# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<![,.])\d+(?:[,.-]\d+)? ?- ?\d+(?:[,.]\d+)? km ?\/ ?(?:h|\d+min)\b"
test_str = ("The car drives 50,5 - 80 km/10min on the road.\n"
"The car drives 50,5 - 80 km / 10min on the road.\n"
"The car drives 40,5-80 km/h on the road.\n"
"The car drives 30-50 km/h on the road.\n"
"The car drives 40 - 60.8 km/ h on the road.\n"
"The car drives 40.90-60,8 km/h on the road.\n"
"The car drives 50,5 - 80 km/10 on the road.\n"
"The car drives 505,000.2 - 80 km/10min on the road.\n")
matches = re.finditer(regex, test_str, re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html