# Step 1: Generate a mask where watermark exists (manual ROI) convert input.pdf[0] -threshold 50% mask.png for i in $(seq 0 $(pdfinfo input.pdf | grep Pages | awk 'print $2')); do convert input.pdf[$i] mask.png -compose dst_out -composite page_$i.pdf done Step 3: Rebuild PDF and OCR pdfunite page_*.pdf no_watermark.pdf ocrmypdf no_watermark.pdf final_clean.pdf --deskew --clean
# 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
No single tool works universally. The deep approach: 3. Deep Dive: PyMuPDF Script (Most Effective) import fitz # PyMuPDF def remove_watermark_by_rect(input_pdf, output_pdf, rect_tolerance=0.1): """ Remove all vector/text elements inside specified rectangular regions. rect_tolerance: match watermark position across pages (fraction of page) """ doc = fitz.open(input_pdf) # Step 1: Generate a mask where watermark
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() []): for span in line.get("spans"