import re line="(1 (2 (1 (1 (1 (2 You) (1 (2 (2 wo) (2 n't)) (2 (2 like) (2 Roger)))) (2 ,)) (2 but)) (2 (2 you) (3 (3 (2 will) (2 quickly)) (2 (2 recognize) (2 him))))) (2 .))\n" numR=re.compile(r"\((\d) ([.',]|\w+)\)") print(re.findall(numR,line))
Standard input is empty
[('2', 'You'), ('2', 'wo'), ('2', 'like'), ('2', 'Roger'), ('2', ','), ('2', 'but'), ('2', 'you'), ('2', 'will'), ('2', 'quickly'), ('2', 'recognize'), ('2', 'him'), ('2', '.')]