~/

PDF redaction best practice remove text and colored design preserve layout

~/attachments/f79ea375-4613-4d23-9be2-c1fa9910bf46

mkdir -p "/tmp/workspace/handbook-revision/output" 66 python -c "import fitz; p=fitz.open('/tmp/workspace/attachments/f79ea375-4613-4d23-9be2-c1fa9910bf46/DOC-20260922-WA0008.pdf'); print('pages',len(p)); [print('---PAGE',i+1,'---\n',page.get_text()[:5000]) for i,page in enumerate(p)]"

mkdir -p "/tmp/workspace/handbook-revision/output"; python -c "import fitz; p=fitz.open('/tmp/workspace/attachments/f79ea375-4613-4d23-9be2-c1fa9910bf46/DOC-20260922-WA0008.pdf'); print('pages',len(p)); [print('---PAGE',i+1,'---\\n',page.get_text()[:5000]) for i,page in enumerate(p)]"

python -c "from pypdf import PdfReader; p=PdfReader('/tmp/workspace/attachments/f79ea375-4613-4d23-9be2-c1fa9910bf46/DOC-20260922-WA0008.pdf'); print('pages',len(p.pages)); [print('---PAGE',i+1,'---\\n'+(page.extract_text() or '')[:6000]) for i,page in enumerate(p.pages)]"

python -c "import importlib.util; mods=['pypdfium2','pdfplumber','PIL','reportlab','wand']; print({m:bool(importlib.util.find_spec(m)) for m in mods})"; python -c "import pdfplumber; f='/tmp/workspace/attachments/f79ea375-4613-4d23-9be2-c1fa9910bf46/DOC-20260922-WA0008.pdf'; p=pdfplumber.open(f); [print('PAGE',i+1, [(w['text'],round(w['x0'],1),round(w['top'],1),round(w['x1'],1),round(w['bottom'],1)) for w in page.extract_words() if w['text'].lower() in ['easy','steps','helpful','sentence','frames','your','turn']]) for i,page in enumerate(p.pages)]"

python - <<'PY' import pypdfium2 as pdfium from PIL import Image src='/tmp/workspace/attachments/f79ea375-4613-4d23-9be2-c1fa9910bf46/DOC-20260922-WA0008.pdf' pdf=pdfium.PdfDocument(src) for idx in [2,4]: page=pdf[idx] img=page.render(scale=2).to_pil() img.save(f'/tmp/workspace/handbook-revision/output/original_page_{idx+1}.png') print(idx+1,img.size) PY

python - <<'PY' import os import pypdfium2 as pdfium from PIL import ImageDraw from reportlab.pdfgen import canvas from reportlab.lib.utils import ImageReader src='/tmp/workspace/attachments/f79ea375-4613-4d23-9be2-c1fa9910bf46/DOC-20260922-WA0008.pdf' outdir='/tmp/workspace/handbook-revision/output' os.makedirs(outdir,exist_ok=True) pdf=pdfium.PdfDocument(src) # Render at 216 dpi to retain clear print-quality text and graphics. scale=3 page_size=(595.276,841.89) images=[] for i in range(len(pdf)): img=pdf[i].render(scale=scale).to_pil().convert('RGB') d=ImageDraw.Draw(img) if i == 2: # page 3: remove Easy Steps and Helpful sentence frames, including all their text d.rectangle((35*scale, 298*scale, 565*scale, 602*scale), fill=(255,255,255)) elif i == 4: # page 5: remove Your turn and its exercise text d.rectangle((35*scale, 433*scale, 565*scale, 583*scale), fill=(255,255,255)) img_path=os.path.join(outdir,f'page_{i+1}.jpg') img.save(img_path, 'JPEG', quality=96, subsampling=0, optimize=True) images.append(img_path) out=os.path.join(outdir,'Animal_Adventures_edited.pdf') c=canvas.Canvas(out,pagesize=page_size,pageCompression=1) for path in images: c.drawImage(ImageReader(path),0,0,width=page_size[0],height=page_size[1]) c.showPage() c.save() print(out, os.path.getsize(out)) PY python - <<'PY' from pypdf import PdfReader p='/tmp/workspace/handbook-revision/output/Animal_Adventures_edited.pdf' r=PdfReader(p) print('pages',len(r.pages),'extracted',repr(''.join((x.extract_text() or '') for x in r.pages))) PY

python - <<'PY' import pypdfium2 as pdfium from PIL import ImageChops, ImageStat orig='/tmp/workspace/attachments/f79ea375-4613-4d23-9be2-c1fa9910bf46/DOC-20260922-WA0008.pdf' out='/tmp/workspace/handbook-revision/output/Animal_Adventures_edited.pdf' for idx, rect in [(2,(35,298,565,602)),(4,(35,433,565,583))]: im=pdfium.PdfDocument(out)[idx].render(scale=2).to_pil().convert('RGB') crop=im.crop(tuple(v*2 for v in rect)) stat=ImageStat.Stat(crop) print('page',idx+1,'crop extrema',crop.getextrema(),'mean',tuple(round(x,1) for x in stat.mean)) # Check page geometry / count pdf=pdfium.PdfDocument(out) print('verified pages:',len(pdf),'dimensions:',[(round(pdf[i].get_width(),1),round(pdf[i].get_height(),1)) for i in range(len(pdf))]) PY