# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"[^<>](?![^<]*>|[^<>]*<\/)(?!\s\#\s)(\#\S[^<>](?![^<]*>|[^<>]*<\/)(.*?)\S\#)"
test_str = ("With # : #Zhong Lun Law Firm#\n\n"
"With # : #Algeria’s new Investment Law#\n\n"
"With # : #中伦律师事务所#\n\n"
"With # : #Victor I-Hsiu Chang#\n\n"
"With # : #叶姝欐#\n\n"
"With # : #Nguyen Anh Tuan#\n\n"
"With # : #AnJie Law Firm#\n\n"
"With # : #锦天城律师事务所#\n\n"
"<section id=\"Capital\" class=\"vantage-bg-grey\">\n"
"<p id=\"Capital\" class=\"DOTY_DOTY-Number\" style=\"background-color: #ec1c24; color: #ffffff; font-weight: bold; font-size: 20px; padding: 5px; text-align: justify;\"><a style=\"color: white;\" href=\"#Capital\"><u>CAPITAL MARKETS</u></a></p><section id=\"Capital\" class=\"vantage-bg-grey\">\n"
"<p id=\"Capital\" class=\"DOTY_DOTY-Number\" style=\"background-color: #ec1c24; color: #ffffff; font-weight: bold; font-size: 20px; padding: 5px; text-align: justify;\"><a style=\"color: white;\" href=\"#Capital\"><u>CAPITAL MARKETS</u></a></p><section id=\"Capital\" class=\"vantage-bg-grey\">\n"
"<p id=\"Capital\" class=\"DOTY_DOTY-Number\" style=\"background-color: #ec1c24; color: #ffffff; font-weight: bold; font-size: 20px; padding: 5px; text-align: justify;\"><a style=\"color: white;\" href=\"#Capital\"><u>CAPITAL MARKETS</u></a></p><section id=\"Capital\" class=\"vantage-bg-grey\">\n"
"<p id=\"Capital\" class=\"DOTY_DOTY-Number\" style=\"background-color: #ec1c24; color: #ffffff; font-weight: bold; font-size: 20px; padding: 5px; text-align: justify;\"><a style=\"color: white;\" href=\"#Capital\"><u>CAPITAL MARKETS</u></a></p>\n\n"
"one <p>two</p> three <p class=\"test\">four</p> five <a>six</a> seven <p> eight nine <p/> ten\n\n"
"<a style=\"text-decoration: none;\" href=\"https://beta2.law.asia/china/china-top-lawyers-2022/\"><button style=\"width: 100%; font-size: 18px; letter-spacing: 1px; padding: 14px 20px; color: #666; border-color: #F4F4F4; background-color: #fff; background-image: linear-gradient(to bottom,rgba(0,0,0,.01) 0,rgba(0,0,0,.02) 100%); background-repeat: repeat-x; border-radius: 5px; a: hover{background-color:#000;\"><span style=\"color: #c94f3f; font-weight: bold; text-transform: uppercase;\">China</span></button> </a>\n\n"
"[vc_column_text]<a style=\"text-decoration: none;\" href=\"https://beta2.law.asia/asia/lawyers/singapore-lawyers/\"><button style=\"width: 100%; font-size: 18px; letter-spacing: 1px; padding: 14px 20px; color: #666; border-color: #F4F4F4; background-color: #fff; background-image: linear-gradient(to bottom,rgba(0,0,0,.01) 0,rgba(0,0,0,.02) 100%); background-repeat: repeat-x; border-radius: 5px; a: hover{background-color:#000;\"><span style=\"color: #c94f3f; font-weight: bold; text-transform: uppercase;\">Singapore</span></button> </a>[/vc_column_text][/vc_column][vc_column width=\"1/2\"][vc_column_text]\n\n\n\n"
"[vc_column_text]<a style=\"text-decoration: none;\" href=\"https://beta2.law.asia/asia/lawyers/singapore-lawyers/\"><span style=\"color: #c94f3f; font-weight: bold; text-transform: uppercase;\">Singapore</span></a>[/vc_column_text][/vc_column][vc_column width=\"1/2\"][vc_column_text]\n\n"
"<a href=\"https://beta2.law.asia/law-firm/drew-napier/\">Drew & Napier</a><br>\n"
"Drew & Napier<br>\n"
"<a href=\"https://beta2.law.asia/law-firm/allen-overy/\">Allen & Overy</a><br>\n"
"Allen & Overy<br>\n"
"<a href=\"https://beta2.law.asia/asia/\">Robert Hasan</a><br>\n"
"Robert Hasan<br>\n"
"华进律师事务所<br>\n"
"华进律师事务所<br>\n"
"<a href=\"https://beta2.law.asia/law-firm/deep-far-attorneys-at-law/\">Deep & Far</a><br>\n"
"Deep & Far\n"
"#<a href=\"https://beta2.law.asia/law-firm/drew-napier/\">Drew & Napier</a>#")
matches = re.finditer(regex, test_str, re.MULTILINE)
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