~/

~/attachments/f14417ca-784a-4476-a526-452420e7c5b6

python -c "from pypdf import PdfReader; p='/tmp/workspace/attachments/f14417ca-784a-4476-a526-452420e7c5b6/DOC-20260901-WA0029 (1).pdf'; r=PdfReader(p); print('pages',len(r.pages)); [print('---PAGE',i+1,'---\n',pg.extract_text()[:4000]) for i,pg in enumerate(r.pages)]"

mkdir -p "/tmp/workspace/animal-handbook/output"  python -c "import fitz; p='/tmp/workspace/attachments/f14417ca-784a-4476-a526-452420e7c5b6/DOC-20260901-WA0029 (1).pdf'; d=fitz.open(p); print([(i+1, d[i].rect) for i in range(len(d))]); pix=d[3].get_pixmap(matrix=fitz.Matrix(1.5,1.5),alpha=False); pix.save('/tmp/workspace/animal-handbook/output/page4.png')"

mkdir -p "/tmp/workspace/animal-handbook/output" && python -c "import fitz; p='/tmp/workspace/attachments/f14417ca-784a-4476-a526-452420e7c5b6/DOC-20260901-WA0029 (1).pdf'; d=fitz.open(p); print([(i+1, str(d[i].rect)) for i in range(len(d))]); pix=d[3].get_pixmap(matrix=fitz.Matrix(1.5,1.5),alpha=False); pix.save('/tmp/workspace/animal-handbook/output/page4.png')"

python -c "from pypdf import PdfReader; p='/tmp/workspace/attachments/f14417ca-784a-4476-a526-452420e7c5b6/DOC-20260901-WA0029 (1).pdf';r=PdfReader(p); print([str(x.mediabox) for x in r.pages]); print(r.pages[3].get_contents().get_data()[:1000])"

python -c "import pdfplumber; p='/tmp/workspace/attachments/f14417ca-784a-4476-a526-452420e7c5b6/DOC-20260901-WA0029 (1).pdf'; pdf=pdfplumber.open(p); pg=pdf.pages[3]; print(pg.width,pg.height); [print(x['text'],round(x['x0'],1),round(x['top'],1),round(x['x1'],1),round(x['bottom'],1)) for x in pg.extract_words()]"

python -c "import reportlab; print(reportlab.Version)" && python -c "import os; print(os.path.exists('/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf'), os.path.exists('/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf'))"

/usr/share/fonts

python -c "from pypdf import PdfReader; p='/tmp/workspace/attachments/f14417ca-784a-4476-a526-452420e7c5b6/DOC-20260901-WA0029 (1).pdf'; r=PdfReader(p); print(r.pages[3].extract_text(visitor_text=lambda text,cm,tm,fontDict,fontSize: print(repr(text), tm, getattr(fontDict,'keys',lambda:[])()) if text.strip() else None))"

/usr/share/fonts/google-noto-vf

python - <<'PY' from reportlab.pdfgen import canvas from reportlab.lib.colors import HexColor, white from reportlab.pdfbase import pdfmetrics from reportlab.pdfbase.ttfonts import TTFont from pypdf import PdfReader, PdfWriter from pathlib import Path base=Path('/tmp/workspace/animal-handbook') outdir=base/'output'; outdir.mkdir(parents=True,exist_ok=True) src=Path('/tmp/workspace/attachments/f14417ca-784a-4476-a526-452420e7c5b6/DOC-20260901-WA0029 (1).pdf') overlay=outdir/'new_page.pdf' out=outdir/'Animal_Vocabulary_Handbook_Updated.pdf' font='/usr/share/fonts/google-noto-vf/NotoSans[wght].ttf' pdfmetrics.registerFont(TTFont('NotoSans',font)) # reportlab maps bold via Noto Sans variable; use same clean font c=canvas.Canvas(str(overlay),pagesize=(612,792)) # warm cream background c.setFillColor(HexColor('#FFF9EC'));c.rect(0,0,612,792,stroke=0,fill=1) # playful background bubbles for x,y,r,col in [(51,661,3,'#BFE7E0'),(452,670,4,'#F9B6C5'),(541,621,3,'#BFE7E0'),(169,166,3,'#F9B6C5'),(531,171,4,'#F9B6C5'),(366,454,3,'#F9B6C5'),(412,447,2,'#F9B6C5')]: c.setFillColor(HexColor(col));c.circle(x,y,r,stroke=0,fill=1) # header c.setFillColor(HexColor('#304D65'));c.setFont('NotoSans',24);c.drawString(40,737,'Words to Know') c.setFillColor(HexColor('#506B7C'));c.setFont('NotoSans',10);c.drawString(40,713,'English meaning and Russian translation') # soft boxes entries=[ ('15','tail','the long part at the back of an animal’s body','Русский: хвост','#F5D7E1'), ('16','fins','flat parts fish use to swim','Русский: плавники','#D5EFE9'), ('17','wet skin','skin that stays moist, like an amphibian’s skin','Русский: влажная кожа','#F9E6B9'), ] ys=[608,440,272] for (num,word,meaning,rus,col),y in zip(entries,ys): # rounded box c.setFillColor(HexColor(col));c.roundRect(48,y-56,516,130,16,stroke=0,fill=1) # number badge c.setFillColor(HexColor('#F19AAA'));c.circle(81,y+42,18,stroke=0,fill=1) c.setFillColor(white);c.setFont('NotoSans',14);c.drawCentredString(81,y+37,num) # word c.setFillColor(HexColor('#304D65'));c.setFont('NotoSans',18);c.drawString(112,y+35,word) # meaning and russian c.setFillColor(HexColor('#415C6C'));c.setFont('NotoSans',10);c.drawString(68,y,meaning) c.setFillColor(HexColor('#3E6878'));c.setFont('NotoSans',10);c.drawString(68,y-27,rus) # footer c.setFillColor(HexColor('#506B7C'));c.setFont('NotoSans',8);c.drawString(42,18,'Animal Vocabulary') c.drawRightString(564,18,'6') c.save() writer=PdfWriter() for page in PdfReader(str(src)).pages: writer.add_page(page) writer.add_page(PdfReader(str(overlay)).pages[0]) with open(out,'wb') as f: writer.write(f) print(out, out.stat().st_size) # Verify page and extracted text r=PdfReader(str(out)); print('pages',len(r.pages)); print(r.pages[-1].extract_text()) PY