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 = "/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}") pregnan_pages = [] drug_resistant_pages = [] for i, page in enumerate(pdf.pages): text = page.extract_text() or "" if re.search(r'pregnan', text, re.IGNORECASE): pregnan_pages.append(i+1) if re.search(r'drug.?resist', text, re.IGNORECASE): drug_resistant_pages.append(i+1) print(f"Pages with 'pregnan': {pregnan_pages}") print(f"Pages with 'drug resist': {drug_resistant_pages}") EOF

python3 -c " import pdfplumber, 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}') pregnan_pages = [] for i, page in enumerate(pdf.pages): text = page.extract_text() or '' if re.search(r'pregnan', text, re.IGNORECASE): pregnan_pages.append(i+1) print(f'Pages with pregnan: {pregnan_pages}') "

ls "/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/" && echo "---" && python3 -c "import pdfplumber; print('pdfplumber ok')" && python3 -c "from pptx import Presentation; print('pptx ok')"

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

python3 -c " import pdfplumber, re pdf_path = \"/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/Sharma mohan latest_compressed-compressed (1).pdf\" pregnan_pages = [] drug_pages = [] with pdfplumber.open(pdf_path) as pdf: total = len(pdf.pages) print('Total pages:', total) for i in range(total): page = pdf.pages[i] text = page.extract_text() or '' if re.search(r'pregnan', text, re.IGNORECASE): pregnan_pages.append(i+1) if re.search(r'drug.?resist', text, re.IGNORECASE): drug_pages.append(i+1) print('Pregnan pages:', pregnan_pages) print('Drug-resist pages:', drug_pages) " 2>&1

python3 -c " from pypdf import PdfReader import re pdf_path = \"/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/Sharma mohan latest_compressed-compressed (1).pdf\" reader = PdfReader(pdf_path) total = len(reader.pages) print('Total pages:', total) "

python3 -c " from pypdf import PdfReader import re pdf_path = \"/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/Sharma mohan latest_compressed-compressed (1).pdf\" reader = PdfReader(pdf_path) total = len(reader.pages) pregnan_pages = [] for i in range(total): text = reader.pages[i].extract_text() or '' if re.search(r'pregnan', text, re.IGNORECASE): pregnan_pages.append(i+1) print('Pregnan pages:', pregnan_pages) " 2>&1

python3 -c " from pypdf import PdfReader import re pdf_path = \"/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/Sharma mohan latest_compressed-compressed (1).pdf\" reader = PdfReader(pdf_path) total = len(reader.pages) drug_pages = [] for i in range(total): text = reader.pages[i].extract_text() or '' if re.search(r'drug.?resist', text, re.IGNORECASE): drug_pages.append(i+1) print('Drug-resist pages:', drug_pages) " 2>&1

python3 -c " pregnan = [23, 56, 181, 190, 191, 197, 249, 262, 314, 344, 371, 372, 373, 374, 375, 376, 377, 378, 380, 390, 392, 419, 436, 460, 464, 497, 498, 499, 506, 558, 560, 616, 618, 619, 622, 630, 652, 653, 657, 664, 753, 815, 818, 951, 967, 968, 982, 989, 990, 992, 1000, 1001] drug = set([14, 16, 24, 30, 34, 35, 36, 37, 38, 40, 42, 44, 46, 47, 48, 49, 73, 80, 81, 82, 83, 88, 89, 92, 95, 97, 106, 114, 129, 131, 132, 133, 135, 153, 154, 167, 169, 170, 192, 199, 213, 214, 224, 234, 244, 246, 255, 256, 261, 263, 272, 273, 276, 293, 335, 337, 347, 348, 358, 365, 366, 370, 372, 373, 375, 377, 379, 388, 392, 451, 455, 456, 482, 484, 489, 490, 495, 498, 501, 502, 505, 507, 511, 513, 514, 516, 517, 519, 520, 538, 539, 543, 544, 547, 552, 553, 559, 596, 604, 605, 606, 607, 608, 609, 610, 611, 612, 613, 614, 615, 616, 617, 618, 620, 621, 622, 623, 624, 625, 626, 627, 628, 629, 630, 631, 632, 633, 634, 635, 636, 637, 638, 639, 640, 641, 642, 643, 644, 645, 646, 647, 651, 652, 653, 654, 655, 656, 657, 658, 659, 660, 669, 672, 673, 677, 678, 679, 680, 681, 683, 684, 685, 686, 687, 691, 692, 693, 695, 696, 697, 698, 700, 702, 704, 710, 711, 722, 729, 730, 732, 734, 736, 740, 742, 743, 744, 745, 748, 751, 752, 753, 757, 761, 768, 769, 771, 778, 783, 786, 790, 791, 792, 795, 797, 799, 801, 802, 807, 810, 812, 813, 814, 815, 816, 819, 915, 916, 919, 921, 925, 926, 928, 939, 940, 944, 948, 952, 974, 979, 989, 994, 995, 996, 1001, 1002, 1003]) both = [p for p in pregnan if p in drug] print('Both pregnan AND drug-resist:', both) "

python3 << 'PYEOF' from pypdf import PdfReader import re pdf_path = "/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/Sharma mohan latest_compressed-compressed (1).pdf" reader = PdfReader(pdf_path) pregnan_pages = [23, 56, 181, 190, 191, 197, 249, 262, 314, 344, 371, 372, 373, 374, 375, 376, 377, 378, 380, 390, 392, 419, 436, 460, 464, 497, 498, 499, 506, 558, 560, 616, 618, 619, 622, 630, 652, 653, 657, 664, 753, 815, 818, 951, 967, 968, 982, 989, 990, 992, 1000, 1001] output = [] for pg in pregnan_pages: text = reader.pages[pg-1].extract_text() or "" output.append(f"\n{'='*60}\n=== PAGE {pg} ===\n{'='*60}\n{text}") result = "\n".join(output) print(result[:50000]) PYEOF

python3 << 'PYEOF' from pypdf import PdfReader import re pdf_path = "/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/Sharma mohan latest_compressed-compressed (1).pdf" reader = PdfReader(pdf_path) # Get the core pregnancy chapter pages (371-380, 390, 392) and surrounding core_pages = [371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382, 383, 384, 385, 386, 387, 388, 389, 390, 391, 392] for pg in core_pages: text = reader.pages[pg-1].extract_text() or "" if re.search(r'pregnan|TB|tubercul', text, re.IGNORECASE): print(f"\n{'='*60}\n=== PAGE {pg} ===\n{'='*60}\n{text}") PYEOF

python3 << 'PYEOF' from pypdf import PdfReader import re pdf_path = "/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/Sharma mohan latest_compressed-compressed (1).pdf" reader = PdfReader(pdf_path) # Remaining pregnan pages not yet extracted remaining_pages = [419, 436, 460, 464, 497, 498, 499, 506, 558, 560, 616, 618, 619, 622, 630, 652, 653, 657, 664, 753, 815, 818, 951, 967, 968, 982, 989, 990, 992, 1000, 1001] for pg in remaining_pages: text = reader.pages[pg-1].extract_text() or "" print(f"\n{'='*60}\n=== PAGE {pg} ===\n{'='*60}\n{text}") PYEOF

python3 << 'PYEOF' from pptx import Presentation import re pptx_path = "/home/daytona/workspace/attachments/94b62c8a-ece6-4265-869c-7cae5980c78b/PMDT Guidelines_March 2025.pptx" prs = Presentation(pptx_path) print(f"=== FILE: PMDT Guidelines_March 2025.pptx ===") print(f"Total slides: {len(prs.slides)}") # First pass: find all slides with 'pregnan' pregnan_slides = [] 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): pregnan_slides.append(i+1) print(f"Slides with 'pregnan': {pregnan_slides}") PYEOF