54065add4551a2415af574ad558f7c2d6fbeb9a9,pdftotree/TreeVisualizer.py,,get_pdf_dim,#Any#,86

Before Change

        "pdftotext -f {} -l {} -bbox "{}" -".format("1", "1", pdf_file), shell=True
    )
    soup = BeautifulSoup(html_content, "html.parser")
    pages = soup.find_all("page")
    page_width, page_height = (
        int(float(pages[0].get("width"))),
        int(float(pages[0].get("height"))),
    )
    return page_width, page_height

After Change

def get_pdf_dim(pdf_file) -> Tuple[int, int]:
    with open(pdf_file, "rb") as f:
        parser = PDFParser(f)
        doc = PDFDocument(parser)
        // Look at the 1st page only.
        page = next(PDFPage.create_pages(doc))
        _, _, page_width, page_height = page.mediabox
    return page_width, page_height

Instances