# Most watermarks are at same coordinates across pages common_rect = fitz.Rect() if watermarks: common_rect = watermarks[0] # simplify: take first
# Detect watermark region (first page, look for repeated gray text) first_page = doc[0] watermarks = [] for block in first_page.get_text("dict")["blocks"]: for line in block.get("lines", []): for span in line.get("spans", []): if span["color"] < 0.5: # dark gray/black threshold bbox = fitz.Rect(span["bbox"]) watermarks.append(bbox) pdf remove watermark github
for page_num in range(len(doc)): page = doc[page_num] # Method 1: Draw white over watermark (crude but works) page.draw_rect(common_rect, color=(1,1,1), fill=(1,1,1), width=0) # Method 2: Remove text objects (more aggressive) page.clean_contents() doc.save(output_pdf) doc.close() # Most watermarks are at same coordinates across
This physically removes the text—even from copied text layer. Image watermarks (scan of a stamp, logo) require a different approach: []): for span in line.get("spans"