Ngl#dZddlZddlZddlmZddlmZmZmZm Z m Z m Z ddl m Z mZmZmZmZddlmZddlmZmZdd lmZmZdd lmZmZdd lmZdd lm Z m!Z!m"Z" d*dede"de#de#de ede$de ee$de#de%de$de#de e#de&d e&d!e&d"ed#df"d$Z' d+d&e!de#de ee$de$d'e&de#de ed#e#fd(Z( d,d&e!de#de ee$de$d'e&de ed#e efd)Z)dS)-zIFunctions that can be used for the most common use-cases for pdfminer.sixN)StringIO)AnyBinaryIO ContainerIteratorOptionalcast) XMLConverter HTMLConverter TextConverterPDFPageAggregator HOCRConverter) ImageWriter)LAParamsLTPage) PDFDevice TagExtractor)PDFResourceManagerPDFPageInterpreter)PDFPage) open_filename FileOrNameAnyIOtextutf-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$r4 stripcontrolhtml)r#r(r*r$r4hocr)r#r$r6tag)r#z1Output type can be text, html, xml or tag but is r%r'r3ih)logging getLoggersetLevelDEBUGrrsysstdoutbufferr r r rrr r ValueErrorrr get_pagesrotate process_pageclose)r r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r4rsrcmgrdevicemsg interpreterpages O/var/www/html/ai-engine/env/lib/python3.11/site-packages/pdfminer/high_level.pyextract_text_to_fprMs^ 4$$W]333K.!*--  _)<===G"&Ff#*!4!4 !f U%(         #&         !#       U%(      gtHe'<'>>"#3hGGG()96BB %  x(G     D  $ $T * * *&&((FLLLL                    sBCCC) rrNrNrrrrNFFF)rNrTrN)rNrTN)*__doc__r;r?iortypingrrrrrr converterr r r rrimagerrYrr pdfdevicerr pdfinterprrpdfpagerutilsrrrstrintfloatboolrMrUrZrNrLrisSOO EEEEEEEEEEEEEEEE$$$$$$$$........========3333333333 #'-1 $!oo o oo  o x o  o9S>*oo ooo oo oo !o" #ooooh-1#'((((((((9S>*(( ((  ((  ((x (( ((((((((Z-1#' !!!!9S>*! !  ! x !f!!!!!!rN