# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\n(HORIZON-\S+-[A-Z]{1}\d{1}-\d{2})\s+"
test_str = ("\n"
"HORIZON-CL5-2021-D1-01\n"
"Conditions for the Call\n"
"Indicative budget(s) \n"
"Topics Type of Action Budgets (EUR million) Expected EU contribution per project (EUR million) Number of projects expected to be funded\n"
" 2021 \n"
"Opening: 15 Apr 2021\n"
"Deadline(s): 07 Sep 2021\n\n"
"HORIZON-CL5-2022-D1-01-two-stage\n"
"Conditions for the Call\n"
"Indicative budget(s) \n"
"Topics Type of Action Budgets (EUR million) Expected EU contribution per project (EUR million) Number of projects expected to be funded\n"
" 2022 \n"
"Opening: 04 Nov 2021\n"
"Deadline(s): 15 Feb 2022 (First Stage), 07 Sep 2022 (Second Stage)\n\n\n"
"HORIZON-CL5-2021-D2-01\n"
"Conditions for the Call\n"
"Indicative budget(s) \n"
"Topics Type of Action Budgets (EUR million) Expected EU contribution per project (EUR million) Number of projects expected to be funded\n"
" 2021 2022 \n"
"Opening: 15 Apr 2021\n"
"Deadline(s): 19 Oct 2021")
matches = re.finditer(regex, test_str, re.MULTILINE | re.DOTALL)
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