import re
regex = r"Title:\s *(.*?)\s *Procedure|Title:\s *(.*)"
test_str = ( "Title: Anorectal Fistula (Fistula-in-Ano) Procedure Code(s):\n \n "
"Effective date: 7/1/07\n \n "
"Title:\n \n "
"2003247\n \n "
"or previous effective dates)\n \n "
"Title:\n \n "
"ST2 Assay for Chronic Heart Failure\n \n "
"Description/Background\n \n "
"Heart Failure\n \n "
"HF is one among many cardiovascular diseases that comprises a major cause of morbidity and mortality worldwide. The term “heart failure” (HF) refers to a complex clinical syndrome ." )
res = [ ]
for m in re .finditer ( regex, test_str) :
if m.group ( 1 ) :
res.append ( m.group ( 1 ) )
else :
res.append ( m.group ( 2 ) )
print ( res)
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