# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(<[\s]*(?![\/])figure.*?>)|(([^<.*figure.*>\w])(<[\s]*(?![\/])img.*?>)([^<.*\/*figure.*>]))"
test_str = ("аываыва <img sdasd asd > sdf dsf < sdf imG>\n\n"
"<h2>\n\n"
"< H2 sdf > </h2> sdf sdf sdf sdfsdf sdf sd f\n\n"
"< sdf sdf H2 sdf > \n\n"
"</h2>\n"
"< h2> adasd asd < h2> \n"
"< / H2>\n\n\n"
"<img 2>\n\n"
"<figure><img></figure> ыва ыва ыва ыва ыва ыва\n\n"
"< figure >< img >< / figure >\n\n"
"< figure sdfsdfsdfsd f> asd as das asd< img asd asd a/> asd asd asd <> < / figure> фываы ва ыв\n\n\n"
"<img>\n\n"
"< figure > фыв ыфв фыв фыв ыфв < img > < / figure >\n\n"
"<figure itemprop=\"associatedMedia image\" itemscope=\"\" itemtype=\"https://schema.org/ImageObject\"> <meta itemprop=\"representativeOfPage\" content=\"true\"> <img itemprop=\"contentUrl url\" src=\"//site.com/url.jpg\" title=\"\" alt=\"\"> <meta itemprop=\"name\" content=\"\"> <meta itemprop=\"width\" content=\"\"> <meta itemprop=\"height\" content=\"\"></figure>")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE)
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