# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\bfrom company\b.*?\K\b(?<!\$|[\d.])(?:\d++)\b"
test_str = ("This is invoice from company XYZ - $1234545 product name 31h10 , $456.12 product number g456, 123f 456 information invoice unit cost $12.0 and invoice total $1343.00\n\n"
"This is invoice from company ABC - 1234545 product name and information invoice total cost $6777 and invoice unit cost $654")
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