# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<span class=\"ccd\">[^<]*<\/span>"
test_str = ("<td class=\"col-2\">\n\n"
" \n\n"
" 5 doors, 6 Speed manual,\n\n"
" \n"
" <span class=\"pc\">\n"
" from £24,270\n"
" </span>\n"
" \n\n"
" <span class=\"ccd\">\n"
" from £24,215\n"
" </span>\n"
" \n"
" <a href=\"/fleet/company-tax?modelId=1353&trimId=1365&derivativeId=1366\" class=\"tax-calculator ccd vw-btn btn-no-border\"><span class=\"vw-icon-link-small\">Get a company car tax quote</span></a>\n"
" <br>\n"
" \n\n"
" 5 doors, 7 Speed auto DSG,\n\n"
" \n"
" <span class=\"pc\">\n"
" from £25,685\n"
" </span>\n"
" \n\n"
" <span class=\"ccd\">\n"
" from £25,630\n"
" </span>\n"
" \n"
" <a href=\"/fleet/company-tax?modelId=1353&trimId=1365&derivativeId=1374\" class=\"tax-calculator ccd vw-btn btn-no-border\"><span class=\"vw-icon-link-small\">Get a company car tax quote</span></a>\n"
" <br>\n"
" \n"
" </td>")
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