make a ppt from this article which should contain 10-12 slides and only include the underlined text and nothing other than that
ls -la /tmp/workspace/attachments/9308aff9-99b7-481e-997f-ce4d18aac015/
cd /tmp/workspace && python3 -c " import pdfplumber with pdfplumber.open('attachments/9308aff9-99b7-481e-997f-ce4d18aac015/12663_2020_Article_1414.pdf') as pdf: print('pages', len(pdf.pages)) p = pdf.pages[0] print('lines', len(p.lines)) print('rects', len(p.rects)) print('curves', len(p.curves)) print(p.lines[:5]) print(p.rects[:5]) "
cd /tmp/workspace && python3 -c " import pdfplumber with pdfplumber.open('attachments/9308aff9-99b7-481e-997f-ce4d18aac015/12663_2020_Article_1414.pdf') as pdf: for i,p in enumerate(pdf.pages): thin = [r for r in p.rects if r['height'] < 2] print('page', i+1, 'total rects', len(p.rects), 'thin rects', len(thin)) "
cd /tmp/workspace && python3 -c " from pypdf import PdfReader reader = PdfReader('attachments/9308aff9-99b7-481e-997f-ce4d18aac015/12663_2020_Article_1414.pdf') for i,page in enumerate(reader.pages): annots = page.get('/Annots') if annots: print('page', i+1, 'annots:', len(annots)) for a in annots: obj = a.get_object() print(' subtype', obj.get('/Subtype'), 'rect', obj.get('/Rect')) "
cd /tmp/workspace && python3 -c " from pypdf import PdfReader reader = PdfReader('attachments/9308aff9-99b7-481e-997f-ce4d18aac015/12663_2020_Article_1414.pdf') total=0 for i,page in enumerate(reader.pages): annots = page.get('/Annots') if annots: annots = annots.get_object() print('page', i+1, 'annots:', len(annots)) total+=len(annots) for a in annots: obj = a.get_object() print(' subtype', obj.get('/Subtype'), 'rect', obj.get('/Rect')) print('total', total) "