;3hg#dZddlZddlZddlmZddlmZmZmZm Z m Z m Z ddl m Z mZmZmZmZddlmZddlmZmZddlmZmZdd lmZdd lmZmZdd lm Z dd l!m"Z"m#Z#m$Z$ d#d ede"de%de%de ede&de ee&de%de'de&de%de e%de(de(de(deddf"dZ) d$de#de%de ee&de&d e(de%de ede%fd!Z* d%de#de%de ee&de&d e(de ede efd"Z+y)&zIFunctions that can be used for the most common use-cases for pdfminer.sixN)StringIO)AnyBinaryIO ContainerIteratorOptionalcast) HOCRConverter HTMLConverterPDFPageAggregator TextConverter XMLConverter) ImageWriter)LAParamsLTPage) PDFDevice TagExtractor) PDFValueError)PDFPageInterpreterPDFResourceManager)PDFPage)AnyIO FileOrName open_filenameinfoutfp output_typecodeclaparamsmaxpages page_numberspasswordscalerotation layoutmode output_dir strip_controldebugdisable_cachingkwargsreturnc | r1tjjtjd}| r t | }t | }d}|dk7r-|t jk(rt jj}|dk(rt|||||}nw|dk(rt|||||| }n`|dk(rt||||| ||}nH|d k(rt||||| }n2|d k(rt|tt|| }nd |}t!||Jt#||}t%j&||||| D]*}|j(| zdz|_|j+|,|j-y)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. Ncachingtext)rr imagewriterxml)rrr0 stripcontrolhtml)rr#r%rr0hocr)rrr2tag)rz1Output type can be text, html, xml or tag but is r r"r.ih)logging getLoggersetLevelDEBUGrrsysstdoutbufferr rr r rr rrrr get_pagesrotate process_pageclose)rrrrrr r!r"r#r$r%r&r'r(r)r*r0rsrcmgrdevicemsg interpreterpages S/var/www/html/audio-gradio/venv/lib/python3.12/site-packages/pdfminer/high_level.pyextract_text_to_fprHs^ $$W]]3K!*-  _)<=G"&Ff#**!4 !!f  #      #&      !#     &    gtHe'r@getvalue) rJr"r!r r.rrfp output_stringrBrCrErFs rG extract_textrPs,: x &("hj(M (B $W5w UXV(&9 %%     +D  $ $T * +%%'(((((((s# CA7B. C.B7 3CC c#ZK| t}t|d5}tt|}t |}t ||}t ||} tj|||||D]'} | j| |j} | ) dddy#1swYyxYww)aExtract and yield LTPage objects :param pdf_file: Either a file path or a file-like object for the PDF file to be worked on. :param password: For encrypted PDFs, the password to decrypt. :param page_numbers: List of zero-indexed page numbers to extract. :param maxpages: The maximum number of pages to parse :param caching: If resources should be cached :param laparams: An LAParams object from pdfminer.layout. If None, uses some default settings that often work well. :return: LTPage objects NrLr-)rr6) rrr rrr rrr>r@ get_result) rJr"r!r r.rrNresource_managerrCrErFlayouts rG extract_pagesrUs(: x &" (B -g>"#3hG()96B %%    D  $ $T *&&(FL  sB+A:B B+B($B+) r/utf-8NrNg?rnormalNFFF)rWNrTrVN)rWNrTN),__doc__r7r;iortypingrrrrrr pdfminer.converterr r r r rpdfminer.imagerpdfminer.layoutrrpdfminer.pdfdevicerrpdfminer.pdfexceptionsrpdfminer.pdfinterprrpdfminer.pdfpagerpdfminer.utilsrrrstrintfloatboolrHrPrUrIrGrisO EE',60E$;; #'-1 $!w w ww  w x w  w9S>*ww www ww ww !w" #wx-1#'((((((9S>*(( ((  ((  ((x (( ((Z-1#' %%%9S>*% %  % x %f%rI