Extract PDF Watermark Details in Python
Contents
[
Hide
]
Read the text and bounding rectangle of watermark artifacts on the first page of a PDF in Python.
Read watermark text and bounds
Print the text and bounding rectangle of each pagination artifact with the WATERMARK subtype.
import aspose.pdf as ap
def extract_watermark_from_pdf(infile):
with ap.Document(infile) as document:
watermarks = [
artifact
for artifact in document.pages[1].artifacts
if artifact.type == ap.Artifact.ArtifactType.PAGINATION
and artifact.subtype == ap.Artifact.ArtifactSubtype.WATERMARK
]
for watermark in watermarks:
print(f"{watermark.text} {watermark.rectangle}")