fork download
  1. import re
  2.  
  3. pattern = r"-?\b\d+(?:[.,]\d+)*\s*m?g(?:\s*/\s*-?\d+(?:[.,]\d+)*\s*m?g)+\b"
  4.  
  5. strings = [
  6. "Dexamethasonacetat 5 mg/10 mg, Lidocain-HCl 1H2O 30 mg/60 mg",
  7. "Anakinra 120 mg /-20 g /-12mg gentechnologisch hergestellt aus E. coli. 10mg pack"
  8. ]
  9.  
  10. for s in strings:
  11. print([re.sub(r"[\s-]+", "", m) for m in re.findall(pattern, s)])
Success #stdin #stdout 0.03s 9372KB
stdin
Standard input is empty
stdout
['5mg/10mg', '30mg/60mg']
['120mg/20g/12mg']