python3 -c " from pypdf import PdfReader reader = PdfReader('/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta'\''s Textbook of Gynecology_11zon (1).pdf') print(f'Total pages: {len(reader.pages)}') # Print first few pages to understand structure for i in range(5): text = reader.pages[i].extract_text() print(f'--- PAGE {i+1} ---') print(text[:500]) print() "

PDF="/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" python3 << 'EOF' from pypdf import PdfReader pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" reader = PdfReader(pdf_path) print(f"Total pages: {len(reader.pages)}") for i in range(8): text = reader.pages[i].extract_text() print(f"--- PAGE {i+1} ---") print(text[:600]) print() EOF

python3 << 'EOF' from pypdf import PdfReader pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" reader = PdfReader(pdf_path) print(f"Total pages: {len(reader.pages)}") # Check pages 10-30 for content for i in range(9, 30): text = reader.pages[i].extract_text() if text and len(text.strip()) > 50: print(f"--- PAGE {i+1} ---") print(text[:400]) print() EOF

python3 << 'EOF' import pdfplumber pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" with pdfplumber.open(pdf_path) as pdf: print(f"Total pages: {len(pdf.pages)}") # Try pages 10-30 for i in range(9, 40): page = pdf.pages[i] text = page.extract_text() if text and len(text.strip()) > 50: print(f"--- PAGE {i+1} ---") print(text[:500]) print() break else: print("No text found in pages 10-40") # Try scanning for text in any page for i in range(0, 100, 10): page = pdf.pages[i] text = page.extract_text() if text and len(text.strip()) > 50: print(f"First text found at page {i+1}:") print(text[:300]) break EOF

python3 << 'EOF' import pdfplumber pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" with pdfplumber.open(pdf_path) as pdf: print(f"Total pages: {len(pdf.pages)}") # Scan all pages to find first with text found = False for i in range(0, 588, 5): page = pdf.pages[i] text = page.extract_text() if text and len(text.strip()) > 100: print(f"First text found at page {i+1}:") print(text[:600]) found = True break if not found: print("Trying word extraction...") for i in range(0, 588, 5): page = pdf.pages[i] words = page.extract_words() if words: print(f"Words found at page {i+1}:") print(words[:10]) break EOF

python3 << 'EOF' import pdfplumber pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" with pdfplumber.open(pdf_path) as pdf: page = pdf.pages[20] # Check page properties print(f"Page size: {page.width} x {page.height}") print(f"Images on page: {len(page.images)}") if page.images: print(f"First image: {page.images[0]}") # Try chars chars = page.chars print(f"Chars count: {len(chars)}") if chars: print(f"First char: {chars[0]}") EOF

tesseract --version 2>&1 | head -3 && python3 -c "import pytesseract; print('pytesseract ok')" 2>&1 && python3 -c "from pdf2image import convert_from_path; print('pdf2image ok')" 2>&1

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract import os pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" # OCR pages 1-15 to find TOC images = convert_from_path(pdf_path, first_page=1, last_page=15, dpi=200) for i, img in enumerate(images): text = pytesseract.image_to_string(img) if text.strip(): print(f"=== PAGE {i+1} ===") print(text[:800]) print() EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" # OCR pages 15-18 for more TOC images = convert_from_path(pdf_path, first_page=15, last_page=18, dpi=200) for i, img in enumerate(images): text = pytesseract.image_to_string(img) if text.strip(): print(f"=== PAGE {i+15} ===") print(text) print() EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" # OCR pages around where chapter 5 should be (PDF page ~55-70) # TOC is at PDF page 15, chapters start around page 20 of PDF # Let's scan a few pages to find Chapter 5 start images = convert_from_path(pdf_path, first_page=54, last_page=65, dpi=180) for i, img in enumerate(images): text = pytesseract.image_to_string(img) if 'uberty' in text or 'Puberty' in text or 'puberty' in text: print(f"=== PDF PAGE {i+54} ===") print(text[:800]) print() EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" # OCR Chapter 5 fully - pages 59-68 print("=== EXTRACTING CHAPTER 5 (PUBERTY) ===") images = convert_from_path(pdf_path, first_page=59, last_page=68, dpi=200) full_text = "" for i, img in enumerate(images): text = pytesseract.image_to_string(img) full_text += f"\n\n=== PDF PAGE {i+59} ===\n" + text with open('/home/daytona/workspace/ch5_puberty.txt', 'w') as f: f.write(full_text) print("Chapter 5 saved. Pages extracted:", len(images)) print(full_text[:500]) EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" # Find Chapter 7 (Neuroendocrinology) and Chapter 8 (Menstruation) # TOC showed Ch7 pages 53-65, Ch8 pages ~66+ # Need to find PDF page equivalents - Ch5 was text pg 39, PDF pg 59, so offset ~20 # Ch7 text pg 53 -> PDF ~73, Ch8 text pg 66 -> PDF ~86 print("Scanning for Chapter 7 and 8 headers...") images = convert_from_path(pdf_path, first_page=72, last_page=80, dpi=180) for i, img in enumerate(images): text = pytesseract.image_to_string(img) if 'Neuro' in text or 'endocrin' in text.lower() or 'Menst' in text or 'Chapter' in text: print(f"=== PDF PAGE {i+72} ===") print(text[:600]) print() EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" # OCR Chapter 7 (Neuroendocrinology) - PDF pages 73-87 print("=== EXTRACTING CHAPTER 7 (NEUROENDOCRINOLOGY) ===") images = convert_from_path(pdf_path, first_page=73, last_page=87, dpi=200) full_text = "" for i, img in enumerate(images): text = pytesseract.image_to_string(img) full_text += f"\n\n=== PDF PAGE {i+73} ===\n" + text with open('/home/daytona/workspace/ch7_neuroendo.txt', 'w') as f: f.write(full_text) print(f"Chapter 7 saved. Pages: {len(images)}") print(full_text[:300]) EOF

ls /home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" # First get total pages and scan TOC to find chapter page numbers images = convert_from_path(pdf_path, first_page=15, last_page=16, dpi=200) for i, img in enumerate(images): text = pytesseract.image_to_string(img) print(f"=== TOC PAGE {i+15} ===") print(text) print() EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract import os pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" os.makedirs('/home/daytona/workspace/dutta_ocr', exist_ok=True) # Extract Chapter 5 (Puberty): text pp 39-45 -> PDF pp ~59-65 # Extract Chapter 7 (Neuroendo): text pp 53-65 -> PDF pp ~73-85 # Extract Chapter 8 (Menstruation): text pp 66-79 -> PDF pp ~86-100 # All together: PDF pages 59-100 print("Starting OCR of pages 59-100...") images = convert_from_path(pdf_path, first_page=59, last_page=100, dpi=200) all_text = {} for i, img in enumerate(images): pg = i + 59 text = pytesseract.image_to_string(img) all_text[pg] = text print(f"Page {pg} done ({len(text)} chars)") # Save raw with open('/home/daytona/workspace/dutta_ocr/raw_pages_59_100.txt', 'w') as f: for pg, text in all_text.items(): f.write(f"\n\n{'='*60}\nPDF PAGE {pg}\n{'='*60}\n") f.write(text) print("\nAll done! Saved to raw_pages_59_100.txt") EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract, os pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" os.makedirs('/home/daytona/workspace/dutta_ocr', exist_ok=True) # Batch 1: Chapter 5 Puberty PDF pages 59-68 images = convert_from_path(pdf_path, first_page=59, last_page=68, dpi=180) text_b1 = "" for i, img in enumerate(images): text_b1 += f"\n\n=== PDF PAGE {i+59} ===\n" + pytesseract.image_to_string(img) with open('/home/daytona/workspace/dutta_ocr/ch5_puberty.txt', 'w') as f: f.write(text_b1) print("Batch 1 done (Ch5 Puberty pp 59-68)") EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract, os pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" # Batch 2: Chapter 7 Neuroendocrinology PDF pages 73-85 images = convert_from_path(pdf_path, first_page=73, last_page=85, dpi=180) text_b2 = "" for i, img in enumerate(images): text_b2 += f"\n\n=== PDF PAGE {i+73} ===\n" + pytesseract.image_to_string(img) with open('/home/daytona/workspace/dutta_ocr/ch7_neuroendo.txt', 'w') as f: f.write(text_b2) print("Batch 2 done (Ch7 Neuroendo pp 73-85)") EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract, os pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" # Smaller batch: Ch7 pages 73-79 only images = convert_from_path(pdf_path, first_page=73, last_page=79, dpi=150) text = "" for i, img in enumerate(images): text += f"\n\n=== PDF PAGE {i+73} ===\n" + pytesseract.image_to_string(img) with open('/home/daytona/workspace/dutta_ocr/ch7_neuroendo_a.txt', 'w') as f: f.write(text) print("Done pp73-79") EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract, os pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" # Ch7 pages 80-86 images = convert_from_path(pdf_path, first_page=80, last_page=86, dpi=150) text = "" for i, img in enumerate(images): text += f"\n\n=== PDF PAGE {i+80} ===\n" + pytesseract.image_to_string(img) with open('/home/daytona/workspace/dutta_ocr/ch7_neuroendo_b.txt', 'w') as f: f.write(text) print("Done pp80-86") EOF

python3 << 'EOF' from pdf2image import convert_from_path import pytesseract, os pdf_path = "/home/daytona/workspace/attachments/7f0da9df-a16f-4bfa-b954-ac39f22f687d/DC Dutta's Textbook of Gynecology_11zon (1).pdf" # Ch8 Menstruation pages 87-95 images = convert_from_path(pdf_path, first_page=87, last_page=95, dpi=150) text = "" for i, img in enumerate(images): text += f"\n\n=== PDF PAGE {i+87} ===\n" + pytesseract.image_to_string(img) with open('/home/daytona/workspace/dutta_ocr/ch8_menstruation.txt', 'w') as f: f.write(text) print("Done pp87-95") EOF