# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"Subject :\s*([\s\S]*?)(?=\*+end of input\*+)"
test_str = ("Subject :\n\n"
"So for example, one field can span any number of lines and then there will be a message similar to\n"
"****end of input****\n\n"
"It will match anything after the colon until it hits a new line character. This works for almost all of the fields I need to scrape. One however, is a bit more trouble. One of them, the last one I need to scrape (not shown above) will span multiple lines. There's no way to predict how long it will be, but instead I have another predefined piece of text I can use to determine where to stop capturing.")
matches = re.search(regex, test_str)
if matches:
print ("Match was found at {start}-{end}: {match}".format(start = matches.start(), end = matches.end(), match = matches.group()))
for groupNum in range(0, len(matches.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = matches.start(groupNum), end = matches.end(groupNum), group = matches.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