TAiR&6SrSSKJr SSKrSSKrSSKJr SSKJ r SSK J r SSK J r SSK J r SS K Jr SS KJr SS KJr SS KJr S SKJr S SKJr S SKJr S SKJr S SKJr S SKJr S SKJr S SKJr S SKJr S SKJ r S SKJ!r! \\\\S.r""SS5r#g)z0Functions to handle all operations on the PDF's.) annotationsN)Path)Any)LTChar)LTImage)LTTextLineHorizontal)LTTextLineVertical) PdfReader) PdfWriter) StrByteType) TableList)Hybrid)Lattice)Network)Stream)TemporaryDirectory) download_url)get_image_char_and_text_objects)get_page_layout) get_rotation)is_url)latticestreamnetworkhybridc\rSrSrSrS S SjjrSrS SjrS SSjjrSSjr S r g) PDFHandler'a*Handles all operations on the PDF's. Handles all operations like temp directory creation, splitting file into single page PDFs, parsing each PDF and then removing the temp directory. Parameters ---------- filepath : str Filepath or URL of the PDF file. pages : str, optional (default: '1') Comma-separated page numbers. Example: '1,3,4' or '1,4-end' or 'all'. password : str, optional (default: None) Password for decryption. debug : bool, optional (default: False) Whether the parser should store debug information during parsing. Nc:X@l[U5(a[[U55nXl[ U[5(a/UR 5RS5(d [S5eUcSUl OX0l URU5Ul g)N.pdfzFile format not supported) debugrrstrfilepath isinstancelowerendswithNotImplementedErrorpassword _get_pagespages)selfr%r,r*r#s L/var/www/html/land-ocr/venv/lib/python3.13/site-packages/camelot/handlers.py__init__PDFHandler.__init__;sy (  #CM2H2: h $ $X^^-=-F-Fv-N-N%&AB B  DM$M__U+ c/nUS:XaURSSS.5 GO[URSS9nUR(aUR UR 5 US:Xa(URS[ UR5S.5 OURS5HnSU;aVURS5upVUS :Xa[ UR5nUR[U5[U5S.5 M_UR[U5[U5S.5 M /nUH'nUR[US US S-55 M) [[U55$) a!Convert pages string to list of integers. Parameters ---------- filepath : str Filepath or URL of the PDF file. pages : str, optional (default: '1') Comma-separated page numbers. Example: '1,3,4' or '1,4-end' or 'all'. Returns ------- P : list List of int page numbers. 1r )startendFstrictall,-r5r4)appendr r% is_encrypteddecryptr*lenr,splitintextendrangesortedset) r-r, page_numbersinfilerabresultps r.r+PDFHandler._get_pagesPs"" C<   !A 6 7t}}U;F""t}}-~##aFLL8I$JKS)Aax wws|: #FLL 1A$++c!fSV,LM$++c!fSV,LM*A MM%' AeHqL9 :c&k""r1c [USS9nUR(aURUR5 [R R USUS35n[R RU5upxURUS- n [5n U RU 5 [US5n U RU 5 SSS5 [U40UD6up[U 5upnn[UUU5nUS:wGa/SR UR!S S 5S U/5n[R""UU5 [US 5n[USS9nUR(aURUR5 [5n URS n US:XaU R%S5 OUS:XaU R%S5 U RU 5 [US5n U RU 5 SSS5 [U40UD6up[U 5upnnUR'5 XXUU4$XXUU4$!,(df  GNu=f!,(df  NY=f)aSaves specified page from PDF into a temporary directory. Parameters ---------- filepath : str Filepath or URL of the PDF file. page : int Page number. temp : str Tmp directory. Returns ------- layout : object dimensions : tuple The dimensions of the pdf page filepath : str The path of the single page PDF - either the original, or a normalized version. Fr6page-r!r wbNr"pagerK_rotatedrbr anticlockwiseZ clockwisei)r r<r=r*ospathjoinsplitextr,r add_pageopenwriterrrreplacerenamerotateclose)r-r%rPtemp layout_kwargsrFfpathfrootfextrKoutfileflayout dimensionsimagescharshorizontal_text vertical_textrotation fpath_newinstreams r. _save_pagePDFHandler._save_page|sD8E2    NN4== ) TU4&#56gg&&u-  LL "+ % ! MM! ,UDmD8W 9 5   F r>vs!;Z NOI IIeY 'It,Hx6F""t}}-kG QA?* [(   Q eT"a a #"1!H-!H F/7 :F?M NN vo}T T6/=PP? ,#"s5H5"I5 I Ic Uc0n/n[UnU"SSUR0UD6n[5n [R"5n U(a[ UR 5S:aU S:a[R"S5RU S9n /n UR H3n U RURXXU45nU RU5 M5 U H$nUR5nURU5 M& SSS5 O7UR H'n URXXU5nURU5 M) SSS5 [[U55$!,(df  N*=f!,(df  N3=f)aExtract tables by calling parser.get_tables on all single page PDFs. Parameters ---------- flavor : str (default: 'lattice') The parsing method to use. Lattice is used by default. suppress_stdout : bool (default: False) Suppress logs and warnings. parallel : bool (default: False) Process pages in parallel using all available cpu cores. layout_kwargs : dict, optional (default: {}) A dict of `pdfminer.layout.LAParams `_ kwargs. kwargs : dict See camelot.read_pdf kwargs. Returns ------- tables : camelot.core.TableList List of tables found in PDF. Nr#r spawn) processes)PARSERSr#rmp cpu_countr>r, get_contextPool apply_async _parse_pager;getrArrC)r-flavorsuppress_stdoutparallelrbkwargstables parser_objparsertempdirrypooljobsrKjts r.parsePDFHandler.parsesI>  MV_ 7$**77  !W IC Oa/IM^^G,11I1F$D!ZZ ,, ,,-P A ("EEG a("GFA((F]AMM!$ $%"0(('GF " !s&AE+A0E>AE+ E( $E++ E9c UR"URX40UD6upgpp[RR USUS35n UR U UUUUU U US9 UR 5n U $)aExtract tables by calling parser.get_tables on a single page PDF. Parameters ---------- page : int Page number to parse parser : Lattice, Stream, Network or Hybrid The parser to use. suppress_stdout : bool Suppress logs and warnings. layout_kwargs : dict, optional (default: {}) A dict of `pdfminer.layout.LAParams `_ kwargs. Returns ------- tables : camelot.core.TableList List of tables found in PDF. rNr!)rb)rqr%rVrWrXprepare_page_parseextract_tables)r-rPrrrrbrhrirjrkrlrm page_pathrs r.r}PDFHandler._parse_pages0 OODMM4 JM J JF?GGLLE$t*<= !!       ' " &&( r1)r#r%r,r*)r3NF)r%zStrByteType | Path | str)r%zStrByteType | PathrPr@rar$returnzrtuple[Any, tuple[float, float], list[LTImage], list[LTChar], list[LTTextLineHorizontal], list[LTTextLineVertical]])rFFN)rr$rboolrrrbzdict[str, Any] | None)rPr@rr$rr) __name__ __module__ __qualname____firstlineno____doc__r/r+rqrr}__static_attributes__rvr1r.rr's, ,*,**#XIQ*IQ25IQ=@IQ IQZ %/3 ?)?)?) ?) - ?)B&&"%&@D&r1r)$r __future__rmultiprocessingrxrVpathlibrtypingrpdfminer.layoutrrrr pypdfr r pypdf._utilsr corerparsersrrrrutilsrrrrrrrwrrvr1r.rsn6" "#0.$%2"  GGr1