o e5@sldZddlmZddlmZddlmZddlmZddl m Z dd l m Z dd l m Z Gd d d e Zd S)a%Page object parsed with PDF raw dict. In addition to base structure described in :py:class:`~pdf2docx.page.RawPage`, some new features, e.g. sections, table block, are also included. Page elements structure: * :py:class:`~pdf2docx.page.Page` >> :py:class:`~pdf2docx.layout.Section` >> :py:class:`~pdf2docx.layout.Column` * :py:class:`~pdf2docx.layout.Blocks` * :py:class:`~pdf2docx.text.TextBlock` >> :py:class:`~pdf2docx.text.Line` >> :py:class:`~pdf2docx.text.TextSpan` / :py:class:`~pdf2docx.image.ImageSpan` >> :py:class:`~pdf2docx.text.Char` * :py:class:`~pdf2docx.table.TableBlock` >> :py:class:`~pdf2docx.table.Row` >> :py:class:`~pdf2docx.table.Cell` * :py:class:`~pdf2docx.layout.Blocks` * :py:class:`~pdf2docx.shape.Shapes` * :py:class:`~pdf2docx.shape.Shapes` * :py:class:`~pdf2docx.shape.Shape.Stroke` * :py:class:`~pdf2docx.shape.Shape.Fill` * :py:class:`~pdf2docx.shape.Shape.Hyperlink` :: { "id": 0, # page index "width" : w, "height": h, "margin": [left, right, top, bottom], "sections": [{ ... # section properties }, ...], "floats": [{ ... # floating picture }, ...] } )Pt) WD_SECTION)BaseCollection) debug_plot)BasePage)Sections) ImageBlockcseZdZdZ         d"dededed ed ed ed ed e de ffdd Z e ddZ ddZdefddZedddZddZddZdefd d!ZZS)#Pagez;Object representing the whole page, e.g. margins, sections.TNid skip_parsingwidthheightheaderfootermarginsections float_imagesc sX||_||_tj|||d|pt|d|_|pd|_|pd|_| p%t|_ d|_ dS)aInitialize page layout. Args: id (int, optional): Page index. Defaults to -1. skip_parsing (bool, optional): Don't parse page if True. Defaults to True. width (float, optional): Page width. Defaults to 0.0. height (float, optional): Page height. Defaults to 0.0. header (str, optional): Page header. Defaults to None. footer (str, optional): Page footer. Defaults to None. margin (tuple, optional): Page margin. Defaults to None. sections (Sections, optional): Page contents. Defaults to None. float_images (BaseCollection, optional): Float images in th is page. Defaults to None. )rrr)parentFN) rrsuper__init__r rrrrr _finalized) selfrrrrrrrrr __class__BD:\Projects\ConvertPro\env\Lib\site-packages\pdf2docx/page/Page.pyr6s    z Page.__init__cCs|jS)N)r)rrrr finalizedbszPage.finalizedc Cs2|j|j|j|j|j|j|j|jd}|S)z#Store parsed layout in dict format.)rrrrrrrfloats) rrrrrstorerrr)rresrrr r#fs z Page.storedatacCs|dd|_|dd|_|dd|_|dd|_|j|dg|d d |_|d d |_| |d gd |_ |S)z#Restore Layout from parsed results.rr rr rr)rrrrrrrrr"T) getrrrrrrestorerr_restore_float_imagesr)rr%rrr r'usz Page.restorez Final LayoutcKs|jjdi|d|_|jS)zParse page layout.TNr)rparser)rsettingsrrr r)sz Page.parsecKs^g}|jD]}|D]}|dr||jjq ||jjq qg}|D]}||jq$|S)zExtract content from tables (top layout only). .. note:: Before running this method, the page layout must be either parsed from source page or restored from parsed data. Zextract_stream_table)rextendblocksZ table_blocksZlattice_table_blocksappendtext)rr* collectionssectioncolumnZtablesZ table_blockrrr extract_tabless zPage.extract_tablescCs||jr |tj}n|jd}t|j|_t|j|_ |j \}}}}t||_ t||_ t||_ t||_|j|dS)a!Set page size, margin, and create page. .. note:: Before running this method, the page layout must be either parsed from source page or restored from parsed data. Args: doc (Document): ``python-docx`` document object rN)Z paragraphs add_sectionrZNEW_PAGErrrZ page_widthrZ page_heightrZ left_marginZ right_marginZ top_marginZ bottom_margin make_docx)rdocr0leftrighttopbottomrrr r4s        zPage.make_docxrawscCs4|j|D]}t|}||j|qdS)zRestore float images.N)rresetr Zset_float_image_blockr-)rr:rawimagerrr r(s zPage._restore_float_images) r Tr r NNNNN)__name__ __module__ __qualname____doc__intboolfloatstrtupler rrpropertyr!r#dictr'rr)r2r4listr( __classcell__rrrr r 3sJ,  r N)rAZ docx.sharedrZdocx.enum.sectionrZcommon.CollectionrZ common.sharerrZlayout.Sectionsr Zimage.ImageBlockr r rrrr s '