Class Page

pdf2docx/page/Page.py:51–211

Object representing the whole page, e.g. margins, sections.

class Page(BasePage):
    '''Object representing the whole page, e.g. margins, sections.'''

    def __init__(self, id:int=-1, 
                        skip_parsing:bool=True,
                        width:float=0.0,
                        height:float=0.0,
                        header:str=None, 
                        footer:str=None, 
                        margin:tuple=None, 
                        sections:Sections=None,
                        float_images:BaseCollection=None):
        '''Initialize 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.
        ''' 
        # page index
        self.id = id
        self.skip_parsing = skip_parsing

        # page size and margin
        super().__init__(width=width, height=height, margin=margin)

        # flow structure: 
        # Section -> Column -> Blocks -> TextBlock/TableBlock
        # TableBlock -> Row -> Cell -> Blocks
        self.sections = sections or Sections(parent=self)

        # page header, footer
        self.header = header or ''
        self.footer = footer or ''
        
        # floating images are separate node under page
        self.float_images = float_images or BaseCollection()

        self._finalized = False


    @property
    def finalized(self): return self._finalized   


    def store(self):
        '''Store parsed layout in dict format.'''
        res = {
            'id'      : self.id,
            'width'   : self.width,
            'height'  : self.height,
            'margin'  : self.margin,