vlj ddlZddlZddlmZmZddlmZmZmZddl m Z ddl m Z m Z mZddlmZmZddlmZddlmZmZmZmZdd lmZdd lmZmZej<eZ ed Z!ed Z"Gd dZ#y)N) ContainerIterator)AnyBinaryIOClassVar)settings) PDFDocumentPDFNoPageLabelsPDFTextExtractionNotAllowed)PDFObjectNotFound PDFValueError) PDFParser) dict_value int_value list_valueresolve1)LIT)Rect parse_rectPagePagesceZdZUdZdededededzddf dZdefd Zhd Z e e ee d <e d ededfd Ze ddedeedzdedededededfdZdedefdZdededefdZdedeefdZy)PDFPageazAn object that holds the information about a page. A PDFPage object is merely a convenience class that has a set of keys and values, which describe the properties of a page and point to its contents. Attributes ---------- doc: a PDFDocument object. pageid: any Python object that can uniquely identify the page. attrs: a dictionary of page attributes. contents: a list of PDFStream objects that represents the page content. lastmod: the last modified time of the page. resources: a dictionary of resources used by the page. mediabox: the physical size of the page. cropbox: the crop rectangle of the page. rotate: the page rotation (in degree). annots: the page annotations. beads: a chain that represents natural reading order. label: the page's label (typically, the logical page number). docpageidattrslabelNreturnc||_||_t||_||_t |jj d|_t |jj di|_|j|jj d|_ |j|jj d|j|_ |j|jj d|_t|jj dddzdz|_|jj d |_|jj d |_y ) zInitialize a page object. doc: a PDFDocument object. pageid: any Python object that can uniquely identify the page. attrs: a dictionary of page attributes. label: page label string. LastModified ResourcesMediaBoxCropBoxContentsRotaterihAnnotsBN)rrrrrrgetlastmod resources_parse_mediaboxmediabox_parse_cropboxcropbox_parse_contentscontentsrrotateannotsbeads)selfrrrrs F/var/www/html/pp/venv/lib/python3.12/site-packages/pdfminer/pdfpage.py__init__zPDFPage.__init__1s &   ~ >? /7 JJNN; +0 ,,TZZ^^J-GH **4::>>)+DdmmT ,,TZZ^^J-GH  !!<=CsJ jjnnX. ZZ^^C( c<d|jd|jdS)Nz)r*r,)r4s r5__repr__zPDFPage.__repr__Ps"%dnn%7{4==BSSTUUr7>r%r#r"r!INHERITABLE_ATTRSdocumentc# K d dtdtttfdttdzdtt t tttttffff fd j}d}djvrB jdj}|D]\}}||t|d}|svjD]f}|jD]Q} j|}t!|tr-|j#d t$ur||t|Shyy#t$rtjd}YwxYw#t&$rYwxYww) Nobjparentvisitedrc3Kt|tr+|}t j|j }n%|j }t|j }| t }||vry|j||jD]\}}| jvs||vs|||< |jd}|!tjs|jd}|turCd|vr?tjd|dt!|dD]} |||Ed{y|t"urtjd|||fyy7-w)NTypetypeKidszPages: Kids=%rzPage: %r) isinstanceintrgetobjcopyobjidsetadditemsr;r(rSTRICT LITERAL_PAGESlogdebugr LITERAL_PAGE) r>r?r@ object_idobject_propertieskv object_typechildclsdepth_first_searchr<s r5rYz0PDFPage.create_pages..depth_first_search\sd #s# $.xy/I$J$O$O$Q! II $.sO$8$8$:!%G# KK "  -1---!;L2L+,%a( -,//7K"8??/33F; m+:K0K *,=f,EF'(9&(ABUE1%9JGTTTU , *&78 "344-UsB'E+E0A>E.E/.EFrTrBN)rdictstrrJrtuplerFget_page_labelsr itertoolsrepeatcatalognextxrefs get_objidsrGrEr(rQr ) rXr< page_labelspagesobjectsrItreexrefr>rYs `` @r5 create_pageszPDFPage.create_pagesZs (,$ 5$ 5cN$ 5X_$ 5eCc4S>&9!::; < $ 5L 1080H0H0JK h&& &()9)9')BHDTDTUG&  t(E4k1BCC   !__.E&ooe4%c40SWWV_ 5T"%hsDA6E<5AE-E< E*'E<)E**E<- E96E<8E99E<fppagenosmaxpagespasswordcachingcheck_extractablec#$Kt|}t|||}|js-|rd|} t| d|d} tj | t |j|D]\} } |r| |vr | |s|| dzksyyw)N)rnroz Text extraction is not allowed: zThe PDF z contains a metadata field indicating that it should not allow text extraction. Ignoring this field and proceeding. Use the check_extractable if you want to raise an error in this case)rr is_extractabler rOwarning enumeraterj) rXrkrlrmrnrorpparserr error_msg warning_msgpagenopages r5 get_pageszPDFPage.get_pagess2&8WE!! >rfE 1)<<rf%AA K(%c&6&6s&;< LFDF'1JH 2  sBBB Bvaluecd}|tjd|S tdt|DS#t$rtjd|cYSwxYw)N)r~g @g@zHMediaBox missing from /Page (and not inherited), defaulting to US Letterc32K|]}t|ywrZr.0vals r5 z*PDFPage._parse_mediabox..GhsmGz2Invalid MediaBox in /Page, defaulting to US Letter)rOrtrrr )r4r| us_letters r5r+zPDFPage._parse_mediaboxsa, = KK*   GxGG G  KKL M  s8 AAr,c||S tdt|DS#t$rtj d|cYSwxYw)Nc32K|]}t|ywrZrrs r5rz)PDFPage._parse_cropbox..rrz0Invalid CropBox in /Page, defaulting to MediaBox)rrr rOrt)r4r|r,s r5r-zPDFPage._parse_cropboxsG =O GxGG G  KKJ KO s! AAcJg}|t|}t|ts|g}|SrZ)rrElist)r4r|r0s r5r/zPDFPage._parse_contentss,   Hh-$:r7)NrTF)__name__ __module__ __qualname____doc__r objectr\r6r:r;rrJ__annotations__ classmethodrrjrrrFboolr{rrr+r-rr/r7r5rrsJ.) )) ) Tz )  )>V#V-xC);K;HY4G;;z*."'" "3$&" "  "  " " ) ""HST" C 4 D ST#Yr7r)$r_loggingcollections.abcrrtypingrrrpdfminerrpdfminer.pdfdocumentr r r pdfminer.pdfexceptionsr r pdfminer.pdfparserrpdfminer.pdftypesrrrrpdfminer.psparserrpdfminer.utilsrr getLoggerrrOrQrNrrr7r5rsh/** D(II!+g!6{ G GGr7