python3 << 'EOF' import pdfplumber pdf_path = "/home/daytona/workspace/attachments/df2604ad-db29-496a-a1f3-a77d7c147ac3/Respiratory Golwala-1.pdf" with pdfplumber.open(pdf_path) as pdf: print(f"Total pages: {len(pdf.pages)}") # Extract first 5 pages to understand structure for i, page in enumerate(pdf.pages[:5]): text = page.extract_text() print(f"\n--- PAGE {i+1} ---") print(text[:2000] if text else "(no text)") EOF

python3 << 'EOF' import subprocess # Check if pytesseract and pdf2image are available try: import pytesseract print("pytesseract available") except: print("pytesseract NOT available") try: from pdf2image import convert_from_path print("pdf2image available") except: print("pdf2image NOT available") # Check for pdftotext result = subprocess.run(['pdftotext', '-v'], capture_output=True, text=True) print("pdftotext:", result.returncode, result.stderr[:100]) # Try pypdf from pypdf import PdfReader reader = PdfReader("/home/daytona/workspace/attachments/df2604ad-db29-496a-a1f3-a77d7c147ac3/Respiratory Golwala-1.pdf") print(f"Pages: {len(reader.pages)}") page = reader.pages[0] print("Page0 text:", repr(page.extract_text()[:200])) print("Page0 images:", len(page.images)) EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract pdf_path = "/home/daytona/workspace/attachments/df2604ad-db29-496a-a1f3-a77d7c147ac3/Respiratory Golwala-1.pdf" print("Converting PDF to images...") images = convert_from_path(pdf_path, dpi=200) print(f"Converted {len(images)} pages") # OCR all pages full_text = "" for i, img in enumerate(images): text = pytesseract.image_to_string(img) full_text += f"\n\n===PAGE {i+1}===\n{text}" print(f"Page {i+1} done, chars: {len(text)}") # Save to file with open("/home/daytona/workspace/respiratory_golwala_ocr.txt", "w") as f: f.write(full_text) print(f"\nTotal chars: {len(full_text)}") print("Saved to respiratory_golwala_ocr.txt") EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract pdf_path = "/home/daytona/workspace/attachments/df2604ad-db29-496a-a1f3-a77d7c147ac3/Respiratory Golwala-1.pdf" # Process in batches - lower DPI for speed print("Converting PDF pages 1-10...") images = convert_from_path(pdf_path, dpi=150, first_page=1, last_page=10) print(f"Got {len(images)} images") full_text = "" for i, img in enumerate(images): text = pytesseract.image_to_string(img) full_text += f"\n\n===PAGE {i+1}===\n{text}" with open("/home/daytona/workspace/resp_ocr_1_10.txt", "w") as f: f.write(full_text) print("Pages 1-10 saved. Preview:") print(full_text[:3000]) EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract pdf_path = "/home/daytona/workspace/attachments/df2604ad-db29-496a-a1f3-a77d7c147ac3/Respiratory Golwala-1.pdf" print("Converting pages 11-20...") images = convert_from_path(pdf_path, dpi=150, first_page=11, last_page=20) full_text = "" for i, img in enumerate(images): text = pytesseract.image_to_string(img) full_text += f"\n\n===PAGE {i+11}===\n{text}" with open("/home/daytona/workspace/resp_ocr_11_20.txt", "w") as f: f.write(full_text) print("Pages 11-20 done, chars:", len(full_text)) EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract pdf_path = "/home/daytona/workspace/attachments/df2604ad-db29-496a-a1f3-a77d7c147ac3/Respiratory Golwala-1.pdf" print("Converting pages 21-31...") images = convert_from_path(pdf_path, dpi=150, first_page=21, last_page=31) full_text = "" for i, img in enumerate(images): text = pytesseract.image_to_string(img) full_text += f"\n\n===PAGE {i+21}===\n{text}" with open("/home/daytona/workspace/resp_ocr_21_31.txt", "w") as f: f.write(full_text) print("Pages 21-31 done, chars:", len(full_text)) EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract pdf_path = "/home/daytona/workspace/attachments/df2604ad-db29-496a-a1f3-a77d7c147ac3/Respiratory Golwala-1.pdf" print("Converting pages 21-26...") images = convert_from_path(pdf_path, dpi=150, first_page=21, last_page=26) full_text = "" for i, img in enumerate(images): text = pytesseract.image_to_string(img) full_text += f"\n\n===PAGE {i+21}===\n{text}" with open("/home/daytona/workspace/resp_ocr_21_26.txt", "w") as f: f.write(full_text) print("Done, chars:", len(full_text)) EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract pdf_path = "/home/daytona/workspace/attachments/df2604ad-db29-496a-a1f3-a77d7c147ac3/Respiratory Golwala-1.pdf" print("Converting pages 27-31...") images = convert_from_path(pdf_path, dpi=150, first_page=27, last_page=31) full_text = "" for i, img in enumerate(images): text = pytesseract.image_to_string(img) full_text += f"\n\n===PAGE {i+27}===\n{text}" with open("/home/daytona/workspace/resp_ocr_27_31.txt", "w") as f: f.write(full_text) print("Done, chars:", len(full_text)) EOF