import re for p in ['output/original-submission/diagnosis.md','output/diagnosis.md']: t=open(p).read() raw=len(t.split()) words=len([w for w in t.split() if re.search(r'[A-Za-z0-9]', w)]) print(p, 'raw tokens', raw, 'alnum words', words) t=open('output/diagnosis.md').read() for s in ['Media','Relink','Captions','Burn into video','Apply','Export','Online','Sidecar only','E204','00:00:42','/Volumes/WORK_SSD/Review/interview_camA.mp4']: print(s, s in t)