def get_pdf_page_array(): pdf_pages = [] attrs = {"MediaBox": [0, 0, 400, 300]} for i in range(4): page = PDFPage(doc=None, pageid=i, attrs=attrs) rawdata = "Department of Homeland Security" pdf_stream = PDFStream(attrs, rawdata) pdf_stream.data = rawdata pdf_stream.set_objid(i, i) page.contents = [pdf_stream] pdf_pages.append(page) return pdf_pages