parse_table.py

import json
import sys

entries = []
dic = {
	'Protein number':  None,
	'PDB code':        None,
	'BMRB code':       None,
	'Protein name':    None,
	'Deposition date': None,
	'PDB title':       None,
	'PDB authors':     None,
	'Last author':     None,
	'Reference':       None,
	'Reference title': None,
	'Software listed': None,
	'Spectrometer':    None
}

with open(sys.argv[1], 'r') as fp:
	protein = False
	for line in fp.readlines():
		line = line.rstrip()
		
		if line.startswith('Protein number'):
			protein = True
			counter = line.split()[-1]
			entry = dic.copy()
			entry['Protein number'] = counter
			continue
		
		elif protein:
			if len(line) == 0:
				protein = False
				entries.append(entry)
				continue
			else:
				wrds = line.split()
				first = wrds[0]
				two   = ' '.join(wrds[:2])
				if first in entry:
					entry[first] = ' '.join(wrds[1:])
					continue
				if two in entry:
					entry[two] = ' '.join(wrds[2:])
					continue

#print(json.dumps(entries, indent=2))
#nesgcount = 0
for entry in entries:
	pdbtitle = entry['PDB title']
	pdbtitle = pdbtitle.upper()
	if 'NORTHEAST' in pdbtitle and 'TARGET' in pdbtitle:
		#nesgcount += 1
		#print(pdbtitle)
		targetsplit = pdbtitle.split('TARGET ')
		nesg = targetsplit[-1]
		#print(nesg)
		entry['NESG id'] = nesg
	else: entry['NESG id'] = None
#print(nesgcount)
print(json.dumps(entries,indent=2))