# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(~~([^~~])*~~)"
test_str = "<p><span style=\\\"color: #44444d; font-family: Roboto, sans-serif; font-size: 16px;\\\">Indian women's cricket team captain **Mithali Raj** became the all-time highest run-scorer in women's ODI __cricket__, going past ~~Charlotte~~ Edwards' tally of 5,992 runs, against Australia in the ICC Women's World Cup on Wednesday. Mithali is also the second player after Charlotte Edwards to score over 500 runs in four different calendar years in women's ODI cricket.</span></p>"
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