Function extract_cells

src/table.py:223–324

Extract text from a rect-like 'cell' as plain or MD styled text. This function should ultimately be used to extract text from a table cell. Markdown output will only work correctly if extraction flag bit TEXT_COLLECT_STYLES is set. Args: textpage: A PyMuPDF TextPage object.

(textpage, cell, markdown=False)

def extract_cells(textpage, cell, markdown=False):
    """Extract text from a rect-like 'cell' as plain or MD styled text.

    This function should ultimately be used to extract text from a table cell.
    Markdown output will only work correctly if extraction flag bit
    TEXT_COLLECT_STYLES is set.

    Args:
        textpage: A PyMuPDF TextPage object. Must have been created with
            TEXTFLAGS_TEXT | TEXT_COLLECT_STYLES.
        cell: A tuple (x0, y0, x1, y1) defining the cell's bbox.
        markdown: If True, return text formatted for Markdown.

    Returns:
        A string with the text extracted from the cell.
    """
    text = ""
    for block in textpage.extractRAWDICT()["blocks"]:
        if block["type"] != 0:
            continue
        block_bbox = block["bbox"]
        if (
            0
            or block_bbox[0] > cell[2]
            or block_bbox[2] < cell[0]
            or block_bbox[1] > cell[3]
            or block_bbox[3] < cell[1]
        ):
            continue  # skip block outside cell
        for line in block["lines"]:
            lbbox = line["bbox"]
            if (
                0
                or lbbox[0] > cell[2]
                or lbbox[2] < cell[0]
                or lbbox[1] > cell[3]
                or lbbox[3] < cell[1]
            ):
                continue  # skip line outside cell

            if text:  # must be a new line in the cell
                text += "<br>" if markdown else "\n"

            # strikeout detection only works with horizontal text
            horizontal = line["dir"] == (0, 1) or line["dir"] == (1, 0)

            for span in line["spans"]:
                sbbox = span["bbox"]
                if (
                    0
                    or sbbox[0] > cell[2]
                    or sbbox[2] < cell[0]
                    or sbbox[1] > cell[3]
                    or sbbox[3] < cell[1]
                ):
                    continue  # skip spans outside cell

                # only include chars with more than 50% bbox overlap