import re
regex = re.compile(r"""
(?<!\\) # Check it was not escaped with a \
(?<img_all>
\!\[(?<img_alt>.+?)\] # image alternative text, i.e. the text used when the image does not
(?:
(?:
[ ]? # possibly followed by some spaces
(?:\n[ ]*)? # and a new line with some space
\[(?<img_id>.*?)\] # with the link id in brackets, but may be empty
)
|
(?:
(?:
\(
[ \t]*
<(?<img_url> # link url within <>; or
.+?
)>
[ \t]* # possibly followed by some spaces or tabs
(?:
(?<img_title_container>['"]) # Title is surrounded ether by double or single quotes
(?<img_title>.*?) # actual title, but could be empty as in ""
\g{img_title_container} # make the sure enclosing mark balance
)?
[ \t]*
\)
)
|
(?:
\(
[ \t]*
(?<img_url> # link url within <>; or
(?:((?!["']).)*+|.*)
)
[ \t]*
(?:
(?<img_title_container>['"]) # Title is surrounded ether by double or single quotes
(?<img_title>.*?) # actual title, but could be empty as in ""
\g{img_title_container} # make the sure enclosing mark balance
)?
[ \t]*
\)
)
)
)
)
""", flags=re.MULTILINE | re.VERBOSE)
test_str = ("\n\n"
"Inline within a paragraph: .\n\n"
".jpg'Title here')\n\n"
".jpg \"With title\") some text after\n\n"
"\n\n"
"")
matches = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
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