def test_get_images(src, nb_images):
src = os.path.join(RESOURCE_ROOT, src)
reader = PdfFileReader(src)
with pytest.raises(TypeError):
page = reader.pages["0"]
page = reader.pages[-1]
page = reader.pages[0]
images_extracted = []
if RES.XOBJECT in page[PG.RESOURCES]:
xObject = page[PG.RESOURCES][RES.XOBJECT].getObject()
for obj in xObject:
if xObject[obj][IA.SUBTYPE] == "/Image":
extension, byte_stream = _xobj_to_image(xObject[obj])
if extension is not None:
filename = obj[1:] + ".png"
with open(filename, "wb") as img:
img.write(byte_stream)
images_extracted.append(filename)
assert len(images_extracted) == nb_images
# Cleanup
for filepath in images_extracted:
os.remove(filepath)
def main(pdf: str):
reader = PyPDF2.PdfFileReader(pdf)
page = reader.pages[30]
if RES.XOBJECT in page[PG.RESOURCES]:
xObject = page[PG.RESOURCES][RES.XOBJECT].getObject()
for obj in xObject:
if xObject[obj][IA.SUBTYPE] == "/Image":
extension, byte_stream = _xobj_to_image(xObject[obj])
if extension is not None:
filename = obj[1:] + ".png"
with open(filename, "wb") as img:
img.write(byte_stream)
else:
print("No image found.")