python3 -c " import pdfplumber pdf_path = '/home/daytona/workspace/attachments/d83b66e3-d9b6-41a8-8763-e339723ed77f/I have excellent content from Campbell-Walsh-Wein .pdf' with pdfplumber.open(pdf_path) as pdf: print(f'Total pages: {len(pdf.pages)}') for i, page in enumerate(pdf.pages[:5]): text = page.extract_text() print(f'--- PAGE {i+1} ---') print(text[:800] if text else '[No text]') print() "

python3 -c " import pdfplumber pdf_path = '/home/daytona/workspace/attachments/d83b66e3-d9b6-41a8-8763-e339723ed77f/I have excellent content from Campbell-Walsh-Wein .pdf' with pdfplumber.open(pdf_path) as pdf: # Get all headings/topics across all pages all_text = [] for i, page in enumerate(pdf.pages): text = page.extract_text() if text: all_text.append(f'PAGE {i+1}: {text[:300]}') print('\n'.join(all_text[5:])) "

"cdn.orris.care" in /textbooks/9780323546423

python3 -c " import re # Read the block file and extract all image URLs with captions with open('/textbooks/9780323546423/9780323546423_block54.md', 'r') as f: content = f.read() # Find all image lines images = re.findall(r'!\[([^\]]*)\]\((https://cdn\.orris\.care/[^\)]+)\)\s*\n\s*\*([^\*]+)\*', content) for alt, url, caption in images[:15]: print(f'URL: {url}') print(f'Caption: {caption[:120]}') print() "

/

mkdir -p /home/daytona/workspace/campbell-images && python3 -c " import json, subprocess, base64, os images = [ ('rcc_papillary_ct', 'https://cdn.orris.care/cdss_images/85bdc63e1a1cef113189ed2bfcf2b5dd1ff2d2cbc94b7a92032b4a43cbc0f64d.png', 'Fig. 29.14: Papillary RCC - Pre and post-contrast CT showing large solid left renal mass with low-level enhancement typical of papillary cell carcinoma. (Grainger & Allison Radiology)'), ('rcc_t4_ct', 'https://cdn.orris.care/cdss_images/c252200a3183c43b7e1b73602cb95dacb5c86fa0bde5607ef2787797eba08488.png', 'Fig. 29.17: T4 Renal Cancer - CECT demonstrating large right renal mass with local infiltration, extension onto liver, and necrotic metastatic para-aortic nodes. (Grainger & Allison Radiology)'), ('checkpoint_inhibitor', 'https://cdn.orris.care/cdss_images/15204d744810ab622a0efecd7a7213ac12ede1886b691fae34c519eeffccac5a.png', 'Fig. 97.8: Mechanism of checkpoint inhibitors (PD-1/CTLA-4 pathway) used in metastatic RCC immunotherapy. (Campbell-Walsh-Wein Urology)'), ('urothelial_tcc', 'https://cdn.orris.care/cdss_images/4c0989dc42da83579b6dfbd16c0facb5bebcaaea90956623c438bd1e415758f2.png', 'Fig. 29.23: Urothelial Cell Cancer of the Kidney - Post-contrast CT showing large central soft-tissue mass invading renal pelvis causing hydronephrosis (TCC). (Grainger & Allison Radiology)'), ] result = json.loads(subprocess.check_output([ 'node', '/home/daytona/skills/shared/scripts/fetch_images.js' ] + [url for _, url, _ in images])) for i, (name, url, caption) in enumerate(images): img_data = result[i] if img_data.get('base64'): raw = base64.b64decode(img_data['base64'].split(',')[1]) out_path = f'/home/daytona/workspace/campbell-images/{name}.png' with open(out_path, 'wb') as f: f.write(raw) print(f'Saved: {out_path} ({len(raw)} bytes)') else: print(f'FAILED: {name} - {img_data.get(\"error\")}') "

python3 << 'PYEOF' import io from pypdf import PdfReader, PdfWriter from reportlab.lib.pagesizes import A4 from reportlab.pdfgen import canvas from reportlab.lib.utils import ImageReader from PIL import Image as PILImage INPUT_PDF = '/home/daytona/workspace/attachments/d83b66e3-d9b6-41a8-8763-e339723ed77f/I have excellent content from Campbell-Walsh-Wein .pdf' OUTPUT_PDF = '/home/daytona/workspace/campbell-images/Campbell-Walsh-Wein_with_images.pdf' # Images to insert: (after_page_index (0-based), image_path, caption) # Page 6 = index 5 (RCC types table - after it, add papillary CT) # Page 7 = index 6 (staging table - after it, add T4 CT) # Page 9 = index 8 (management/targeted therapy - after it, add checkpoint inhibitor) # Page 19 = index 18 (bladder/TCC diverticulum complications - add TCC image) IMAGE_INSERTS = [ (5, '/home/daytona/workspace/campbell-images/rcc_papillary_ct.png', 'Fig. 29.14: Papillary RCC - Pre- and post-contrast CT showing large solid left renal mass\nwith low-level enhancement, typical of papillary cell carcinoma.\n(Source: Grainger & Allison\'s Diagnostic Radiology)'), (6, '/home/daytona/workspace/campbell-images/rcc_t4_ct.png', 'Fig. 29.17: T4 Renal Cancer - CECT demonstrating large right renal mass with local\ninfiltration onto liver, and necrotic metastatic para-aortic nodes.\n(Source: Grainger & Allison\'s Diagnostic Radiology)'), (9, '/home/daytona/workspace/campbell-images/checkpoint_inhibitor.png', 'Fig. 97.8: Mechanism of checkpoint inhibitors (PD-1/PD-L1 and CTLA-4 pathways)\nused as immunotherapy in metastatic RCC.\n(Source: Campbell-Walsh-Wein Urology 12th Ed.)'), (18, '/home/daytona/workspace/campbell-images/urothelial_tcc.png', 'Fig. 29.23: Urothelial (Transitional) Cell Carcinoma of the Kidney - Post-contrast CT\nshowing central soft-tissue mass invading renal pelvis causing hydronephrosis.\n(Source: Grainger & Allison\'s Diagnostic Radiology)'), ] def make_image_page(img_path, caption): """Create a PDF page with the image centred and caption below.""" buf = io.BytesIO() w, h = A4 # 595 x 842 pts c = canvas.Canvas(buf, pagesize=A4) # Background c.setFillColorRGB(0.97, 0.97, 0.97) c.rect(0, 0, w, h, fill=1, stroke=0) # Header bar c.setFillColorRGB(0.12, 0.29, 0.49) # dark navy c.rect(0, h - 40, w, 40, fill=1, stroke=0) c.setFillColorRGB(1, 1, 1) c.setFont('Helvetica-Bold', 11) c.drawString(20, h - 26, 'MEDICAL ILLUSTRATION — Campbell-Walsh-Wein Urology / Grainger & Allison Radiology') # Draw image margin = 40 max_img_h = h - 160 # leave room for caption and header max_img_w = w - 2 * margin pil_img = PILImage.open(img_path) iw, ih = pil_img.size ratio = min(max_img_w / iw, max_img_h / ih) draw_w = iw * ratio draw_h = ih * ratio x = (w - draw_w) / 2 y = 100 # bottom area for caption c.drawImage(ImageReader(img_path), x, y, width=draw_w, height=draw_h, preserveAspectRatio=True) # Border around image c.setStrokeColorRGB(0.12, 0.29, 0.49) c.setLineWidth(1.5) c.rect(x - 4, y - 4, draw_w + 8, draw_h + 8, fill=0, stroke=1) # Caption box c.setFillColorRGB(0.22, 0.22, 0.22) c.setFont('Helvetica', 9) lines = caption.split('\n') cap_y = 80 for line in reversed(lines): c.drawCentredString(w / 2, cap_y, line) cap_y -= 13 c.save() buf.seek(0) return PdfReader(buf).pages[0] reader = PdfReader(INPUT_PDF) writer = PdfWriter() original_pages = list(reader.pages) total = len(original_pages) print(f'Original pages: {total}') # Build insert map: after which original page (0-based) to insert an image page insert_map = {} for after_idx, img_path, caption in IMAGE_INSERTS: insert_map.setdefault(after_idx, []).append((img_path, caption)) for i, page in enumerate(original_pages): writer.add_page(page) if i in insert_map: for img_path, caption in insert_map[i]: img_page = make_image_page(img_path, caption) writer.add_page(img_page) print(f' Inserted image after page {i+1}: {img_path.split("/")[-1]}') with open(OUTPUT_PDF, 'wb') as f: writer.write(f) print(f'\nDone! Output: {OUTPUT_PDF}') print(f'Total pages in output: {len(writer.pages)}') PYEOF