python3 << 'EOF' import pdfplumber pdf_path = "/tmp/workspace/attachments/e61ce95b-60de-4984-a6b1-b87562cb98f0/RD 2 cases.pdf" with pdfplumber.open(pdf_path) as pdf: print(f"Total pages: {len(pdf.pages)}\n") for page_num, page in enumerate(pdf.pages): print(f"--- PAGE {page_num + 1} ---") text = page.extract_text() print(text) print("\n") EOF

python3 << 'EOF' import pdfplumber import json pdf_path = "/tmp/workspace/attachments/e61ce95b-60de-4984-a6b1-b87562cb98f0/RD 2 cases.pdf" try: with pdfplumber.open(pdf_path) as pdf: print(f"Total pages: {len(pdf.pages)}") all_text = [] for page_num, page in enumerate(pdf.pages): print(f"\n=== PAGE {page_num + 1} ===") # Try different extraction methods text = page.extract_text() if text: print(text[:500]) all_text.append(text) # Also check if there are tables tables = page.extract_tables() if tables: print(f"Found {len(tables)} tables on this page") for i, table in enumerate(tables): print(f"Table {i+1}:") for row in table[:3]: # First 3 rows print(row) except Exception as e: print(f"Error: {e}") import traceback traceback.print_exc() EOF

python3 << 'EOF' from pypdf import PdfReader pdf_path = "/tmp/workspace/attachments/e61ce95b-60de-4984-a6b1-b87562cb98f0/RD 2 cases.pdf" try: reader = PdfReader(pdf_path) print(f"Total pages: {len(reader.pages)}\n") for page_num, page in enumerate(reader.pages): print(f"===== PAGE {page_num + 1} =====") text = page.extract_text() print(text) print("\n") except Exception as e: print(f"Error: {e}") import traceback traceback.print_exc() EOF

python3 << 'EOF' from pdf2image import convert_from_path import os pdf_path = "/tmp/workspace/attachments/e61ce95b-60de-4984-a6b1-b87562cb98f0/RD 2 cases.pdf" # Check if pdf2image is available try: images = convert_from_path(pdf_path, first_page=1, last_page=2) for i, image in enumerate(images): image.save(f'/tmp/workspace/page_{i+1}.png', 'PNG') print(f"Converted page {i+1} to image") except Exception as e: print(f"pdf2image not available: {e}") # Try using pypdf to get raw content from pypdf import PdfReader reader = PdfReader(pdf_path) print(f"PDF has {len(reader.pages)} pages") # Check page dimensions for i, page in enumerate(reader.pages): print(f"Page {i+1}: {page.mediabox}") EOF

python3 << 'EOF' from docx import Document doc_path = "/tmp/workspace/attachments/e61ce95b-60de-4984-a6b1-b87562cb98f0/RD 2 cases.docx" doc = Document(doc_path) print("=== DOCUMENT CONTENT ===\n") for para in doc.paragraphs: if para.text.strip(): print(para.text) # Also check tables if any if doc.tables: print("\n=== TABLES ===") for table_idx, table in enumerate(doc.tables): print(f"\nTable {table_idx + 1}:") for row in table.rows: row_data = [cell.text for cell in row.cells] print(" | ".join(row_data)) EOF

python3 << 'EOF' from docx import Document import zipfile doc_path = "/tmp/workspace/attachments/e61ce95b-60de-4984-a6b1-b87562cb98f0/RD 2 cases.docx" try: # Try direct extraction first doc = Document(doc_path) print(f"Document loaded. Paragraphs: {len(doc.paragraphs)}, Tables: {len(doc.tables)}") all_text = [] for para in doc.paragraphs: text = para.text.strip() if text: all_text.append(text) if all_text: print("\n".join(all_text)) else: print("No paragraphs found. Checking for images/embedded content...") # Try unpacking the docx to see what's inside import tempfile import os with tempfile.TemporaryDirectory() as tmpdir: with zipfile.ZipFile(doc_path, 'r') as zip_ref: zip_ref.extractall(tmpdir) # List all files print("\nFiles in DOCX:") for root, dirs, files in os.walk(tmpdir): for file in files: filepath = os.path.join(root, file) print(f" {filepath}") # Try reading document.xml doc_xml_path = os.path.join(tmpdir, 'word', 'document.xml') if os.path.exists(doc_xml_path): with open(doc_xml_path, 'r', encoding='utf-8') as f: content = f.read() print("\n=== DOCUMENT.XML (first 2000 chars) ===") print(content[:2000]) except Exception as e: print(f"Error: {e}") import traceback traceback.print_exc() EOF

python3 << 'EOF' import zipfile import os from PIL import Image doc_path = "/tmp/workspace/attachments/e61ce95b-60de-4984-a6b1-b87562cb98f0/RD 2 cases.docx" # Extract images from the docx extract_dir = "/tmp/workspace/extracted_images" os.makedirs(extract_dir, exist_ok=True) with zipfile.ZipFile(doc_path, 'r') as zip_ref: # Extract all images for file in zip_ref.namelist(): if 'media/image' in file: zip_ref.extract(file, extract_dir) print(f"Extracted: {file}") # List extracted images image_dir = os.path.join(extract_dir, 'word', 'media') if os.path.exists(image_dir): images = sorted(os.listdir(image_dir)) print(f"\nFound {len(images)} images") for img in images: src = os.path.join(image_dir, img) dst = f"/tmp/workspace/{img}" os.rename(src, dst) print(f"Moved to: {dst}") # Check image info try: im = Image.open(dst) print(f" - {img}: {im.size} ({im.format})") except: pass EOF

python3 << 'EOF' import pytesseract from PIL import Image import os image_dir = "/tmp/workspace" # Process all images and extract text all_text = {} for img_num in range(2, 9): img_path = f"{image_dir}/image{img_num}.jpeg" if os.path.exists(img_path): print(f"\n{'='*60}") print(f"IMAGE {img_num}") print('='*60) try: img = Image.open(img_path) text = pytesseract.image_to_string(img) all_text[f"image{img_num}"] = text print(text) except Exception as e: print(f"Error processing image{img_num}: {e}") EOF

python3 << 'EOF' from PIL import Image import os # List all extracted images image_dir = "/tmp/workspace" for i in range(1, 9): img_path = f"{image_dir}/image{i}.jpeg" if os.path.exists(img_path): img = Image.open(img_path) print(f"Image {i}: Size {img.size}, Mode: {img.mode}") # Try to save at different quality to see content thumb = img.copy() thumb.thumbnail((200, 200)) print(f" Created thumbnail") # Now let's try to copy images to a location we can view import shutil for i in range(2, 9): src = f"/tmp/workspace/image{i}.jpeg" dst = f"/tmp/workspace/case_image_{i}.jpg" if os.path.exists(src): shutil.copy(src, dst) print(f"Copied: {dst}") EOF