# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"([^\s=]+)=('?)(\"?)([^>\"']*)\2\3"
test_str = (" style=\"width: 462px;\" src='data:image/png;base64,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' data-filename=\"Screenshot from 2016-02-09 21:54:47.png\"\n\n\n"
"<tr><td><A HREF=\"brackets.html\" TARGET=\"_top\">Capturing group</A></td>\n"
" <td><TT>(regex)</TT></td>\n"
" <td>Parentheses group the regex between them. They capture the text matched by the regex inside them into a numbered group that can be reused with a numbered backreference. They allow you to apply regex operators to the entire grouped regex.</td>\n"
" <td><TT CLASS=code><SPAN CLASS=\"regexnest1\">(</SPAN><SPAN CLASS=\"regexplain\">abc</SPAN><SPAN CLASS=\"regexnest1\">)</SPAN><SPAN CLASS=\"regexspecial\">{3}</SPAN></TT> matches <TT CLASS=match>abcabcabc</TT>. First group matches <TT CLASS=match>abc</TT>.</td>\n"
"<td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>ECMA<br>extended<br>egrep<br>awk</td><td class=yes>YES</td><td>no</td><td class=yes>YES</td><td>no</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td><td class=yes>YES</td></tr>\n\n"
"<tr><td><A HREF=\"brackets.html\" TARGET=\"_top\">Capturing group</A></td>\n"
" <td><TT>\\(regex\\)</TT></td>\n"
" <td>Escaped parentheses group the regex between them. They capture the text matched by the regex inside them into a numbered group that can be reused with a numbered backreference. They allow you to apply regex operators to the entire grouped regex.</td>\n"
" <td><TT CLASS=code><SPAN CLASS=\"regexnest1\">\\(</SPAN><SPAN CLASS=\"regexplain\">abc</SPAN><SPAN CLASS=\"regexnest1\">\\)</SPAN><SPAN CLASS=\"regexplain\">{3}</SPAN></TT> matches <TT CLASS=match>abcabcabc</TT>. First group matches <TT CLASS=match>abc</TT>.</td>\n"
"<td>no</td><td>no</td><td>no</td><td>no</td><td>no</td><td>no</td><td>no</td><td>no</td><td>no</td><td>no</td><td>no</td><td>no</td><td>no</td><td>no</td><td class=yes>basic<br>grep</td><td>no</td><td class=yes>YES</td><td>no</td><td class=yes>YES</td><td>no</td><td>no</td><td>no</td><td>no</td></tr>\n\n"
"<tr><td><A HREF=\"brackets.html\" TARGET=\"_top\">Non-capturing group</A></td>\n")
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