count species ranked taxa in OTT with two word names from the output of the otcetera command in https://gist.github.com/mtholder/0ab3ef34ac96d4eec38fcfbefd4e66cc

count_species_rank_binomen.py

#!/usr/bin/env python
import sys
inp = sys.stdin
count = 0
for line in inp:
    ls = [i.strip() for i in line.split(' |')]
    if ls:
        assert len(ls) == 3 and ls[2] == ''
        rank = ls[0]
        if rank == 'species':
            name = ls[1]
            num_words = name.split()
            if len(num_words) == 2:
                count += 1
                if count % 10000 == 0:
                   sys.stderr.write(" ... count = {} ...\n".format(count))
sys.stdout.write('{}'.format(count))
sys.stdout.write('\n')