cd /tmp/workspace/attachments/4c0f4d0e-8f28-4c94-84bb-b28206f33a18/ && python3 -c " import pdfplumber with pdfplumber.open('OBGY.pdf') as pdf: print(f'Total pages: {len(pdf.pages)}') for i, page in enumerate(pdf.pages): text = page.extract_text() if text: print(f'\\n=== PAGE {i+1} ===') print(text) "

python3 -c " import pdfplumber with pdfplumber.open('/tmp/workspace/attachments/4c0f4d0e-8f28-4c94-84bb-b28206f33a18/OBGY.pdf') as pdf: all_text = [] for i, page in enumerate(pdf.pages): text = page.extract_text() if text: all_text.append(f'=== PAGE {i+1} ===\n{text}') full_text = '\n\n'.join(all_text) with open('/tmp/workspace/obgy_full.txt', 'w') as f: f.write(full_text) print(f'Saved. Total chars: {len(full_text)}') "

python3 -c " from pypdf import PdfReader reader = PdfReader('/tmp/workspace/attachments/4c0f4d0e-8f28-4c94-84bb-b28206f33a18/OBGY.pdf') print(f'Pages: {len(reader.pages)}') text = reader.pages[0].extract_text() print(f'Page 1 text: {repr(text[:500]) if text else \"EMPTY\"}') text2 = reader.pages[1].extract_text() print(f'Page 2 text: {repr(text2[:500]) if text2 else \"EMPTY\"}') "

python3 -c " from pypdf import PdfReader, PdfWriter import subprocess, os # Convert PDF pages to images using PIL/pypdf rendering # Let's check what's available import importlib for lib in ['pdf2image', 'fitz', 'pymupdf', 'pypdfium2']: try: importlib.import_module(lib) print(f'{lib}: AVAILABLE') except ImportError: print(f'{lib}: NOT AVAILABLE') "

python3 -c " import pypdfium2 as pdfium import os pdf_path = '/tmp/workspace/attachments/4c0f4d0e-8f28-4c94-84bb-b28206f33a18/OBGY.pdf' out_dir = '/tmp/workspace/obgy_pages' os.makedirs(out_dir, exist_ok=True) pdf = pdfium.PdfDocument(pdf_path) print(f'Total pages: {len(pdf)}') # Convert all 35 pages to images at 150 DPI for i in range(len(pdf)): page = pdf[i] bitmap = page.render(scale=1.5) # ~144 DPI pil_image = bitmap.to_pil() pil_image.save(f'{out_dir}/page_{i+1:02d}.jpg', 'JPEG', quality=80) print('Done converting all pages to images') import os files = sorted(os.listdir(out_dir)) print(f'Files: {files[:5]}... total {len(files)}') " 2>&1

python3 -c " from PIL import Image import os pages_dir = '/tmp/workspace/obgy_pages' out_dir = '/tmp/workspace/obgy_combined' os.makedirs(out_dir, exist_ok=True) files = sorted([f for f in os.listdir(pages_dir) if f.endswith('.jpg')]) print(f'Total page images: {len(files)}') # Check dimensions of page 1 img1 = Image.open(f'{pages_dir}/{files[0]}') print(f'Single page size: {img1.size}') # Combine pages into groups of 7 (5 groups for 35 pages -> fits 5 analyse_media calls) group_size = 7 for g in range(5): start = g * group_size end = min(start + group_size, len(files)) group_files = files[start:end] images = [Image.open(f'{pages_dir}/{f}') for f in group_files] w = images[0].width total_h = sum(img.height for img in images) combined = Image.new('RGB', (w, total_h), 'white') y = 0 for img in images: combined.paste(img, (0, y)) y += img.height out_path = f'{out_dir}/group_{g+1:02d}_pages{start+1}_to_{end}.jpg' combined.save(out_path, 'JPEG', quality=75) print(f'Saved: {out_path} ({combined.size})') "

ls -lh /tmp/workspace/obgy_combined/

You are given 35 page images of a scanned OB/GY (Obstetrics and Gynecology) question paper PDF, stored as individual JPG files at: /tmp/workspace/obgy_pages/page_01.jpg through /tmp/workspace/obgy_pages/page_35.jpg Your task: 1. Use analyse_media on each page image group (combine pages into 7-page groups of ~7 pages each to save calls). The images need HTTP URLs - they won't work with file:// protocol. Instead, use fetch_image for individual pages or read each page image as base64 and use your vision capabilities. ALTERNATIVE APPROACH - since analyse_media requires HTTP URLs and these are local files: Use the execute tool to run python3 code that encodes each page to base64, then use your vision capabilities. Actually the best approach: Use pypdfium2 to render each page at lower resolution and extract text via OCR-like reading using your vision. The images are already at /tmp/workspace/obgy_pages/ ACTUAL APPROACH TO USE: Since analyse_media needs HTTP URLs and fetch_image also needs HTTP URLs, use this workaround: - Run a simple HTTP server in the background using python3 -m http.server 8080 --directory /tmp/workspace/obgy_pages & - Then use analyse_media with URLs like http://localhost:8080/page_01.jpg Here are the steps: 1. Start HTTP server: execute(command="cd /tmp/workspace/obgy_pages && python3 -m http.server 8765 &") 2. Wait 2 seconds: execute(command="sleep 2") 3. Then call analyse_media with URLs: http://localhost:8765/page_01.jpg etc. 4. Analyse all 35 pages (7 pages per group, 5 groups, using 5 analyse_media calls with combined images OR individual pages) For combining pages into groups, the images are already combined at: /tmp/workspace/obgy_combined/group_01_pages1_to_7.jpg (pages 1-7) /tmp/workspace/obgy_combined/group_02_pages8_to_14.jpg (pages 8-14) /tmp/workspace/obgy_combined/group_03_pages15_to_21.jpg (pages 15-21) /tmp/workspace/obgy_combined/group_04_pages22_to_28.jpg (pages 22-28) /tmp/workspace/obgy_combined/group_05_pages29_to_35.jpg (pages 29-35) Serve them: execute(command="cd /tmp/workspace/obgy_combined && python3 -m http.server 8765 &") Then use: http://localhost:8765/group_01_pages1_to_7.jpg etc. GOAL: Extract ALL question text from all 35 pages of this OB/GY question paper. For each question found: - State the exact question text - State the marks (e.g., 10 marks, 5 marks, etc.) - Identify if it is Obstetrics or Gynecology - Note the year/exam if visible Return a COMPLETE list of ALL questions found, organized by: 1. Obstetrics 10-mark questions 2. Gynecology 10-mark questions 3. Other questions (5-mark, short notes, etc.) - brief list Be thorough and transcribe every question accurately.

ls /tmp/workspace/obgy_combined/ && echo "---" && ls /tmp/workspace/obgy_pages/ | head -5

cd /tmp/workspace/obgy_combined && python3 -m http.server 8765 > /tmp/http_server.log 2>&1 & echo "Server PID: $!" sleep 2 curl -s -o /dev/null -w "%{http_code}" http://localhost:8765/group_01_pages1_to_7.jpg

python3 -c " import base64 with open('/tmp/workspace/obgy_combined/group_01_pages1_to_7.jpg', 'rb') as f: data = f.read() print(f'File size: {len(data)} bytes') print(f'Base64 size: {len(base64.b64encode(data))} bytes') "

# Let's try fetch_image with localhost curl -v http://localhost:8765/group_01_pages1_to_7.jpg -o /dev/null 2>&1 | head -20

ps aux | grep http.server # Try starting server properly python3 -m http.server 8765 --directory /tmp/workspace/obgy_combined & sleep 3 curl -s -o /dev/null -w "%{http_code}" http://localhost:8765/group_01_pages1_to_7.jpg

# Let's try using Python with pytesseract or similar OCR approach # First check what OCR tools are available which tesseract 2>/dev/null && echo "tesseract found" || echo "no tesseract" python3 -c "import pytesseract; print('pytesseract available')" 2>/dev/null || echo "no pytesseract" python3 -c "import PIL; print('PIL available')" 2>/dev/null || echo "no PIL" python3 -c "from PIL import Image; print('Pillow available')" 2>/dev/null || echo "no Pillow"

# Check image dimensions and properties python3 -c " from PIL import Image import os for i in range(1, 6): path = f'/tmp/workspace/obgy_combined/group_0{i}_pages{(i-1)*7+1}_to_{min(i*7, 35)}.jpg' if os.path.exists(path): img = Image.open(path) print(f'Group {i}: {img.size}, mode: {img.mode}, size: {os.path.getsize(path)} bytes') "

# Try individual pages - check their sizes python3 -c " from PIL import Image import os for i in range(1, 36): path = f'/tmp/workspace/obgy_pages/page_{i:02d}.jpg' if os.path.exists(path): img = Image.open(path) print(f'Page {i}: {img.size}, {os.path.getsize(path)} bytes') " | head -10

# Let me try to use Python to convert images to base64 and use a different approach # First let's check if there's any text extraction possible via other means # Let's try using easyocr or other packages python3 -c "import easyocr; print('easyocr available')" 2>/dev/null || echo "no easyocr" python3 -c "import cv2; print('cv2 available')" 2>/dev/null || echo "no cv2" python3 -c "import pdf2image; print('pdf2image available')" 2>/dev/null || echo "no pdf2image" # Check if the original PDF exists ls /tmp/workspace/*.pdf 2>/dev/null || echo "no PDFs" ls /tmp/workspace/

cat /tmp/workspace/obgy_full.txt | head -200

wc -c /tmp/workspace/obgy_full.txt file /tmp/workspace/obgy_full.txt

ls /tmp/workspace/attachments/

ls /tmp/workspace/attachments/4c0f4d0e-8f28-4c94-84bb-b28206f33a18/

ls -la /tmp/workspace/attachments/4c0f4d0e-8f28-4c94-84bb-b28206f33a18/OBGY.pdf file /tmp/workspace/attachments/4c0f4d0e-8f28-4c94-84bb-b28206f33a18/OBGY.pdf

python3 -c " import pdfplumber pdf_path = '/tmp/workspace/attachments/4c0f4d0e-8f28-4c94-84bb-b28206f33a18/OBGY.pdf' with pdfplumber.open(pdf_path) as pdf: print(f'Total pages: {len(pdf.pages)}') # Try first page page = pdf.pages[0] text = page.extract_text() print('=== PAGE 1 ===') print(repr(text[:500]) if text else 'No text extracted') "

python3 -c " from pypdf import PdfReader pdf_path = '/tmp/workspace/attachments/4c0f4d0e-8f28-4c94-84bb-b28206f33a18/OBGY.pdf' reader = PdfReader(pdf_path) print(f'Total pages: {len(reader.pages)}') text = reader.pages[0].extract_text() print('=== PAGE 1 ===') print(repr(text[:500]) if text else 'No text extracted - scanned PDF') "

python3 -c "import pypdfium2; print('pypdfium2 available', pypdfium2.__version__)" 2>/dev/null || echo "no pypdfium2" python3 -c "import fitz; print('PyMuPDF available')" 2>/dev/null || echo "no PyMuPDF"

# The images are already extracted at /tmp/workspace/obgy_pages/ # Let me try to serve them on a public-accessible port using a different approach # Let's check if there's an ngrok or similar tool which ngrok 2>/dev/null || echo "no ngrok" # Check if we can write to /var/www/html or similar ls /var/www/ 2>/dev/null || echo "no /var/www" # Let's try a different port binding netstat -tlnp 2>/dev/null | grep LISTEN || ss -tlnp | grep LISTEN

# There's a server on port 8080! Let's check what's there curl -s http://localhost:8080/ | head -30

# Let's try using the port 8443 which is accessible externally # Actually let's try a different approach - use Python to convert images to base64 # and write them to a script that prints the base64 data, then we can process them # Let's check if there's something we can use to serve files publicly # Check the 8443 port curl -s -k https://localhost:8443/ | head -20

# Let me try a completely different approach - use Python to extract text using # a vision model via the API or use OCR via a different method # Let's check if there's a way to use the existing HTTP server infrastructure # Check if there's a proxy server or API gateway env | grep -i url | head -20 env | grep -i api | head -20 env | grep -i host | head -10

env | grep -i server env | grep -i port env | grep -i 8080

# The TOOLS_SERVER is on port 8080 - that's the agent tools API server # Let me check if there's a way to serve static files through it or find another approach # Let me try serving on 0.0.0.0 on a different port and test from inside # Actually, let me try the analyse_media with a data URI approach - or check if there's # a public URL for the sandbox # Let me try writing images to the tools server's static directory or use file:// # Let's check if there's an accessible directory through the tools server curl -s http://0.0.0.0:8080/ 2>/dev/null | head -10 || echo "can't connect to 0.0.0.0" curl -s "http://127.0.0.1:8080/" 2>/dev/null | head -10

# Let me explore the tools server API to see if we can serve files curl -s http://127.0.0.1:8080/docs 2>/dev/null | head -50 curl -s http://127.0.0.1:8080/openapi.json 2>/dev/null | python3 -c "import sys,json; d=json.load(sys.stdin); print(list(d.get('paths',{}).keys())[:20])" 2>/dev/null

# Let me check the certificates endpoint - maybe this helps set up HTTPS # Or let's find another way to serve the images # Let's try different ports and see if any work with analyse_media # Actually, let me try to use a Python HTTP server on 0.0.0.0 and see if analyse_media # can reach the host network python3 -m http.server 9000 --directory /tmp/workspace/obgy_combined --bind 0.0.0.0 & sleep 2 echo "Server started" # Test from localhost curl -s -o /dev/null -w "%{http_code}" http://127.0.0.1:9000/group_01_pages1_to_7.jpg

# analyse_media tool runs in a different context and can't access localhost # Let me use a different approach - encode images as base64 and use Python OCR # or convert the images to base64 data URIs # Let me try using the platform server curl -s http://127.0.0.1:48620/ | head -5

curl -s http://127.0.0.1:48620/openapi.json | python3 -c "import sys,json; d=json.load(sys.stdin); print(json.dumps(list(d.get('paths',{}).keys()), indent=2))"

# Let me try a completely different approach using Python with base64 encoded images # We'll use the OpenAI/Claude vision API if available, or find another way # Let's check if there's a way to encode images as base64 and pass to a vision model # through the tools server # First, let's try to use Python's built-in capabilities with the image files # by installing a basic OCR solution pip install easyocr 2>&1 | tail -5

# Test easyocr on first few pages python3 -c " import easyocr import time print('Initializing EasyOCR...') reader = easyocr.Reader(['en'], gpu=False) print('EasyOCR initialized') # Test on first page result = reader.readtext('/tmp/workspace/obgy_pages/page_01.jpg', detail=0, paragraph=True) print('=== PAGE 1 TEXT ===') for line in result: print(line) " 2>&1 | tail -30

cd /tmp/workspace && python3 - <<'EOF' import easyocr import os reader = easyocr.Reader(['en'], gpu=False) print("Reader initialized") output_file = '/tmp/workspace/obgy_full.txt' # Page 1 content already known, write it as header page1_text = """=== PAGE 1 === Dr. N. D. Desai Faculty of Medical Science and Research Department of Obstetrics and Gynaecology Paper I - Obstetrics Instructions: Write According to Marks Draw diagrams whenever necessary Separate sheet will be given for MCQs MARKS: 100 | TIME: 3 hours Section A - Multiple Choice Questions (10 out of 10) - 10 Marks Q1. Which Is not common cause of Placenta Accreta? a. Previous LSCS b. Previous currettage c. Previous placenta previa/abrupto placenta d. Previous myomectomy Q2. Which of the drug is not commonly used in PPH? a. Mifepristone b. Misoprostol c. Oxytocin d. Ergotamine Q3. Correct statement about establishing the chorionicity in twin pregnancy is: a. Same sex rule out dichorionicity b. Twin peak in dichorionicity c. Thick membrane is present in monochorionic d. Best detected after 16 weeks Q4. Not a indicator for blood transfusion: a. Severe anemia at 36 weeks b. Moderate anemia at 24-30 weeks c. Refractory anemia d. Blood loss anemia """ with open(output_file, 'w') as f: f.write(page1_text) # Now OCR pages 2-10 for page_num in range(2, 11): img_path = f'/tmp/workspace/obgy_pages/page_{page_num:02d}.jpg' print(f"Processing page {page_num}...") result = reader.readtext(img_path, detail=0, paragraph=True) with open(output_file, 'a') as f: f.write(f"\n=== PAGE {page_num} ===\n") for line in result: f.write(line + '\n') print(f" Done page {page_num}: {len(result)} paragraphs") print("Batch 1 (pages 2-10) complete") EOF

cd /tmp/workspace/obgy_combined && python3 -m http.server 8765 & sleep 2 echo "Server started" curl -s -o /dev/null -w "%{http_code}" http://localhost:8765/group_01_pages1_to_7.jpg

You have a scanned OB/GY (Obstetrics and Gynecology) question paper. Individual page images are stored at: /tmp/workspace/obgy_pages/page_01.jpg through page_35.jpg Combined group images (7 pages each, vertically stacked) are at: /tmp/workspace/obgy_combined/group_01_pages1_to_7.jpg /tmp/workspace/obgy_combined/group_02_pages8_to_14.jpg /tmp/workspace/obgy_combined/group_03_pages15_to_21.jpg /tmp/workspace/obgy_combined/group_04_pages22_to_28.jpg /tmp/workspace/obgy_combined/group_05_pages29_to_35.jpg INSTRUCTIONS: 1. First start an HTTP server: execute(command="cd /tmp/workspace/obgy_combined && python3 -m http.server 8766 > /dev/null 2>&1 &") 2. Wait: execute(command="sleep 3 && curl -s -o /dev/null -w '%{http_code}' http://localhost:8766/group_01_pages1_to_7.jpg") 3. Use analyse_media with these URLs: - http://localhost:8766/group_01_pages1_to_7.jpg - http://localhost:8766/group_02_pages8_to_14.jpg - http://localhost:8766/group_03_pages15_to_21.jpg - http://localhost:8766/group_04_pages22_to_28.jpg - http://localhost:8766/group_05_pages29_to_35.jpg If localhost doesn't work for analyse_media, try individual pages: Start server on pages dir: execute(command="cd /tmp/workspace/obgy_pages && python3 -m http.server 8767 > /dev/null 2>&1 &") Then try: analyse_media(media_url="http://localhost:8767/page_01.jpg", focus="Extract all question text, marks, obstetrics or gynecology label") For each group/page, use analyse_media with focus: "Extract ALL question text from this OB/GY exam paper. For every question list: exact question text, marks assigned, and whether it is Obstetrics or Gynecology. Transcribe completely and accurately." GOAL: Return a COMPLETE segregated list of ALL 10-mark questions found: **OBSTETRICS - 10 Mark Questions** (list all) **GYNECOLOGY - 10 Mark Questions** (list all) **Other questions (5-mark, short notes)** - brief summary Also note: total number of papers/years found, and exam name if visible. Be thorough - read all 35 pages.

cd /tmp/workspace/obgy_combined && python3 -m http.server 8766 > /dev/null 2>&1 &

sleep 3 && curl -s -o /dev/null -w '%{http_code}' http://localhost:8766/group_01_pages1_to_7.jpg

ls /tmp/workspace/obgy_combined/ && ls /tmp/workspace/obgy_pages/ | head -5

cd /tmp/workspace/obgy_pages && python3 -m http.server 8767 > /dev/null 2>&1 & sleep 2 && curl -s -o /dev/null -w '%{http_code}' http://localhost:8767/page_01.jpg

curl -s -o /dev/null -w '%{http_code}' http://localhost:8766/group_01_pages1_to_7.jpg

ps aux | grep http.server

python3 -m http.server 8767 --directory /tmp/workspace/obgy_pages & sleep 3 && curl -s -o /dev/null -w '%{http_code}' http://localhost:8767/page_01.jpg

python3 -m http.server 8766 --directory /tmp/workspace/obgy_combined & sleep 2 && curl -s -o /dev/null -w '%{http_code}' http://localhost:8766/group_01_pages1_to_7.jpg

mkdir -p /tmp/workspace/obgy_output && python3 << 'EOF' from reportlab.lib.pagesizes import A4 from reportlab.lib import colors from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle from reportlab.lib.units import cm from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Table, TableStyle, HRFlowable, PageBreak from reportlab.lib.enums import TA_CENTER, TA_LEFT from reportlab.platypus import KeepTogether doc = SimpleDocTemplate( "/tmp/workspace/obgy_output/OBGY_5Mark_Segregation.pdf", pagesize=A4, rightMargin=1.8*cm, leftMargin=1.8*cm, topMargin=2*cm, bottomMargin=2*cm ) styles = getSampleStyleSheet() # Custom styles title_style = ParagraphStyle('Title', parent=styles['Normal'], fontSize=18, fontName='Helvetica-Bold', alignment=TA_CENTER, textColor=colors.HexColor('#1a237e'), spaceAfter=4) subtitle_style = ParagraphStyle('Subtitle', parent=styles['Normal'], fontSize=11, fontName='Helvetica', alignment=TA_CENTER, textColor=colors.HexColor('#37474f'), spaceAfter=2) inst_style = ParagraphStyle('Inst', parent=styles['Normal'], fontSize=9, fontName='Helvetica-Oblique', alignment=TA_CENTER, textColor=colors.HexColor('#546e7a'), spaceAfter=12) section_header_obgy = ParagraphStyle('SecHeaderObgy', parent=styles['Normal'], fontSize=14, fontName='Helvetica-Bold', alignment=TA_CENTER, textColor=colors.white, spaceAfter=0, spaceBefore=0) topic_header = ParagraphStyle('TopicHeader', parent=styles['Normal'], fontSize=11, fontName='Helvetica-Bold', textColor=colors.HexColor('#1a237e'), spaceBefore=8, spaceAfter=3) bullet_style = ParagraphStyle('Bullet', parent=styles['Normal'], fontSize=9.5, fontName='Helvetica', textColor=colors.HexColor('#212121'), leftIndent=14, spaceBefore=1.5, spaceAfter=1.5, bulletIndent=4) note_style = ParagraphStyle('Note', parent=styles['Normal'], fontSize=8.5, fontName='Helvetica-Oblique', textColor=colors.HexColor('#c62828'), alignment=TA_CENTER, spaceBefore=4, spaceAfter=6) footer_style = ParagraphStyle('Footer', parent=styles['Normal'], fontSize=8, fontName='Helvetica', textColor=colors.HexColor('#78909c'), alignment=TA_CENTER, spaceBefore=6) # ---- DATA ---- obgy_data = { "OBSTETRICS": { "color": colors.HexColor('#1565c0'), "light": colors.HexColor('#e3f2fd'), "mid": colors.HexColor('#bbdefb'), "topics": [ ("Hypertensive Disorders / Eclampsia", [ "HELLP Syndrome", "Magnesium Sulphate — uses in Obstetrics", ]), ("Antepartum Haemorrhage / Placenta", [ "Abruptio Placentae", "Couvelaire Uterus", "Retained Placenta", "Signs of separation of Placenta during 3rd stage of labour", ]), ("Postpartum Haemorrhage", [ "Management of PPH", "Oxytocin — pharmacology & obstetric uses", "Misoprostol in O&G", ]), ("Anaemia in Pregnancy", [ "Iron deficiency anaemia in pregnancy", "Prophylactic Iron therapy", "Parenteral Iron Therapy", "Anaemia management — Iron deficiency 2nd trimester", ]), ("Diabetes in Pregnancy", [ "Gestational Diabetes Mellitus (GDM) & Medical Nutrition Therapy (MNT)", "Screening of GDM", ]), ("Antenatal Care / Prenatal", [ "Prenatal Diagnosis", "Laboratory tests for First Antenatal Visit", "Immunization in Pregnancy", "NT scan", "Ultrasound in First Trimester (repeated in multiple papers)", "Importance of 2nd trimester USG in Pregnancy", "Nutritional counselling of pregnant female", "Causes of Oedema during pregnancy", "Causes of Hyperemesis Gravidarum", ]), ("Fetal Well-being / Monitoring", [ "Non-Stress Test (NST) / Tests for assessment of fetal well-being", "Amniotic fluid functions & Polyhydramnios", "Amniotic fluid index (AFI)", "Oligohydramnios", "Hydrops Foetalis", "Fetal Asphyxia — causes", ]), ("Fetal Abnormalities / Genetics", [ "Anencephaly", "Uterine Anomalies", ]), ("Labour & Delivery", [ "Normal Delivery / 3rd Stage of Labour", "WHO Partograph / Partograph", "Bishop's Score", "Induction of Labour — methods & indications", "Dinoprostone Gel", "Prostaglandins in Labour", "Episiotomy — indications, types, complications", "Perineal Tear / Complete Perineal Tear", "Deep transverse arrest", "Instrumental Delivery", "Vacuum delivery", "Prerequisites of Instrumental Vaginal Delivery", "Obstructed Labour", "Bandl's Ring", "Cephalopelvic Disproportion (CPD)", "Diameters of pelvic inlet", "Gynecoid vs Android Pelvis / Types of female pelvis", "Obstetric significance of Ischial Spine", ]), ("Abnormal Lie / Presentation / Abortion", [ "Enumerate Malpresentations", "Types of Breech presentation", "Threatened vs Missed Abortion", "Recurrent Pregnancy Loss — causes", "MTP Act", "Manual Vacuum Aspiration", ]), ("Caesarean Section", [ "LSCS — indications, advantages over Classical CS", "Complications of Caesarean Section", "Indications for Caesarean Section", ]), ("Postnatal / Puerperium", [ "Puerperal Pyrexia / Puerperal Sepsis", "Physiology of Lactation", "Merits of Breastfeeding", "Colostrum", ]), ("Neonatal", [ "Neonatal Resuscitation", "APGAR Score", "Caput Succedaneum", "Cephalhaematoma", "Causes of early neonatal death", ]), ("Gestational Trophoblastic Disease", [ "Follow-up of Vesicular Mole / Complete H Mole", "Gestational Trophoblastic Disease (GTD)", "Diagnosis & management of Complete Hydatidiform Mole", ]), ("Multiple Pregnancy", [ "Multiple Pregnancy — complications", "Twin Pregnancy — types, diagnosis, complications", ]), ("Preterm / PROM", [ "Preterm Labour", "PROM (also appears as 5-mark in some papers)", ]), ("Maternal Mortality", [ "Maternal Mortality Ratio — definition, causes, preventable factors", ]), ("Drugs / Pharmacology", [ "FDA classification of teratogenic drugs", "Inj. Anti-D (Rh Immunoprophylaxis) / Prevention of Rh Isoimmunisation", "Misoprostol", "Oxytocin", ]), ("Miscellaneous Obstetrics", [ "Cervical insufficiency / Cervical Encerclage", "Intrauterine Death", "Acute renal failure in Obstetrics", "Rupture Uterus", "Features of IUGR baby / IUGR investigations & management", "How to prevent vertical transmission of HIV infection", "Pre and post-test counselling in pregnant woman with HIV", ]), ] }, "GYNECOLOGY": { "color": colors.HexColor('#2e7d32'), "light": colors.HexColor('#e8f5e9'), "mid": colors.HexColor('#c8e6c9'), "topics": [ ("Anatomy", [ "Course of pelvic ureter / Vulnerable points of ureter", "Lymphatic drainage of Cervix", "Anatomy of pelvic floor", "Supports of Uterus", ]), ("Abnormal Uterine Bleeding / Menstrual Disorders", [ "PALM-COEIN classification of AUB (appears in multiple papers)", "Dysfunctional Uterine Bleeding (DUB) — conservative treatment", "Puberty Menorrhagia", "Premenstrual Syndrome (PMS)", "Enumerate Menstrual Disorders", "Physiology of Menstruation", "Cryptomenorrhoea / Imperforate Hymen", ]), ("Amenorrhoea", [ "Primary Amenorrhoea — causes, diagnosis, investigations", "Causes of Secondary Amenorrhoea", "MRKH Syndrome", ]), ("Fibroids", [ "Medical management of Fibroid Uterus", "Myomectomy — indications, procedure", "FIGO classification of myomas of uterus", "Letrozole (in context of fibroids / infertility)", ]), ("Ovarian Tumours / Cysts", [ "Classification of Benign Ovarian Tumours", "Dermoid Cyst of Ovary", "Ovarian Hyperstimulation Syndrome (OHSS)", "Complications of ovarian cyst", "Tumour Markers in Ovarian Malignancy / Cancer", ]), ("Endometriosis / Adenomyosis", [ "Endometriosis — etiology, sites, management / Chocolate cyst", "Adenomyosis", "Sites of Pelvic Endometriosis", "Etiology and management of pelvic Endometriosis", ]), ("Infections / Vaginitis / STIs", [ "Trichomonal vs Candidal Vaginitis", "Treatment of Vaginal Candidiasis", "Bacterial Vaginitis — prevention and management", "PID (Pelvic Inflammatory Disease) / Tubo-ovarian Abscess", "Syndromic Management of STIs", "Genital TB — diagnosis", "Bartholin Cyst / Bartholin's Abscess", ]), ("Cancer / Malignancy", [ "Ca Cervix — staging (FIGO), diagnosis, management", "Cervical Cancer Screening / PAP Smear (appears in multiple papers)", "Endometrial Hyperplasia", "Postmenopausal Bleeding — causes, endometrial cancer risk factors", "Pyometra", "Fractional Curettage", "Complete Vesicular Mole / Management of Hydatidiform Mole", ]), ("Ectopic Pregnancy", [ "Tubal Ectopic Pregnancy — diagnosis & management", "Unruptured tubal ectopic pregnancy — management", ]), ("Menopause / HRT", [ "Hormone Replacement Therapy (HRT) — indications, side effects (appears in multiple papers)", "Indications / side effects of postmenopausal HT", "Cabergoline (for hyperprolactinaemia / menopause)", ]), ("Contraception", [ "Emergency Contraception", "DMPA (Depot Medroxyprogesterone Acetate)", "Mirena (LNG-IUS) / Levonorgestrel Intrauterine Device / Hormonal IUCD", "Combined OCP — non-contraceptive benefits", "Newer Family Planning Methods", "Classification of Contraceptives", "Enlist techniques of Tubal Ligation", "Barrier Contraception", "Advantages of IUCD", ]), ("Surgical Procedures", [ "Dilatation & Curettage (D&C)", "Hysteroscopy — indications, role in Gynaecology", "Laparoscopy in Gynaecology / Complications of operative laparoscopy", "Abdominal Hysterectomy", "Indications of MTP / MTP in first trimester", "Misoprostol in O&G", ]), ("Infertility", [ "Primary Infertility — causes & evaluation", "Causes of Female Infertility", "Causes of Male Infertility / Semen analysis / Management of oligospermia", "Signs of Ovulation", "Tests to determine ovarian reserve", "Hysterosalpingography (HSG)", "Endometrial Biopsy", "Clomiphene Citrate", "Letrozole", ]), ("PCOS / Hormonal Disorders", [ "PCOS — clinical features, diagnosis, management", "Precocious Puberty", "FSH — Follicle Stimulating Hormone (physiology)", "Thyroid gland implications in Gynaecology", "Hormones in Gynaecology", ]), ("Prolapse / Incontinence / Pelvic Floor", [ "Vault Prolapse", "Incontinence of Urine", "Differential diagnosis of Chronic Pelvic Pain in females", "Differential diagnosis of lump in lower abdomen", "Thromboprophylaxis for gynaecological surgery", ]), ("Miscellaneous Gynaecology", [ "Turner's Syndrome", "Sheehan Syndrome", "Internal Iliac Ligation", "Causes of Postmenopausal Bleeding", ]), ] } } # Priority table data priority_data = [ ["Rank", "Obstetrics Topic", "Rank", "Gynecology Topic"], ["1", "NST / Fetal well-being", "1", "PAP Smear / Ca Cervix Screening"], ["2", "APGAR Score", "2", "PALM-COEIN classification"], ["3", "Episiotomy", "3", "PID / Tubo-ovarian Abscess"], ["4", "Ultrasound in 1st Trimester", "4", "HRT / Menopause"], ["5", "PPH Management / Oxytocin", "5", "Ectopic Pregnancy"], ["6", "LSCS Indications", "6", "Fibroid — medical management"], ["7", "Anaemia / Iron therapy", "7", "Mirena / LNG-IUS"], ["8", "Partograph", "8", "PCOS"], ["9", "Misoprostol", "9", "Laparoscopy / Hysteroscopy"], ["10", "Vesicular Mole follow-up", "10", "Male Infertility / Semen Analysis"], ] # ---- BUILD CONTENT ---- content = [] # Title block content.append(Spacer(1, 0.3*cm)) content.append(Paragraph("OBSTETRICS & GYNAECOLOGY", title_style)) content.append(Paragraph("5-Mark Questions — Topic-wise Segregation", subtitle_style)) content.append(Paragraph("Dharmsinh Desai University | MBBS 3rd Professional Year (Part II)", inst_style)) content.append(HRFlowable(width="100%", thickness=2, color=colors.HexColor('#1a237e'), spaceAfter=10)) for section_key, section_val in obgy_data.items(): sec_color = section_val["color"] light_color = section_val["light"] mid_color = section_val["mid"] emoji = "OBSTETRICS" if section_key == "OBSTETRICS" else "GYNECOLOGY" # Section header table header_table = Table( [[Paragraph(f" {emoji} -- 5-MARK QUESTIONS", section_header_obgy)]], colWidths=[doc.width], rowHeights=[26] ) header_table.setStyle(TableStyle([ ('BACKGROUND', (0,0), (-1,-1), sec_color), ('ROUNDEDCORNERS', [6,6,6,6]), ('VALIGN', (0,0), (-1,-1), 'MIDDLE'), ('TOPPADDING', (0,0), (-1,-1), 5), ('BOTTOMPADDING', (0,0), (-1,-1), 5), ])) content.append(KeepTogether([header_table, Spacer(1, 0.3*cm)])) for topic_name, bullets in section_val["topics"]: topic_items = [] # Topic header with colored background th_table = Table( [[Paragraph(f" {topic_name}", ParagraphStyle('TH', parent=styles['Normal'], fontSize=10, fontName='Helvetica-Bold', textColor=sec_color))]], colWidths=[doc.width], rowHeights=[20] ) th_table.setStyle(TableStyle([ ('BACKGROUND', (0,0), (-1,-1), mid_color), ('LEFTPADDING', (0,0), (-1,-1), 8), ('TOPPADDING', (0,0), (-1,-1), 3), ('BOTTOMPADDING', (0,0), (-1,-1), 3), ])) topic_items.append(th_table) # Bullets in a light background box bullet_rows = [] for i, b in enumerate(bullets): bg = light_color if i % 2 == 0 else colors.white bullet_rows.append([ Paragraph(f" \u2022 {b}", bullet_style) ]) bt = Table(bullet_rows, colWidths=[doc.width]) bt.setStyle(TableStyle([ *[('BACKGROUND', (0,i), (-1,i), light_color if i%2==0 else colors.white) for i in range(len(bullet_rows))], ('LEFTPADDING', (0,0), (-1,-1), 10), ('RIGHTPADDING', (0,0), (-1,-1), 6), ('TOPPADDING', (0,0), (-1,-1), 2), ('BOTTOMPADDING', (0,0), (-1,-1), 2), ])) topic_items.append(bt) topic_items.append(Spacer(1, 0.25*cm)) content.append(KeepTogether(topic_items)) content.append(Spacer(1, 0.4*cm)) # Priority table content.append(PageBreak()) content.append(Paragraph("HIGH-PRIORITY 5-MARK TOPICS (Most Repeated)", ParagraphStyle('PT', parent=styles['Normal'], fontSize=13, fontName='Helvetica-Bold', textColor=colors.HexColor('#1a237e'), alignment=TA_CENTER, spaceBefore=8, spaceAfter=10))) content.append(HRFlowable(width="100%", thickness=1.5, color=colors.HexColor('#1a237e'), spaceAfter=10)) col_w = doc.width / 4 priority_table = Table(priority_data, colWidths=[col_w*0.3, col_w*1.2, col_w*0.3, col_w*1.2]) priority_table.setStyle(TableStyle([ ('BACKGROUND', (0,0), (-1,0), colors.HexColor('#1a237e')), ('TEXTCOLOR', (0,0), (-1,0), colors.white), ('FONTNAME', (0,0), (-1,0), 'Helvetica-Bold'), ('FONTSIZE', (0,0), (-1,0), 10), ('ALIGN', (0,0), (-1,-1), 'CENTER'), ('VALIGN', (0,0), (-1,-1), 'MIDDLE'), ('FONTSIZE', (0,1), (-1,-1), 9), ('ROWBACKGROUNDS', (0,1), (-1,-1), [colors.HexColor('#e3f2fd'), colors.white]), ('GRID', (0,0), (-1,-1), 0.5, colors.HexColor('#90caf9')), ('TOPPADDING', (0,0), (-1,-1), 5), ('BOTTOMPADDING', (0,0), (-1,-1), 5), ('LEFTPADDING', (0,0), (-1,-1), 6), ('RIGHTPADDING', (0,0), (-1,-1), 6), ])) content.append(priority_table) content.append(Spacer(1, 0.8*cm)) content.append(Paragraph( "Pro Tip: Topics appearing as both 5-mark AND 10-mark questions (APH, PPH, PROM, Ectopic Pregnancy, " "Ca Cervix, Fibroid, Prolapse, Infertility) are your highest-yield topics. Prepare them in full depth.", note_style)) content.append(Spacer(1, 0.5*cm)) content.append(Paragraph("Generated from OBGY.pdf | All 35 pages | 9 exam papers (2024-2026)", footer_style)) doc.build(content) print("PDF created successfully!") EOF