def test_remove_text(input_path, ignore_byte_string_object):
pdf_path = os.path.join(RESOURCE_ROOT, input_path)
reader = PdfReader(pdf_path)
writer = PdfWriter()
page = reader.pages[0]
writer.insert_page(page, 0)
writer.remove_text(ignore_byte_string_object=ignore_byte_string_object)
# finally, write "output" to PyPDF2-output.pdf
tmp_filename = "dont_commit_writer_removed_text.pdf"
with open(tmp_filename, "wb") as output_stream:
writer.write(output_stream)
# Cleanup
os.remove(tmp_filename)
def test_remove_images(input_path, ignore_byte_string_object):
pdf_path = os.path.join(RESOURCE_ROOT, input_path)
reader = PdfReader(pdf_path)
writer = PdfWriter()
page = reader.pages[0]
writer.insert_page(page, 0)
writer.remove_images(ignore_byte_string_object=ignore_byte_string_object)
# finally, write "output" to PyPDF2-output.pdf
tmp_filename = "dont_commit_writer_removed_image.pdf"
with open(tmp_filename, "wb") as output_stream:
writer.write(output_stream)
with open(tmp_filename, "rb") as input_stream:
reader = PdfReader(input_stream)
if input_path == "side-by-side-subfig.pdf":
extracted_text = reader.pages[0].extract_text()
assert "Lorem ipsum dolor sit amet" in extracted_text
# Cleanup
os.remove(tmp_filename)
def test_writer_operations():
"""
This test just checks if the operation throws an exception.
This should be done way more thoroughly: It should be checked if the
output is as expected.
"""
pdf_path = os.path.join(RESOURCE_ROOT, "crazyones.pdf")
pdf_outline_path = os.path.join(RESOURCE_ROOT, "pdflatex-outline.pdf")
reader = PdfReader(pdf_path)
reader_outline = PdfReader(pdf_outline_path)
writer = PdfWriter()
page = reader.pages[0]
with pytest.raises(PageSizeNotDefinedError) as exc:
writer.add_blank_page()
assert exc.value.args == ()
writer.insert_page(page, 1)
writer.insert_page(reader_outline.pages[0], 0)
writer.add_bookmark_destination(page)
writer.remove_links()
writer.add_bookmark_destination(page)
bm = writer.add_bookmark("A bookmark", 0, None, (255, 0, 15), True, True,
"/FitBV", 10)
writer.add_bookmark("The XYZ fit", 0, bm, (255, 0, 15), True, True, "/XYZ",
10, 20, 3)
writer.add_bookmark("The FitH fit", 0, bm, (255, 0, 15), True, True,
"/FitH", 10)
writer.add_bookmark("The FitV fit", 0, bm, (255, 0, 15), True, True,
"/FitV", 10)
writer.add_bookmark("The FitR fit", 0, bm, (255, 0, 15), True, True,
"/FitR", 10, 20, 30, 40)
writer.add_bookmark("The FitB fit", 0, bm, (255, 0, 15), True, True,
"/FitB")
writer.add_bookmark("The FitBH fit", 0, bm, (255, 0, 15), True, True,
"/FitBH", 10)
writer.add_bookmark("The FitBV fit", 0, bm, (255, 0, 15), True, True,
"/FitBV", 10)
writer.add_blank_page()
writer.add_uri(2, "https://example.com", RectangleObject([0, 0, 100, 100]))
writer.add_link(2, 1, RectangleObject([0, 0, 100, 100]))
assert writer._get_page_layout() is None
writer._set_page_layout("/SinglePage")
assert writer._get_page_layout() == "/SinglePage"
assert writer._get_page_mode() is None
writer.set_page_mode("/UseNone")
assert writer._get_page_mode() == "/UseNone"
writer.insert_blank_page(width=100, height=100)
writer.insert_blank_page() # without parameters
# TODO: This gives "KeyError: '/Contents'" - is that a bug?
# writer.removeImages()
writer.add_metadata({"author": "Martin Thoma"})
writer.add_attachment("foobar.gif", b"foobarcontent")
# finally, write "output" to PyPDF2-output.pdf
tmp_path = "dont_commit_writer.pdf"
with open(tmp_path, "wb") as output_stream:
writer.write(output_stream)
# cleanup
os.remove(tmp_path)
def test_remove_text_all_operators(ignore_byte_string_object):
stream = (b"BT "
b"/F0 36 Tf "
b"50 706 Td "
b"36 TL "
b"(The Tj operator) Tj "
b'1 2 (The double quote operator) " '
b"(The single quote operator) ' "
b"ET")
pdf_data = (
b"%%PDF-1.7\n"
b"1 0 obj << /Count 1 /Kids [5 0 R] /Type /Pages >> endobj\n"
b"2 0 obj << >> endobj\n"
b"3 0 obj << >> endobj\n"
b"4 0 obj << /Length %d >>\n"
b"stream\n" + (b"%s\n" % stream) + b"endstream\n"
b"endobj\n"
b"5 0 obj << /Contents 4 0 R /CropBox [0.0 0.0 2550.0 3508.0]\n"
b" /MediaBox [0.0 0.0 2550.0 3508.0] /Parent 1 0 R"
b" /Resources << /Font << >> >>"
b" /Rotate 0 /Type /Page >> endobj\n"
b"6 0 obj << /Pages 1 0 R /Type /Catalog >> endobj\n"
b"xref 1 6\n"
b"%010d 00000 n\n"
b"%010d 00000 n\n"
b"%010d 00000 n\n"
b"%010d 00000 n\n"
b"%010d 00000 n\n"
b"%010d 00000 n\n"
b"trailer << /Root 6 0 R /Size 6 >>\n"
b"startxref\n%d\n"
b"%%%%EOF")
startx_correction = -1
pdf_data = pdf_data % (
len(stream),
pdf_data.find(b"1 0 obj") + startx_correction,
pdf_data.find(b"2 0 obj") + startx_correction,
pdf_data.find(b"3 0 obj") + startx_correction,
pdf_data.find(b"4 0 obj") + startx_correction,
pdf_data.find(b"5 0 obj") + startx_correction,
pdf_data.find(b"6 0 obj") + startx_correction,
# startx_correction should be -1 due to double % at the beginning indiducing an error on startxref computation
pdf_data.find(b"xref"),
)
print(pdf_data.decode())
pdf_stream = BytesIO(pdf_data)
reader = PdfReader(pdf_stream, strict=False)
writer = PdfWriter()
page = reader.pages[0]
writer.insert_page(page, 0)
writer.remove_text(ignore_byte_string_object=ignore_byte_string_object)
# finally, write "output" to PyPDF2-output.pdf
tmp_filename = "dont_commit_writer_removed_text.pdf"
with open(tmp_filename, "wb") as output_stream:
writer.write(output_stream)
# Cleanup
os.remove(tmp_filename)