# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"((?:<.*>)|(?<=>)(?:\<.*\n?.*\>))"
test_str = ("<p><font face=\"Helv\" size=\"2\"><font face=\"Helv\" size=\"2\">- $25mm to $50mm near term GLRV opportunity. If approved, they would invest in our commingled\n"
"fund.</font></font><br><font face=\"Helv\" size=\"2\"><font face=\"Helv\" size=\"2\">- This was another critical step in Investcorp's investment process. In a\n"
"positive sign, they've decided to concurrently initiate operational due diligence on us and the GLRV fund/strategy.</font></font><br><font face=\"Helv\"\n"
"size=\"2\"><font face=\"Helv\" size=\"2\">- Overall an excellent, interactive meeting mainly focused on risk modeling and measurement, and how we use our \n"
"models/tools throughout the investment process to help source and implement trades; actively allocate risk across sub-strategies; as well as adjust the overall risk\n"
"taking in the strategy</font></font></p>\n\n"
"MEETING DETAILS:\n"
"None Available\n\n"
"NOTES:\n"
"<p><font face=\"Helv\" size=\"2\"><font face=\"Helv\" size=\"2\">- Investcorp is a NY based $10 billion global alternative investments manager with roots and a large\n"
"presence in the middle east.</font></font><br><font face=\"Helv\" size=\"2\"><font face=\"Helv\" size=\"2\">- They are running ~$2 billion in traditional FoHFs AUM (in\n"
"addition to another $2 billion in other custom HF mandates) after closing on their SSARIS Advisors (another FoHFs) acquisition earlier this\n"
"year.</font></font><br><font face=\"Helv\" size=\"2\"><font face=\"Helv\" size=\"2\">- The consolidation of their portfolio continues following the SSARIS acquisition\n"
"and he team is finally ready to allocate to new managers. FI Arb/RV is a space they are interested in again.</font></font><br><font face=\"Helv\" size=\"2\"><font\n"
"face=\"Helv\" size=\"2\">- We have the advantage of being "first in the door" as they assessed the space, since we've been talking to them about LRV\n"
"since early 2014.</font></font><br><font face=\"Helv\" size=\"2\"><font face=\"Helv\" size=\"2\">")
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