# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<b>(?:(?!<\/?b>).)*?<\/b>(?:(?!<\/?b>).)*?<font color=darkslategray>.*?<\/font>"
test_str = ("naive\n"
"<b>na·ive</b><br><div style=\"padding-left:0.5em;\">(<VR><span style=\"color:#006400;font-style:italic\">or</span> <b>na·ïve</b></VR>) <font color=darkslategray>/nɑˈiːv, naıˈiːv/</font> <span style=\"color:#006400;font-style:italic\">adj</span> [<i>more ~; most ~</i>]<br></div><div style=\"padding-left:1em;\"><b>:</b> having or showing a lack of experience or knowledge <b>:</b> innocent or simple<br></div><div style=\"padding-left:1.5em;\"><font color=\"#004A95\">a <i>naive</i> belief that all people are good</font><br></div><div style=\"padding-left:1.5em;\"><font color=\"#004A95\">a <i>naive</i> view of the world</font><br></div><div style=\"padding-left:1.5em;\"><font color=\"#004A95\">I <i>naively</i> believed that we could fix the problem.</font><br></div><div style=\"padding-left:1em;\"><b>na·ïve·té</b> (<VR><span style=\"color:#006400;font-style:italic\">also</span> <b>na·ive·te</b> <span style=\"color:#006400;font-style:italic\">or</span> <b>na·ive·té</b></VR>) <font color=darkslategray>/nɑˌiːvˈteı, naıˌiːvˈteı/</font> <span style=\"color:#006400;font-style:italic\">noun</span> [<span style=\"color:#006400;font-style:italic\">noncount</span>]<br></div><div style=\"padding-left:1.5em;\"><font color=\"#004A95\">political <i>naïveté</i></font><br></div><div style=\"padding-left:1em;\"><b>na·ive·ty</b> (<VR><span style=\"color:#006400;font-style:italic\">also</span> <b>na·ïve·ty</b></VR>) <font color=darkslategray>/nɑˈiːvəti, naıˈiːvəti/</font> <span style=\"color:#006400;font-style:italic\">noun</span> [<span style=\"color:#006400;font-style:italic\">noncount</span>] <span style=\"color:#006400;font-style:italic\">chiefly Brit</span><br></div><div style=\"padding-left:1.5em;\"><font color=\"#004A95\">political <i>naïvety</i></font><br></div>")
matches = re.finditer(regex, test_str, 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