptionsrpdfminer.pdfinterprrpdfminer.pdfpagerpdfminer.utilsrrrstrintfloatboolrKrSrXrLrJrjshOO ////////&&&&&&&&&&'&&&&&,,,,,,,,66666666000000EEEEEEEE$$$$$$;;;;;;;;;;  $*.!!ww w ww  w o w  wC.4'ww wwwd ww ww !w" #wwwwx*. $((((((((C.4'(( ((  ((  ((o(( ((((((((Z*. $ %%%%C.4'% %  % o %f%%%%%%rL