remove_study_drive_logo.py

import pikepdf
import sys

if len(sys.argv)<3:
	print(f"Usage {sys.argv[0]} input.pdf output.pdf")
	exit(1)

input = sys.argv[1]
output = sys.argv[2]

"""
StudyDrive Logo:
<pikepdf.Stream(stream_dict={
    "/BitsPerComponent": 8,
    "/ColorSpace": "/DeviceRGB",
    "/DecodeParms": {
      "/BitsPerComponent": 8,
      "/Colors": 3,
      "/Columns": 816,
      "/Predictor": 15
    },
    "/Filter": "/FlateDecode",
    "/Height": 107,
    "/Length": 16330,
    "/SMask": pikepdf.Stream(stream_dict={
        "/BitsPerComponent": 8,
        "/ColorSpace": "/DeviceGray",
        "/DecodeParms": {
          "/BitsPerComponent": 8,
          "/Colors": 1,
          "/Columns": 816,
          "/Predictor": 15
        },
        "/Filter": "/FlateDecode",
        "/Height": 107,
        "/Length": 6233,
        "/Subtype": "/Image",
        "/Type": "/XObject",
        "/Width": 816
      }, data=<...>),
    "/Subtype": "/Image",
    "/Type": "/XObject",
    "/Width": 816
  }, data=<...>)>
Annotation:
/A:
pikepdf.Dictionary({
  "/S": "/URI",
  "/URI": "https://www.studydrive.net/de?utm_source=Document&utm_medium=Watermark&utm_campaign=Watermark_DE"
})
"""


pdf = pikepdf.open(input)
for p in pdf.pages:
	study_drive_logo = [key for (key,i) in p.get("/Resources",dict()).get("/XObject",dict()).items() if i.get("/Height") == 107 and i.get("/Length") == 16330 ]
	if study_drive_logo:
		del p["/Resources"]["/XObject"][study_drive_logo[0]]
	study_drive_anno = [i for i, val in enumerate(p.get("/Annots",[])) if "https://www.studydrive.net/de?utm_source=Document&utm_medium=Watermark" in str(val.get("/A",dict()).get("/URI"))]
	if study_drive_anno:
		del p["/Annots"][study_drive_anno[0]]

pdf.save(output)