# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
^[ ]{0,3} # Leading space up to 3
(?<link_all>
(?<!\\)\[ # ID within brackets
(?!\^) # Make sure, this is not confused with a footnote
(?<link_id>.+?)
(?<!\\)\]
[ \t]* # Possibly with some space before colon
\:
[ \t]*\n?[ \t]* # Possibly with some space after the colon, possibly with a new line in between?
(?:
<(?<link_url>[^\>]+)> # link within <>
|
(?<link_url>\S+) # or link without <>
)
(?:
(?:
[ \t]+ # Either some space or tabs
|
[ \t]*\n[ \t]* # or a new line surrounded by 0 or more spaces or tabs
)
(?:
(?:
(?<link_title_container>['"]) # Title is surrounded ether by double or single quotes
(?<link_title>.+?)
\g{link_title_container} # make the sure enclosing mark balance
)
| # or
\((?<link_title>[^\)]+)\) # by parenthesis
)
)?
[ \t]* # Possibly ending with some trailing spaces or tab
)
(?:\n+|\Z) # terminated by a new line or end of file
"""
test_str = ("[1]: /url/ \"Title\"\n\n"
"[refid]: /path/to/something (Title)\n\n"
"[^block]:\n"
" Paragraph.\n\n"
" * List item\n\n"
" > Blockquote\n\n"
" Code block\n")
matches = re.finditer(regex, test_str, re.MULTILINE | re.VERBOSE)
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