# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<li><a href=\"(?:(?!#sequence_only).)*\">(.*)</a>"
test_str = (" <!DOCTYPE html>\n\n"
" <!-- The following setting enables collapsible lists -->\n"
" <p>\n"
" <a href=\"#human\">Human</a></p>\n\n"
" <p class=\"collapse-section\">\n"
" <a class=\"collapsed collapse-toggle\" data-toggle=\"collapse\" \n"
" href=#mammals>Mammals</a>\n"
" <div class=\"collapse\" id=\"mammals\">\n"
" <ul>\n"
" <li><a href=\"#alpaca\">Alpaca</a>\n"
" <li><a href=\"#armadillo\">Armadillo</a>\n"
" <li><a href=\"#sequence_only\">Armadillo</a> (sequence only)\n"
" <li><a href=\"#baboon\">Baboon</a>\n"
" <li><a href=\"#bison\">Bison</a>\n"
" <li><a href=\"#bonobo\">Bonobo</a>\n"
" <li><a href=\"#brown_kiwi\">Brown kiwi</a>\n"
" <li><a href=\"#bushbaby\">Bushbaby</a>\n"
" <li><a href=\"#sequence_only\">Bushbaby</a> (sequence only)\n"
" <li><a href=\"#cat\">Cat</a>\n"
" <li><a href=\"#chimp\">Chimpanzee</a>\n"
" <li><a href=\"#chinese_hamster\">Chinese hamster</a>\n"
" <li><a href=\"#chinese_pangolin\">Chinese pangolin</a>\n"
" <li><a href=\"#cow\">Cow</a>\n"
" <li><a href=\"#crab-eating_macaque\">Crab-eating_macaque</a>\n"
" <div class=\"gbFooterCopyright\">\n"
" © 2017 The Regents of the University of California. All \n"
" Rights Reserved.\n"
" <br>\n"
" <a href=\"https://genome.ucsc.edu/conditions.html\">Conditions of \n"
" Use</a>\n"
" </div>")
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