:QgvddlZddlZddlmZmZddlmZddlmZm Z ddl m Z m Z m Z mZmZmZGddeZy) N) PdfFileReader PdfFileWriter) TableList)StreamLattice)TemporaryDirectoryget_page_layoutget_text_objects get_rotationis_url download_urlc2eZdZdZd dZdZdZddifdZy) PDFHandleraHandles 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. Ncbt|r t|}||_|jj ds t d|d|_n=||_tjddkr |j jd|_|j|j||_ y)N.pdfzFile format not supportedrascii) r rfilepathlowerendswithNotImplementedErrorpasswordsys version_infoencode _get_pagespages)selfrrrs M/var/www/html/answerous/venv/lib/python3.12/site-packages/camelot/handlers.py__init__zPDFHandler.__init__%s ( #H-H  ~~((0%&AB B  DM$DM"Q& $ 4 4W = __T]]E: cg}|dk(r|jdddnt|d}t|d}|jr|j |j |dk(r#|jd|j dn|jdD]|}d |vrP|jd \}}|d k(r|j }|jt|t|dW|jt|t|d~|jg} |D]&} | jt| d | d dz(tt| S) a~Converts pages string to list of ints. 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)startendrbFstrictall,-r'r&)appendopenr isEncrypteddecryptr getNumPagessplitintcloseextendrangesortedset) r rr page_numbersinstreaminfilerabPps r!rzPDFHandler._get_pages4sA" C<   !A 6 7Hd+H"8E:F!!t}}-~##a8J8J8L$MNS)NAax wws|1: & 2 2 4A$++c!fSV,LM$++c!fSV,LMN NN   6A HHU1W:qx!|4 5 6c!f~r#ct|d5}t|d}|jr|j|jt j j|d|d}t j j|\}}|j|dz } t} | j| t|d5} | j| dddt|\} } t| d }t| d }t| d }t|||}|d k7r d j|j!ddd|g}t j"||t|d}t|d}|jr|j|jt} |jd} |dk(r| j%dn|dk(r| j'd| j| t|d5} | j| ddd|j)dddy#1swYdxYw#1swY/xYw#1swYyxYw)aSaves specified page from PDF into a temporary directory. Parameters ---------- filepath : str Filepath or URL of the PDF file. page : int Page number. temp : str Tmp directory. r(Fr)page-rrwbNchar)ltypehorizontal_text vertical_textrpagerA_rotatedr anticlockwiseZ clockwise)r/rr0r1rospathjoinsplitextgetPageraddPagewriter r r replacerenamerotateClockwiserotateCounterClockwiser5)r rrItempfileobjr<fpathfrootfextrAoutfileflayoutdimcharsrGrHrotation fpath_newr;s r! _save_pagezPDFHandler._save_page^s(D !! !W"759F!!t}}-GGLLtfD'9:E''**51KE4tax(A#oG OOA eT" !a a  !)%0KFC$V6:E.v=NOO,V?KM#E?MJH2~GGU]]63%?T$RS  %+ 40&x>%%NN4==1'/NN1%.%%b),,,R0"%&%!MM!$% C! !! ! ! !,%%?! !! !s=B6IH7D/III7I <II IIlatticeFc g}t5}|jD]}|j|j||!|jDcgc]&}tj j |d|d(}}|dk(r tdi|n tdi|} |D]'}| j|||} |j| ) dddtt|Scc}w#1swY"xYw)aExtracts tables by calling parser.get_tables on all single page PDFs. Parameters ---------- flavor : str (default: 'lattice') The parsing method to use ('lattice' or 'stream'). Lattice is used by default. suppress_stdout : str (default: False) Suppress logs and warnings. 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. rCrrf)suppress_stdout layout_kwargsN) r rrerrNrOrPrrextract_tablesr6rr8) r flavorrhrikwargstablestempdirrArparserts r!parsezPDFHandler.parses0  ! !WZZ ; q': ;EIZZPRWW\\'U1#T?;PEP*0I*=W&v&6CSFCSF !))m* a  ! !((Q ! !s=C  +C5A C C  C))r%N)__name__ __module__ __qualname____doc__r"rrerrrjr#r!rrs& ;(T.!bR#)r#r)rNrPyPDF2rrcorerparsersrrutilsr r r r r robjectrrjr#r!r|s. /$])])r#