# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r".*?(?:\b(?:[sS]alary|[wW]age|[pP]ay)\b).*?([$][\d,.]+\s*[ot-]+\s*[\d$,.]+\d+)"
test_str = ("“The salary range in Colorado for this role is from USD $123,500 - $185,500”\n\n"
"The budget this year will be from $150,000 to $200,000\n\n"
"“The salary for this role is $180,000 to $216,000”\n"
"The budget this year will be from $150,000 to $200,000\n\n"
"“The salary for this role in the state of Colorado is between $150,800 to $226,000.”\n\n"
"“Pay Range: $12.00 - $16.00”\n\n"
"“Salary Range: $180,000 - $147,000”\n\n"
"“The anticipated starting base pay for this position is: $100,000 to $142,000 per year”\n\n"
"“Hourly wage estimate: $21.49 - $32.24 / hour”\n\n")
matches = re.finditer(regex, test_str)
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