Kent repertory Boenninghausen coryza rubrics page number

coryza

James Tyler Kent repertory 1900 scan page 326 coryza archive.org

Boenninghausen Therapeutic Pocket Book scan page 46 coryza archive.org

https://archive.org/details/b20416234_001

"Coryza" "Boenninghausen's Therapeutic Pocket Book" "page 46"

https://archive.org/stream/b20416234_001/b20416234_001_djvu.…

https://archive.org/metadata/b20416234_001

/tmp/workspace

mkdir -p "/tmp/workspace/coryza-scans/assets" [?25l&& python -c "import requests,json; ids=['b20416234_001','in.ernet.dli.2015.93043','therapeuticpock00hempgoog']; for i in ids: d=requests.get('https://archive.org/metadata/'+i).json(); print('ID',i); print('\\n'.join(f['name'] for f in d.get('files',[]) if any(x in f['name'].lower() for x in ['scandata','djvu.xml','text.pdf','jp2.zip','_pdf']))); print()"

python -c "import requests; urls={'kent':'https://archive.org/download/b20416234_001/b20416234_001_djvu.xml','boen':'https://archive.org/download/in.ernet.dli.2015.93043/2015.93043.Therapeutic-Pocket-book_djvu.xml'}; [open('/tmp/workspace/coryza-scans/assets/'+k+'.xml','wb').write(requests.get(u,timeout=120).content) for k,u in urls.items()]" && python -c "import os; print([(x,os.path.getsize('/tmp/workspace/coryza-scans/assets/'+x)) for x in ['kent.xml','boen.xml']])"

python - <<'PY' from lxml import etree for name in ['kent','boen']: p='/tmp/workspace/coryza-scans/assets/'+name+'.xml' root=etree.parse(p) pages=root.xpath('//OBJECT') print(name, len(pages)) hits=[] for i,o in enumerate(pages): text=' '.join(o.xpath('.//WORD/text()')) if 'coryza' in text.lower(): hits.append((i,text[:200].replace('\n',' '))) print('HITS',len(hits)) for x in hits[:25]: print(x) PY

python - <<'PY' from lxml import etree for name in ['kent','boen']: r=etree.parse('/tmp/workspace/coryza-scans/assets/'+name+'.xml') for i,o in enumerate(r.xpath('//OBJECT')): words=o.xpath('.//WORD/text()') txt=' '.join(words) if name=='boen' and ('oryza' in txt.lower() or 'catarrh' in txt.lower() or 'cold in the head' in txt.lower()): print(i,txt[:350]) if name=='boen' and i<100 and (str(46) in words or str(47) in words or str(48) in words): print('number?',i,words[:30],words[-15:]) PY

python - <<'PY' from lxml import etree for name, inds in [('kent',range(328,336)),('boen',range(121,128))]: r=etree.parse('/tmp/workspace/coryza-scans/assets/'+name+'.xml'); os=r.xpath('//OBJECT') print('\n',name) for i in inds: o=os[i]; print(i,o.attrib, ' | '.join(o.xpath('.//WORD/text()')[:20])) PY

python - <<'PY' import requests urls=[ 'https://archive.org/download/b20416234_001/page/n331.jpg', 'https://ia800205.us.archive.org/BookReader/BookReaderImages.php?zip=/20/items/b20416234_001/b20416234_001_jp2.zip&file=b20416234_001_jp2/b20416234_001_0332.jp2&id=b20416234_001&scale=2&rotate=0', 'https://archive.org/download/in.ernet.dli.2015.93043/page/n124.jpg', 'https://ia800202.us.archive.org/BookReader/BookReaderImages.php?zip=/18/items/in.ernet.dli.2015.93043/2015.93043.Therapeutic-Pocket-book_jp2.zip&file=2015.93043.Therapeutic-Pocket-book_jp2/2015.93043.Therapeutic-Pocket-book_0124.jp2&id=in.ernet.dli.2015.93043&scale=2&rotate=0' ] for j,u in enumerate(urls): r=requests.get(u,timeout=120); print(j,r.status_code,r.headers.get('Content-Type'),len(r.content),r.url) open(f'/tmp/workspace/coryza-scans/assets/test{j}','wb').write(r.content) PY