extract.py

import glob, os, re

output_file_name = 'output.csv'
print('Writing output to %s...' % (output_file_name))

with open(output_file_name, 'w') as output_file:
    
    file_list = glob.glob('*.txt')
    print('Found %d files to process...' % (len(file_list)))
    
    for file_name in file_list:
        with open(file_name, 'r') as input_file:

            for line in input_file.readlines():

                m = re.match(r'Total viable cells / ml \(x 10\^6\) :(.*)', line, re.M|re.I)
                if (m is not None):
                    output_line = '"%s",%s' % (file_name, m.group(1))
                    print(output_line)
                    output_file.write('%s\n' % (output_line))

print('Done.')

extract_more.py

import glob, os, re

def calum_sort(l): 
	convert      = lambda text: int(text) if text.isdigit() else text.lower() 
	alphanum_key = lambda key: [ convert(c) for c in re.split('([0-9]+)', key) ] 
	def get_d(key):
		m = re.match(r'.*?d(\d+)', key, re.M|re.I)
		return int(m.group(1)) if (m is not None) else 0, alphanum_key(key), key
	return sorted(l, key=get_d)

output_file_name = 'output.csv'
print('Writing output to %s...' % (output_file_name))

with open(output_file_name, 'w') as output_file:

	file_list = calum_sort(glob.glob('*.txt'))
	print('Found %d files to process...' % (len(file_list)))

	for file_name in file_list:
		with open(file_name, 'r') as input_file:

			total_cells = 'error'
			viable_cells = 'error'
			viability = 'error'

			for line in input_file.readlines():

				m = re.match(r'Total viable cells / ml \(x 10\^6\) :(.*)', line, re.M|re.I)
				if (m is not None):
					viable_cells = m.group(1)

				m = re.match(r'Total cells / ml \(x 10\^6\) :(.*)', line, re.M|re.I)
				if (m is not None):
					total_cells = m.group(1)

				m = re.match(r'Viability \(\%\) :(.*)', line, re.M|re.I)
				if (m is not None):
					viability = m.group(1)

		output_line = '"%s",%s,%s,%s' % (file_name, viable_cells, total_cells, viability)
		print(output_line)
		output_file.write('%s\n' % (output_line))

print('Done.')