regex_extraction.py 388 B

123456789101112131415
  1. # coding=utf8
  2. import re
  3. regex = r"(\S+\s{1,3}?\S*\s?\S*\S*\s?\S*\S*\s?\S*\S*\s?\S*\S*\s+)"
  4. extracted_dimensions = []
  5. file=open('/home/bscheibel/PycharmProjects/dxf_reader/drawings/5152166_Rev04.txt', 'r')
  6. text= file.read()
  7. file.close()
  8. matches = re.findall(regex, text, re.MULTILINE)
  9. for match in matches:
  10. extracted_dimensions.append(match.strip())
  11. print(extracted_dimensions)