o j@spddlZddlZddlmZmZddlmZddlmZm Z ddl m Z m Z m Z mZmZmZGdddeZdS) N) PdfReader PdfWriter) TableList)StreamLattice)TemporaryDirectoryget_page_layoutget_text_objects get_rotationis_url download_urlc@s:eZdZdZdddZddZdd Zd d ifd d ZdS) 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. 1NcCsnt|rt|}||_|dstd|durd|_n||_tjddkr/|j d|_| ||_ dS)N.pdfzFile format not supportedrascii) r r filepathlowerendswithNotImplementedErrorpasswordsys version_infoencode _get_pagespages)selfrrrrV/var/www/html/fyndo/pharma/fyndo/venv/lib/python3.10/site-packages/camelot/handlers.py__init__%szPDFHandler.__init__c Cs(g}|dkr|dddnjt|jd\}t|dd}|jr%||j|dkr5|dt|jdn5| dD]/}d |vr]| d \}}|d krPt|j}|t |t |dq:|t |t |dq:Wd n1stwYg}|D]} | t | d | d dq}t t|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. rr)startendrbFstrictall,-r#Nr")appendopenrr is_encrypteddecryptrlenrsplitintextendrangesortedset) rr page_numbersfinfilerabPprrr r4s,    zPDFHandler._get_pagesc Cst|d}t|dd}|jr||jtj|d|d}tj|\}}|j |d} t } | | t|d } | | Wdn1sLwYt |\} } t| d d }t| d d }t| d d }t|||}|d krd |ddd|g}t||t|d}t|dd}|jr||jt } |j d} |dkr| dn |dkr| d| | t|d } | | Wdn1swY|WddSWddS1swYdS)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$Fr%page-rrwbNchar)ltypehorizontal_text vertical_textrpager<_rotatedr anticlockwiseZ clockwisei)r+rr,r-rospathjoinsplitextrradd_pagewriter r r replacerenamerotateclose)rrrCtempfileobjr7fpathfrootfextr<outfiler6layoutdimcharsrArBrotation fpath_newinstreamrrr _save_pageasL                     "zPDFHandler._save_pagelatticeFc  sg}tD|jD] }||j|q fdd|jD}|dkr)tdi|ntdi|}|D]}|j|||d} || q2Wdn1sLwYtt |S)aExtracts tables by calling parser.get_tables on all single page PDFs. Parameters ---------- flavor : str (default: 'lattice') The parsing method to use ('lattice' or 'stream'). Lattice is used by default. suppress_stdout : str (default: False) Suppress logs and warnings. layout_kwargs : dict, optional (default: {}) A dict of `pdfminer.layout.LAParams `_ kwargs. kwargs : dict See camelot.read_pdf kwargs. Returns ------- tables : camelot.core.TableList List of tables found in PDF. cs"g|] }tjd|dqS)r=r)rHrIrJ).0r<tempdirrr s"z$PDFHandler.parse..r_)suppress_stdout layout_kwargsNr) rrr^rrrextract_tablesr1rr3) rflavorrdrekwargstablesr<rparsertrrar parses $  zPDFHandler.parse)rN)__name__ __module__ __qualname____doc__r!rr^rlrrrr rs -1r)rHrpypdfrrcorerparsersrrutilsrr r r r r objectrrrrr s