# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\s*<div\sid=\"feature-bullets[\s\S]*?(<li>\s*[\s\S]*?[\s]+<\/ul>)"
test_str = ("<div id=\"feature-bullets\" class=\"a-section a-spacing-medium a-spacing-top-small\">\n\n\n\n\n\n\n\n\n"
" \n"
" \n"
" <ul class=\"a-unordered-list a-vertical a-spacing-none\">\n"
" \n"
" \n\n\n\n"
"<div id=\"hsx-rpp-bullet-fits-message\" class=\"aok-hidden\">\n"
" <div class=\"a-box a-alert-inline a-alert-inline-success hsx-rpp-fitment-bullets\"><div class=\"a-box-inner a-alert-container\"><i class=\"a-icon a-icon-alert\"></i><div class=\"a-alert-content\">\n"
" This fits your <span class=\"hsx-rpp-bullet-model-info\"></span>.\n"
" </div></div></div>\n"
"</div>\n\n\n\n"
"<li id=\"replacementPartsFitmentBullet\" data-doesntfitmessage=\"We're not sure this item fits your \" data-fitsmessage=\"This fits your \" class=\"aok-hidden\"><span class=\"a-list-item\">\n"
" <span id=\"replacementPartsFitmentBulletInner\"> <a class=\"a-link-normal hsx-rpp-fitment-focus\" href=\"#\">Make sure this fits</a>\n"
" <span>by entering your model number.</span>\n"
" </span>\n"
"</span></li>\n\n"
"<script type=\"text/javascript\">\n"
" P.when(\"ReplacementPartsBulletLoader\").execute(function(module){ module.initializeDPX(); })\n"
"</script>\n\n"
" \n"
" \n"
" <li><span class=\"a-list-item\"> \n"
" Precision ground up-cut spiral design\n"
" \n"
" </span></li>\n"
" \n"
" <li><span class=\"a-list-item\"> \n"
" M2 high speed steel runs cooler, lasts longer\n"
" \n"
" </span></li>\n"
" \n"
" <li><span class=\"a-list-item\"> \n"
" Includes sizes 1/4\" x 3\", 1/2\" x 3-1/4\" and 3/8\" x 3\"\n"
" \n"
" </span></li>\n"
" \n"
" <li><span class=\"a-list-item\"> \n"
" 1/4\" shank;\n"
" \n"
" </span></li>\n"
" \n"
" </ul>\n"
" <!-- Loading EDP related metadata -->\n"
" \n"
" \n"
" \n\n"
" \n\n\n\n\n"
"<span class=\"edp-feature-declaration\" data-edp-feature-name=\"featurebullets\" data-edp-asin=\"B006ZBADNW\" data-data-hash=\"2400652208\" data-defects=\"[{"id":"defect-mismatch-info","value":"Different from product"},{"id":"defect-missing-information","value":"Missing information"},{"id":"defect-unessential-info","value":"Unimportant information"},{"id":"defect-other-productinfo-issue","value":"Other"}]\" data-metadata=\"CATALOG\" data-feature-container-id=\"\" data-custom-event-handler=\"\" data-display-name=\"Bullet Points\" data-edit-data-state=\"featureBulletsEDPEditData\" data-position=\"\" data-resolver=\"CQResolver\"></span>\n"
" \n"
" \n"
" \n"
" \n"
" \n"
" \n\n"
" \n\n"
" \n"
" \n"
" <span class=\"caretnext\">›</span>\n"
" <a id=\"seeMoreDetailsLink\" class=\"a-link-normal\" href=\"#productDetails\">See more product details</a>\n"
" \n\n"
" \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