Extract ALL content related to "TB in pregnancy", "tuberculosis in pregnancy", "DSTB in pregnancy", "DRTB in pregnancy", "drug sensitive TB", "drug resistant TB", "pregnant", "pregnancy" from three files: 1. PDF file at: /home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/Sharma mohan latest_compressed-compressed (1).pdf 2. PPTX file at: /home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/PMDT Guidelines_March 2025.pptx 3. PPTX file at: /home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/PMDT 2021.pptx For the PDF: Use pdfplumber to extract text from ALL pages. Search for pages containing "pregnan" (case insensitive) and extract those full pages plus surrounding pages. Also look for any tables/content about TB drugs in pregnancy. For the PPTX files: Use python-pptx to extract all slide text, then find slides mentioning "pregnan" (case insensitive). Here is Python code approach: ```python import pdfplumber import re pdf_path = "/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/Sharma mohan latest_compressed-compressed (1).pdf" with pdfplumber.open(pdf_path) as pdf: total = len(pdf.pages) print(f"Total pages: {total}") for i, page in enumerate(pdf.pages): text = page.extract_text() or "" if re.search(r'pregnan', text, re.IGNORECASE): print(f"\n=== PAGE {i+1} ===") print(text) # Also print tables if any tables = page.extract_tables() for t in tables: print("TABLE:", t) ``` For PPTX: ```python from pptx import Presentation for pptx_path in [ "/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/PMDT Guidelines_March 2025.pptx", "/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/PMDT 2021.pptx" ]: prs = Presentation(pptx_path) print(f"\n\n=== FILE: {pptx_path} ===") for i, slide in enumerate(prs.slides): slide_text = "" for shape in slide.shapes: if shape.has_text_frame: for para in shape.text_frame.paragraphs: slide_text += para.text + "\n" if re.search(r'pregnan', slide_text, re.IGNORECASE): print(f"\n--- SLIDE {i+1} ---") print(slide_text) ``` Execute this code. Return the COMPLETE extracted text from all pregnancy-related pages and slides. Do not truncate or summarize - return the raw text verbatim so it can be used for a medical exam answer. Also, for the PDF, search ALL pages from page 1 to the last page - include any page with "TB" AND "pregnant/pregnancy" on it. Additionally extract any pages about "drug resistant" TB management, dosing tables, treatment regimens for pregnancy.

cd /home/daytona && python3 << 'EOF' import pdfplumber import re pdf_path = "/h…

python3 -c " import pdfplumber, re pdf_path = \"/home/daytona/workspace/attachme…

ls "/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/" &…

pip install python-pptx -q && python3 -c "from pptx import Presentation; print('…

python3 -c " import pdfplumber, re pdf_path = \"/home/daytona/workspace/attachme…

python3 -c " from pypdf import PdfReader import re pdf_path = \"/home/daytona/wo…

python3 -c " from pypdf import PdfReader import re pdf_path = \"/home/daytona/wo…

python3 -c " from pypdf import PdfReader import re pdf_path = \"/home/daytona/wo…

python3 -c " pregnan = [23, 56, 181, 190, 191, 197, 249, 262, 314, 344, 371, 372…

python3 << 'PYEOF' from pypdf import PdfReader import re pdf_path = "/home/dayt…

python3 << 'PYEOF' from pypdf import PdfReader import re pdf_path = "/home/dayt…

python3 << 'PYEOF' from pypdf import PdfReader import re pdf_path = "/home/dayt…

python3 << 'PYEOF' from pptx import Presentation import re pptx_path = "/home/d…